{"schedule": {"version": "0.1", "base_url": "https://pretalx.earthmonitor.org/global-workshop-2026/schedule/", "conference": {"acronym": "global-workshop-2026", "title": "Open-Earth-Monitor Global Workshop 2026", "start": "2026-10-07", "end": "2026-10-09", "daysCount": 3, "timeslot_duration": "00:05", "rooms": [{"name": "Aula Magna", "guid": null, "description": null, "capacity": 170}, {"name": "Rooms 12+14", "guid": null, "description": null, "capacity": 70}, {"name": "Room 18", "guid": null, "description": null, "capacity": 40}], "days": [{"index": 1, "date": "2026-10-07", "day_start": "2026-10-07T04:00:00+02:00", "day_end": "2026-10-08T03:59:00+02:00", "rooms": {"Aula Magna": [{"id": 534, "guid": "66e568aa-439e-5228-9211-815c202f20e0", "logo": "", "date": "2026-10-07T10:00:00+02:00", "start": "10:00", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-534-keynote", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/HWVSXP/", "title": "Keynote", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Keynote Lecture by Matteo Mattiuzzi. Abstract and title to be provided.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 536, "code": "PGGXWC", "public_name": "Matteo Mattiuzzi", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 535, "guid": "4a660c24-8912-54ad-8dea-6696a501a31c", "logo": "", "date": "2026-10-07T10:30:00+02:00", "start": "10:30", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-535-understanding-the-3d-signatures-of-forests-across-the-planet-with-open-eo", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/USFXYN/", "title": "Understanding the 3D Signatures of Forests Across the Planet with Open EO", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "The creatures of our world depend on forests - living structures that provide habitat, food, and water. We draw meaning from trees that shape our perspectives about nature. Now, with access to unprecedented technology, we can understand more complex aspects of tree structure - the architectural form - that were previously hidden. Accurately quantifying forest structure is crucial for assessing climate change mitigating strategies and for guiding conservation efforts.  \r\n\r\nHere, we explore how we use cutting-edge 3D laser mapping from below and above the canopy to understand trees and forest structure around the world. As part of the Global Terrestrial Laser Scanning (GTLS, global-tls.net) Database initiative, we are collecting ultra-high resolution 3D structural data in forests in unprecedented detail - leveraging this rich dataset for updated tree-level scaling, architecture, and biomass. To complement this work, we are looking at the forest canopy from above at a global scale with the NASA / UMD Global Ecosystem Dynamics Investigation (GEDI) to capture and investigate vertical structural signatures of different forests across the planet.  \r\n\r\nWe are now beginning to understand the dimensions of how a more comprehensive understanding of tree and forest architecture has direct implications for accurate carbon accounting, habitat mapping, and biodiversity conservation. Moving forward we will apply our newly developed 3D tree traits to inform structural characterizations of forests with GEDI, while continuing to fill data gaps by collecting ground-based laser scanning data at new sites around the world.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 537, "code": "EXVQGF", "public_name": "Atticus Stovall", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 441, "guid": "617a2fe6-c901-5dfa-885d-0021c9f0727e", "logo": "", "date": "2026-10-07T11:00:00+02:00", "start": "11:00", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-441-opportunities-and-challenges-of-mapping-soils-with-eo-for-large-areas", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/GVGR7V/", "title": "Opportunities and challenges of mapping soils with EO for large areas", "subtitle": "", "track": "Soil, water and agriculture", "type": "Keynote lecture", "language": "en", "abstract": "Healthy soils are an indispensable natural resource providing many ecosystem services, such as producing biomass to secure our food supply, storing large amounts of carbon \u2013 a higher amount with respect to forests worldwide \u2013 storing and purifying our drinking water, and providing a habitat for a variety of organisms. At the same time, soils are a limited, non-renewable and irreplaceable natural resource.\r\n\r\nIn this context, the EU Soil Strategy for 2030 outlines the path to healthy soils in Europe by 2050 through\r\nvoluntary and legislative measures by Member States, leading to the approval of the Soil Monitoring Law\r\nin 2025. Member States are carrying out a variety of activities to activate their existing expertise in soil\r\nmonitoring and promote technologies such as optical and SAR remote sensing, to be used in this frame.\r\n\r\nCurrently, there are several initiatives and projects that explore the potential of Earth Observation for soil\r\nmapping and monitoring for large areas. This will open the path to establish an operational service for soil information that could be available for the public, such as the ones provided in the frame of Copernicus Land Monitoring Service. In this talk, we address the opportunities and challenges of mapping soils with\r\noptical Earth Observation including spaceborne imaging spectroscopy and try to answer the following\r\nquestions: Which technological developments have been achieved in the last decades? What steps are\r\nnecessary to establish a robust Earth observation-based monitoring system for soils? And especially, how can the imaging spectroscopy community contribute to this process?\r\n\r\nThe talk presents the demand for soil-related information, which, depending on the application, must fulfil various spatial and temporal requirements, as well as a specific level of detail. One of the major\r\nchallenges is developing methods and techniques that can handle the heterogeneous regional\r\ncharacteristics of the landscape. We present examples of regionalized models for temporal bare soil\r\ncompositing in Europe to be used as an important input data set (Karlshoefer et al., 2025) and local\r\nensemble models for soil organic carbon estimation in Germany (Broeg et al., 2024). Another challenge\r\ninvolves the coverage and repetition of imaging spectroscopy data, as monitoring soil erosion requires\r\nfrequent updates on vegetation coverage. In such cases, using multispectral and hyperspectral data in\r\ncombination with deep learning algorithms to obtain sub-pixel information about vegetation cover (i.e.,\r\nfractional vegetation cover) is promising (Schwind et al., 2024). Finally, estimating the accuracy and\r\nuncertainty of information products, especially those covering large areas remains challenging. Often,\r\nvalidation data is scarce and unsuitable for the accuracy assessments of large areas. We discuss various\r\nstrategies of assessing accuracy, such as producing pixel-wise uncertainty maps (Ochoa et al., 2025),\r\nevaluating the mapping methods itself (Karlshoefer et al., 2025) and developing UAV-based strategies\r\nwith high transferability potential.\r\n\r\nThe described strategies address the typical challenges of processing large areas, such as countries or\r\ncontinents, which include regional differences and data scarcity. It is crucial to expand the scientific scope in order to overcome these challenges and provide frequent, accurate and reliable soil data for\r\nextensive regions.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 471, "code": "8C89U3", "public_name": "Dr. Uta Heiden", "biography": "Dr. Uta Heiden brings over 20 years of expertise in airborne and spaceborne imaging spectroscopy. Her current work centers on using imaging spectroscopy and multispectral data archives to extract information on soils and soil\u2013vegetation cover, with applications ranging from soil erosion assessment to soil property mapping. A key focus of her research is exploring sensor synergies \u2014 especially the integration of imaging spectroscopy \u2014 to enable large-scale, frequent monitoring of soil systems. She is a senior scientist at the Remote Sensing Technology Institute of the German Aerospace Center (DLR), and she also serves as Science Coordinator for the hyperspectral DESIS mission and as a member of the EnMAP Science Advisory Group. In recognition of her longstanding contributions to the community, she has been honored with, for example, the prestigious IEEE Senior Member status and she holds the senior scientist status of the German Aerospace Center.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 536, "guid": "cb6e9c7e-7ada-59f5-bda2-20d1e4edfb3e", "logo": "", "date": "2026-10-07T11:30:00+02:00", "start": "11:30", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-536-keynote", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/CNMX9F/", "title": "Keynote", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Keynote talk by Markus Reichstein. Abstract and title to be provided.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 538, "code": "VSJARK", "public_name": "Markus Reichstein", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 454, "guid": "d951cd98-ebd7-5051-a01d-38c6ed6a64fa", "logo": "", "date": "2026-10-07T12:30:00+02:00", "start": "12:30", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-454-the-role-of-small-satellites-in-strengthening-innovative-use-caes-within-the-framework-of-the-catalonia-space-strategy", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/GCCBPS/", "title": "The role of small satellites in strengthening innovative use caes within the framework of the Catalonia Space Strategy", "subtitle": "", "track": "Soil, water and agriculture", "type": "Keynote lecture", "language": "en", "abstract": "Over the past five years, the Government of Catalonia has made a firm and sustained commitment to developing a competitive and innovation\u2011driven space sector. This effort has combined Catalonia\u2019s strong capabilities in digital technologies, scientific research and industrial engineering with coordinated collaboration across public institutions, universities, research centres and private companies.\r\nAs part of this initiative, several small satellite missions for communications and Earth observation, such as the GENIOT and GENEO series, have been deployed with supporting ground infrastructure and data platforms. Initially conceived as technology demonstrators, these missions have enabled the validation of operational capabilities and the development of innovative services in areas such as disaster risk management, environmental monitoring and territorial management among others.\r\nThis talk presents the role of small satellites in enabling innovative use cases highlighting the supporting infrastructure, service adoption and future developments under the Catalonia Space 2030 Strategy, approved in November 2025, which foresees the deployment of eight satellite missions by 2030 focused on Earth observation and advanced communications and resilience\u2011oriented applications.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 484, "code": "JN9F8A", "public_name": "Estefania Blanch", "biography": "Estefania Blanch is the Earth Observation Manager at the Area for the Promotion of the Space Sector of Catalonia (APEC) at the Institute of Space Studies of Catalonia (IEEC), where she supports the implementation of Catalonia\u2019s Space Strategy. Her work focuses on promoting the use of satellite data to address real-world challenges such as water management, agriculture, natural hazards, and environmental monitoring. At the IEEC\u2019s Office for Industrial Services and Promotion, she coordinates activities related to Earth observation, helps define satellite-based services, and fosters collaboration between public institutions, industry, and research. With a background in geophysics (PhD) and space studies (MSc), she works to bring the benefits of space technology closer to society and to strengthen the space sector in Catalonia.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 537, "guid": "67c0a011-6b5b-5913-9152-12fe2637761e", "logo": "", "date": "2026-10-07T13:00:00+02:00", "start": "13:00", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-537-keynote", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/HZRYT7/", "title": "Keynote", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Keynote talk by Johan van den Hoogen. Abstract and title to be provided", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 539, "code": "EV9YP7", "public_name": "Johan van den Hoogen", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 491, "guid": "b4f98937-1745-59bb-929a-25becaff28ed", "logo": "/media/global-workshop-2026/submissions/E9SDB8/Screenshot_from_2026-03-31_21-36-03_d4PaCMc.png", "date": "2026-10-07T13:30:00+02:00", "start": "13:30", "duration": "00:15", "room": "Aula Magna", "slug": "global-workshop-2026-491-quantification-of-temporal-changes-in-earth-observation-based-estimates-examples-with-soil-carbon-above-ground-biomass", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/E9SDB8/", "title": "Quantification of temporal changes in Earth-Observation-based estimates: examples with soil carbon & above ground biomass", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "Statistical modeling and uncertainty analysis plays a critical role in evaluating climate and environmental data. Concepts such as standard error of the mean and design-based estimation seem to be increasingly used to manipulate prediction errors and tradable changes. Advanced trend estimation and change-point models are essential for accurately identifying long-term shifts in essential climatic variables such as soil organic carbon and above ground biomass. Subtracting two above-ground biomass (AGB) maps can create false data because map uncertainties propagate into the difference, compounding the errors from both individual maps and inflating apparent change signals. Rather than revealing true environmental dynamics, naive subtraction often produces an apparent \"change\" that is actually just statistical noise. Quantile Regression Random Forests (QRRF) offer a powerful, non-parametric approach to estimating the true distribution of errors by retaining all observations within the terminal leaf nodes of the forest, rather than just calculating the conditional mean. This allows the model to estimate the full conditional cumulative distribution function and extract specific percentiles to form prediction intervals. We demonstrate how this method can be used to determine tradable carbon sequestration without taking additional risks.", "description": "This work is based on the following funding sources / projects:\r\n- AI4SoilHealth: Accelerating collection and use of soil health information using AI technology to support the Soil Deal for Europe and EU Soil Observatory: https://cordis.europa.eu/project/id/101086179\r\n- Intergenerational Open Geospatial Carbon Registry - Open-Source Tools for Connecting EU Agricultural Policies (CAP) and Carbon Removals and Carbon Farming (CRCF) Regulation to national inventories and carbon markets: https://cordis.europa.eu/project/id/101218854", "recording_license": "", "do_not_record": false, "persons": [{"id": 1, "code": "8QMFTU", "public_name": "Tom Hengl (OpenGeoHub)", "biography": "Tom has more than 25 years of experience as an environmental modeler, data scientist and spatial analyst. Tom has a background in soil mapping and geo-information science (PhD at Wageningen University / ITC). He continuously runs hands-on-R training courses to promote use of Open Source software for spatial analysis / spatial modeling purposes. He is currently the project leader of the Open-Earth-Monitor project (https://doi.org/10.3030/101059548) and Director at the OpenGeoHub foundation. Tom is recipient of the Clarivate Highly Cited Researchers for 2021, 2022, 2023, 2024 and 2025. Several of his paper have received the best paper awards including the \"Finding the right pixel size\" (https://doi.org/10.1016/j.cageo.2005.11.008), \"Soil property and class maps of the conterminous USA\" (https://doi.org/10.2136/sssaj2017.04.0122), his articles published in PeerJ are among top 10 most cited of all time; his PLOS One paper (https://doi.org/10.1371/journal.pone.0169748) is listed among the most cited in the field.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 469, "guid": "7b74f7f1-9771-53e9-87c3-63f5ae89d3e3", "logo": "", "date": "2026-10-07T15:00:00+02:00", "start": "15:00", "duration": "00:15", "room": "Aula Magna", "slug": "global-workshop-2026-469-bridging-data-methods-and-user-uptake-in-global-biomass-mapping-an-open-framework-for-validation-estimation-and-inter-comparison", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/K77QLY/", "title": "Bridging Data, Methods and User-Uptake in Global Biomass Mapping: An Open Framework for Validation, Estimation and Inter-Comparison", "subtitle": "", "track": "Forest and biodiversity", "type": "Oral talk", "language": "en", "abstract": "The growing availability of global aboveground biomass (AGB) maps from Earth Observation (EO) is changing how carbon stocks can be quantified, monitored and reported. Rapid advances in EO, cloud computing and GeoAI have expanded the range of available products, from coarse-resolution long time series to emerging global maps at up to 10 m resolution. At the same time, inconsistencies in spatial support, temporal coverage, modeling approach and uncertainty structure continue to limit comparability and reduce confidence in their use for carbon accounting, climate reporting, REDD+ and other policy-facing applications. What is increasingly needed is not simply more biomass maps, but a framework that can validate them consistently, explain where they differ and clarify what those differences mean for actual use.\r\nThis contribution presents an integrated framework developed within the Open-Earth-Monitor ecosystem with four connected components: (1) a harmonized global biomass reference dataset, AGBref; (2) a validation and estimation framework that explicitly accounts for spatial uncertainty and representativeness; (3) a systematic inter-comparison of global AGB maps across methods, resolutions and epochs; and (4) demonstrations of how product differences affect downstream uptake. A key novelty is the use of AGBref across all components. AGBref combines National Forest Inventories, permanent plots and airborne LiDAR-derived biomass maps in a multi-epoch, multi-resolution reference system with uncertainty information, providing a common backbone for independent validation and more transparent interpretation of biomass products. The framework moves beyond validation based only on global summary statistics. In addition to agreement with reference data, it examines how biomass products represent spatial heterogeneity and landscape structure. This is particularly important with the emergence of very high-resolution biomass maps, which may show similar overall accuracy but still differ substantially in the spatial patterns they reproduce. \r\nUse cases are central to the framework. It responds to a clear demand for biomass information that is not only more accurate, but also more comparable, operational and easier to integrate into existing analytical systems. For example, WRI identifies the best available biomass dataset that can strengthen forest carbon stock and emissions assessment, support biomass change analysis, and remain compatible with Global Forest Watch workflows and baseline forest change products. For OECD, the need is similar but framed through environmental indicators, LULUCF-related analysis, and SEEA-based accounting, where one consistent and transparent dataset is preferred over multiple competing products. In both cases, independent validation, comparability with national data, open access, interoperability and regular updates are core conditions for uptake.\r\nThe framework is therefore designed not only to compare maps, but also to test their implications for reporting and accounting contexts. One priority application is carbon accounting across overlapping but distinct frameworks such as UNFCCC reporting and SEEA-based environmental accounting. These frameworks share a need for spatially explicit, transparent and comparable biomass information, yet differ in accounting logic, reporting purpose, and treatment of stocks and changes. The framework creates a basis for examining how the same EO-based biomass product performs across these contexts, where comparability holds, and where important differences emerge. This is especially relevant for countries with limited or infrequent National Forest Inventory data, and for recurrent accounting processes that require methods and datasets that can be updated regularly and consistently through time.\r\nTo support uptake, the framework is implemented through open, cloud-based tools such as Plot2Map within ESA-MAAP, enabling reproducible integration of plot-level reference data with large-scale EO products for validation, visualization and comparison. The platform also serves as a demonstration space for testing how biomass products can support institutional needs in global forest assessment, environmental indicators, policy analysis, SEEA and LULUCF applications, and country-facing monitoring workflows. This is particularly relevant for users such as WRI, OECD and national agencies that require transparent, scalable, open and regularly updateable biomass information.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 100, "code": "HD3CLP", "public_name": "Arnan Araza", "biography": "Postdoc at Earth Systems and Global Change, Wageningen University & Research and Global Land Monitoring of Remote Sensing and Geoinformatics of GFZ German Research Centre for Geosciences", "answers": []}, {"id": 422, "code": "A8MUFY", "public_name": "Martin Herold", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 502, "guid": "da070629-4835-5b9b-9165-d507a2f9fa9b", "logo": "/media/global-workshop-2026/submissions/7DU3RA/Iris_Luik_2025_ametifoto_b66k005.jpg", "date": "2026-10-07T15:15:00+02:00", "start": "15:15", "duration": "00:15", "room": "Aula Magna", "slug": "global-workshop-2026-502-monitoring-herbaceous-biomass-and-restoration-of-semi-natural-grasslands-using-machine-learning-on-sentinel-1-and-sentinel-2-imagery", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/7DU3RA/", "title": "Monitoring herbaceous biomass and restoration of semi-natural grasslands using machine learning on Sentinel-1 and Sentinel-2 imagery", "subtitle": "", "track": "Forest and biodiversity", "type": "Oral talk", "language": "en", "abstract": "Semi-natural grasslands are critical ecosystems that provide a range of essential services, with their role as habitats for diverse species being among the most significant. However, over the past century, semi-natural grasslands that once covered vast areas across Europe have largely been transformed into intensively managed agricultural lands, abandoned, or converted into forests. These large-scale land-use changes have led to considerable biodiversity loss, making the conservation and restoration of semi-natural grasslands an important component of sustainable landscape management. \r\n\r\nWe utilized 97 in-situ herbaceous biomass samples collected during the summer of 2019 from alvar grasslands in Western Estonia, all restored between 2015 and 2019. Samples were collected from 20 \u00d7 20 cm plots nested within 2 \u00d7 2 m botanical plots. Sentinel-1 and Sentinel-2 imagery from the same period was used, with median band values and derived indices (e.g., NDVI, BSI, SAVI, VH/VV) included as predictors. \r\n\r\nRandom Forest models were developed using Sentinel-1 and Sentinel-2 spectral bands and derived indices as predictors. Model robustness was evaluated using 5-fold cross-validation. Two approaches for linking field and satellite data were tested: point sampling and a 3 \u00d7 3 kernel mean, with point sampling performing slightly better. \r\n\r\nThe model achieved an RMSE of 98 \u00b1 54 g/m\u00b2, an MAE of 71 \u00b1 30 g/m\u00b2, and an R\u00b2 of 0.32 \u00b1 0.08, reflecting the high spatial variability of semi-natural grasslands. SHAP analysis identified SAVI, NDVI, and the vegetation red edge band B8A as the most important predictors, while Sentinel-1 variables contributed less to model performance. \r\n\r\nThese results highlight the dominant role of optical data in herbaceous biomass estimation and demonstrate that simple point-based sampling can outperform spatial averaging approaches. The proposed methodology provides a practical and scalable solution for monitoring grassland restoration.", "description": "This study explores the use of freely available Sentinel-1 and Sentinel-2 data combined with machine learning for monitoring the restoration of semi-natural alvar grasslands in Estonia. Alvar grasslands present a challenging case due to their high spatial heterogeneity and patchy vegetation structure. \r\n\r\nParticular attention is given to how field and satellite data are linked, comparing point-based sampling with a 3 \u00d7 3 kernel mean approach. This provides practical insight into how methodological choices influence model performance. \r\n\r\nThe results highlight the importance of optical data and demonstrate a simple, transferable approach for large-scale monitoring of semi-natural grassland restoration.", "recording_license": "", "do_not_record": false, "persons": [{"id": 513, "code": "MXM8GC", "public_name": "Iris Luik", "biography": "I am a PhD researcher in geoinformatics at the University of Tartu, focusing on the use of remote sensing and machine learning to monitor landscape processes and support ecosystem conservation and restoration.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 494, "guid": "b12282d6-d79d-515b-a9de-714789b3fceb", "logo": "", "date": "2026-10-07T15:30:00+02:00", "start": "15:30", "duration": "00:15", "room": "Aula Magna", "slug": "global-workshop-2026-494-understanding-vegetation-climate-relationships-using-geoai-a-spatiotemporal-analysis-in-the-ebro-river-basin", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/9WB3A7/", "title": "Understanding Vegetation\u2013Climate Relationships Using GeoAI: A Spatiotemporal Analysis in the Ebro River Basin", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "Vegetation in terrestrial ecosystems plays a key role in the carbon cycle, and understanding its spatiotemporal patterns and associated drivers is crucial for ecological research. This study explores the relations between remote sensing vegetation Gross Primary Production (GPP) and climate explanatory variables such as the Standardized Precipitation Evapotranspiration Index (SPEI) and soil moisture anomalies (SMA). \r\n\r\nThe study focused on the climatically diverse Ebro River basin (85,600 km\u00b2), Spain's river largest catchment, using monthly data from 2016 to 2024. The area is bounded between the three meteorological domains of this region of SW Europe: Atlantic, European continental and Mediterranean. \r\n\r\nDuring the processing phase, harmonized monthly products at 1 km spatial resolution were generated from multiple satellite and in-situ sources. GPP was aggregated from the MOD17A2HGF product, SPEI was derived in-situ meteorological data (Trypidaki et al 2024) by AEMET, and monthly SMA were computed from Sentinel-1 synthetic aperture radar (SAR) data using a dual-polarization algorithm (DPA) (Fan et al. 2025).\r\n\r\nWe explore vegetation\u2013climate relationships using correlation and GeoAI ML approaches, including Random Forest (caret R package) and Accumulated Local Effects (ALEPlots R package) between GPP and climate variables. Model stability and variable importance were evaluated using multiple metrics.\r\n\r\nOur findings highlight the potential, requirements and limitations of GeoAI tools compared to classical statistical methods, in handling nonlinear relationships and multicollinearity.\r\n\r\nReferences: \r\n\r\nFan, D., Zhao, T., Jiang, X., Garc\u00eda-Garc\u00eda, A., Schmidt, T., Samaniego, L., Attinger, S., Wu, H., Jiang, Y., Shi, J., Fan, L., Tang, B.-H., Wagner, W., Dorigo, W., Gruber, A., Mattia, F., Balenzano, A., Brocca, L., Jagdhuber, T., \u2026 Peng, J. (2025). A Sentinel-1 SAR-based global 1-km resolution soil moisture data product: Algorithm and preliminary assessment. Remote Sensing of Environment, 318, 114579. https://doi.org/10.1016/j.rse.2024.114579\r\n\r\nTrypidaki E., Pesquer L., Domingo-Marimon C, \"Spatiotemporal Analysis for Enhanced Drought Monitoring and Agricultural Applications in the Ebro Basin, Spain,\" 2024 IEEE International Workshop on Metrology for Agriculture and Forestry (MetroAgriFor), Padua, Italy, 2024, pp. 603-608, https://doi.org/10.1109/MetroAgriFor63043.2024.10948835", "description": "", "recording_license": "", "do_not_record": true, "persons": [{"id": 369, "code": "DJGGM9", "public_name": "Eirini Trypidaki", "biography": "Eirini Trypidaki is a predoctoral Researcher at CREAF and member of the Methods and Applications in Remote Sensing and Geographic Information Systems (GRUMETS) research group. \r\n\r\nHer work focuses on the development and refinement of methodologies for high-resolution drought monitoring, with an emphasis on advancing the operational use of environmental data. \r\n\r\nThis research is closely aligned with the objectives of the Open Earth Monitor (OEMP) project and highlights the practical applications of high-resolution Earth observation in sectors such as agriculture, insurance, and reinsurance.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 486, "guid": "e694d9d7-d64c-5a0a-a8f9-bdc2b282647a", "logo": "", "date": "2026-10-07T15:45:00+02:00", "start": "15:45", "duration": "00:15", "room": "Aula Magna", "slug": "global-workshop-2026-486-key-biophysical-variables-for-forest-monitoring-in-catalonia", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/UMRHWT/", "title": "Key biophysical variables for forest monitoring in Catalonia", "subtitle": "", "track": "Forest and biodiversity", "type": "Oral talk", "language": "en", "abstract": "In alignment with the European Green Deal\u2019s strategies, forest monitoring is crucial to fill the existing information gaps and create a comprehensive forest knowledge base.  Based on the 4th Spanish National Forest Inventory collections updated in 2017, we assessed remote sensing data derived from various sources as complementary information to support forest ecosystem monitoring in Catalonia over the last decade.  Our study areas focused on regional natural parks designated by Natura 2000 where deciduous tree species (Fagus sylvatica, Castanea sativa) are well represented to analyse key biophysical variables known as Essential Biodiversity Variables (EBVs) such as LAI and FAPAR.  The data products compared in this study include high-resolution vegetation maps with new algorithms provided through cloud-based platforms such as Copernicus Data Space Ecosystem and Google Earth Engine.   Specifically, we referenced Sentinel-2 based EBVs from BioPAR by VITO and World Reforestation Monitor by ETH Zurich. In discussion our challenges and opportunities associated with data interoperability and quality are addressed.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 116, "code": "K7TRMJ", "public_name": "Kaori Otsu", "biography": "Research Group Methods and Applications in Remote Sensing and Geographic Information Systems (GRUMETS) at CREAF", "answers": []}, {"id": 205, "code": "3QHGZS", "public_name": "Imma Serra", "biography": "Research technician at the Centre for Ecological Research and Forestry Applications (CREAF) in the research group of Remote Sensing and Geographic Information Systems (GRUMETS).", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 484, "guid": "695ab9b1-28e2-5484-b92c-49dc86aa17cd", "logo": "", "date": "2026-10-07T16:00:00+02:00", "start": "16:00", "duration": "00:15", "room": "Aula Magna", "slug": "global-workshop-2026-484-satellite-based-anomaly-detection-using-geoai-embeddings-a-scalable-workflow", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/CDLLLB/", "title": "Satellite-Based Anomaly Detection using GeoAI Embeddings: A Scalable Workflow", "subtitle": "", "track": "Climate and Health", "type": "Oral talk", "language": "en", "abstract": "This study explores the application of high-dimensional embeddings derived from Sentinel-2 imagery for automated anomaly detection in environmental monitoring. By utilizing the SSL4EO self-supervised learning framework, we transform raw satellite data into compact, informative representations that capture essential spatial and temporal features. The entire workflow is integrated within the Copernicus Data Space Ecosystem (CDSE), ensuring efficient access to large-scale, analysis-ready archives and enabling rapid processing of planetary-scale datasets. \r\n\r\nThe core of our approach lies in leveraging SSL4EO to bypass the need for massive labeled datasets, creating a standardized intermediate format that bridges raw imagery with advanced AI tasks. These embeddings serve as the foundation for an anomaly detection pipeline designed to pinpoint deviations from expected seasonal or spatial trends, such as flooding, wildfires, or shifts in vegetation health. To ensure interoperability and ease of use in geospatial analytics, results are stored in the GeoParquet format, which supports both reproducibility and high-performance data handling. \r\n\r\nTo confirm the framework's robustness, we conducted extensive validation across diverse geographical regions and seasonal cycles, including challenging winter conditions with snow cover and low solar illumination. The pipeline demonstrated high resilience, producing consistent embeddings even in the presence of partial cloud cover. Furthermore, we evaluated the system\u2019s portability across heterogeneous computing environments. Testing on the CREODIAS cloud platform (using both CPU and GPU nodes) alongside high-performance computing (HPC) infrastructures like EOHPC and SpaceHPC proved that the solution scales effectively and maintains functional integrity across different hardware architectures. \r\n\r\nThe results indicate that combining self-supervised embeddings with anomaly detection creates a powerful tool for environmental intelligence. The proposed framework is suitable for a wide range of operational applications, from tracking urban growth to monitoring climate-induced environmental changes. By providing a portable and scalable bridge between raw Copernicus data and actionable insights, this study highlights the transformative potential of GeoAI in supporting global and regional decision-making processes.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 507, "code": "LEM9GS", "public_name": "Marcin Kluczek", "biography": "Dr. Marcin Kluczek is a cloud computing and GeoAI expert serving as the Tech Lead for the EO Algorithms Team at CloudFerro S.A. He specializes in architecting scalable solutions for processing massive satellite constellations, focusing on AI-driven embeddings and foundational models. Marcin combines deep technical leadership with an academic background to push the boundaries of how we analyze Earth Observation data at scale, ensuring that complex algorithms run efficiently in cloud-native environments.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 504, "guid": "2dda8dad-a85a-5dc9-b4fe-89954cc2edf1", "logo": "", "date": "2026-10-07T17:00:00+02:00", "start": "17:00", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-504-the-impact-of-adaptive-silviculture-on-the-spectral-response-and-drought-resilience-of-mediterranean-pine-forests-in-spain", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/JRPSQY/", "title": "The impact of adaptive silviculture on the spectral response and drought resilience of Mediterranean pine forests in Spain", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "Mediterranean pine reforestations are increasing its vulnerability to climate change, particularly to recurrent drought events -as raising tree decline and mortality rates have been identified-. In Spain, decades of limited forest management have contributed to mature dense stands characterized by high water stress and reduced ecosystem resilience. In this context, adaptive silviculture emerges as a key strategy to enhance forest stability under changing environmental conditions.\r\nThis study evaluates the effects of thinning treatments on the eco-resilience of mature pine plantations across Spain by integrating field data and multi-source remote sensing observations. First, spectral information derived from vegetation indices (e.g., NDVI, EVI or NBR) and shortwave infrared bands (SWIR1) are analyzed for detecting forest cover reduction promoted by thinning. Second, these observations and the Standardized Precipitation Evapotranspiration Index (SPEI) are used for assessing how adaptive silviculture modulates forest responses to drought events. Third, dendrochronological data are incorporated to compare radial growth patterns with spectral dynamics, enabling cross-validation between traditional growth-based approaches and remote sensing indicators to evaluate forest resilience. Results show that forest management induces measurable changes in the spectral behavior, and that treated stands exhibit faster recovery dynamics following extreme droughts compared to unmanaged stands.\r\nBeyond these findings, the current study aims to frame ongoing research towards a more integrative assessment of forest resilience, combining spectral indicators with structural and ecohydrological perspectives. This approach seeks to advance the development of scalable indicators of eco-resilience, supporting forest management strategies under future climate scenarios.", "description": "This study has been addressed for Marina Mu\u00f1iz Mart\u00ednez as student and Antonio Jaime Molina Herrera as supervisor in the context of a Master's tesis.", "recording_license": "", "do_not_record": false, "persons": [{"id": 515, "code": "FF9XZM", "public_name": "Marina Mu\u00f1iz Mart\u00ednez", "biography": "Environmental data analyst and geospatial scientist with experience in large-scale datasets, spatial\r\nmodelling and Earth Observation. Strong background on EU research projects handling multi-source\r\ndata integration, processing and automation of analytical workflows (skilled in Phyton, R and Google\r\nEarth Engine), and producing decision-suport outputs (maps, visual graphs, presentations) for policy\r\nmakers, technical groups and general stakeholders.\r\n\r\nI am currently working for CREAF as  Research Technician in the SEACURE Project, addressing nutrient pollution in Mediterranean river basins\u00a0through the integration of environmental datasets across multiple administrative and ecological levels. More specifically, my work involves developing terrestrial nutrient budgets at the river basin scale to identify critical pollution hotspots and nutrient flux pathways, as well as producing high-resolution cartographic outputs to support evidence-based decision-making.\r\n\r\nI did my master in the University of C\u00f3rdoba focusing on geomatics and remote sensing techniques applied to forest management, and this work that I am presenting here belongs to the final thesis developed for my masters.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 488, "guid": "978537c5-6d99-5e46-9167-94a23be9bd16", "logo": "", "date": "2026-10-07T17:10:00+02:00", "start": "17:10", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-488-s2biophys-a-global-annual-20-m-dataset-of-vegetation-biophysical-properties-from-sentinel-2", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/GDJSPB/", "title": "S2BIOPHYS: A Global Annual 20 m Dataset of Vegetation Biophysical Properties from Sentinel-2", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "We present S2BIOPHYS, the first global dataset of annual vegetation biophysical properties (LAIe, FAPAR, FCOVER) at 20 m resolution from Sentinel-2 (2019\u20132025). The product combines radiative transfer model inversion with iterative hyperparameter optimization using in-situ calibration and validation data. It provides per-pixel estimates with uncertainty and observation counts, validated against over 11,000 ground measurements. S2BIOPHYS enables scalable monitoring of ecosystem condition, restoration, and biodiversity.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 169, "code": "S8BPN9", "public_name": "Felix Specker", "biography": "TODO", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 487, "guid": "da2140dc-96e6-5feb-892d-c92578887390", "logo": "", "date": "2026-10-07T17:15:00+02:00", "start": "17:15", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-487-unraveling-patterns-and-drivers-of-global-forest-restoration-success-using-remote-sensing", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/RDHLEE/", "title": "Unraveling patterns and drivers of global forest restoration success using remote sensing", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "Understanding where and why forest restoration succeeds remains a key challenge for global monitoring and policy. This project investigates how satellite-based indicators of vegetation structure and function can capture restoration outcomes across spatial scales. We combine global remote sensing data with contextual information on climate, landscape configuration, and human pressure to identify drivers of restoration success and compare intervention strategies. The results aim to inform scalable, operational approaches for monitoring forest recovery and supporting evidence-based restoration efforts worldwide.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 169, "code": "S8BPN9", "public_name": "Felix Specker", "biography": "TODO", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 490, "guid": "f167da3d-bb68-5034-92bd-8ca9c1382b36", "logo": "", "date": "2026-10-07T17:15:00+02:00", "start": "17:15", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-490-eo-processes-and-workflows-with-xcube", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/JRQQU8/", "title": "EO processes and workflows with xcube", "subtitle": "", "track": "Soil, water and agriculture", "type": "Poster presentation", "language": "en", "abstract": "We present recent developments in the xcube ecosystem motivated by its involvement in the Open Earth Monitor project, focusing on xcube server processing facilities and integration into scalable cloud workflows. We describe xcube server's established and newly-implemented API implementations and processing facilities, with particular attention to OGC API \u2013 Processes, openEO, the relationship to the eozilla processing framework, and applicability to Open Earth Monitor science use cases. These capabilities are complemented by further developments in the associated xcengine package, which converts Jupyter notebooks into EO application packages. With these developments, xcube, eozilla, and xcengine provide a powerful and versatile toolkit for developing and deploying EO workflows, both locally and in the cloud.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 198, "code": "DMPAEC", "public_name": "Pontus Lurcock", "biography": "Pontus Lurcock is a software engineer at Brockmann Consult GmbH., with a strong focus on geodatacubes and analysis-ready earth observation data. He has extensive experience of working at the interface between informatics and geosciences, and holds an MSc in Computer Science and a PhD in Geology.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 485, "guid": "0b76809d-6bc7-5d95-9f0c-b425fc6b2853", "logo": "", "date": "2026-10-07T17:20:00+02:00", "start": "17:20", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-485-comparing-foundation-model-embeddings-and-phenology-informed-feature-engineering-for-temporally-consistent-mapping-of-savanna-vegetation-structure", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/KZU8DF/", "title": "Comparing Foundation Model Embeddings and Phenology-Informed Feature Engineering for Temporally Consistent Mapping of Savanna Vegetation Structure", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "Savanna ecosystems cover approximately one fifth of Earth's land surface and provide critical ecosystem services to over one billion people, yet their dynamic vegetation layer remains difficult to monitor consistently at scale. Spaceborne lidar from the Global Ecosystem Dynamics Investigation (GEDI) mission provides vegetation structure measurements, such as canopy height and cover, but its spatially sparse sampling necessitates extrapolation using satellite remote sensing data. Temporal consistency of these wall-to-wall mapping products remains a key challenge, particularly in heterogeneous savanna systems characterized by pronounced seasonality and complex disturbance dynamics.\r\nThis study compares two approaches for mapping GEDI-derived canopy height and cover across Kruger National Park, South Africa. The first uses hand-crafted Sentinel-1/2 features derived from phenology-informed time series analysis. The second uses TESSERA foundation model embeddings (pixel-wise representations of annual Sentinel-1/2 time series) as open, analysis-ready features with lightweight regression heads. Both approaches use phenology-aligned GEDI samples anchored to leaf-on conditions as training data, and are evaluated using temporal cross-validation and independent airborne lidar data acquired across multiple sites in the study area, with particular focus on temporal transferability and label efficiency.\r\nThe comparison addresses a question of growing practical relevance: does explicit phenological knowledge embedded in task-specific feature engineering outperform the implicit temporal representations learned by large-scale foundation models, and under what conditions? The results will inform scalable, open, and reproducible approaches to vegetation structure monitoring in African savannas, with direct relevance for biodiversity conservation and carbon stock assessment.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 508, "code": "RUNFBT", "public_name": "Marco Wolsza", "biography": "I am a PhD candidate at the Department for Earth Observation, Friedrich Schiller University Jena (Germany). My current research focuses on savanna vegetation structure monitoring using synthetic aperture radar, with particular interests in open-source tools and reproducible research practices. My GitHub, Fosstodon, Bluesky and LinkedIn handle is \"maawoo\". I'm happy to connect and open to new opportunities!", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 478, "guid": "7430fc98-ed22-5ce0-9552-6c182b222571", "logo": "", "date": "2026-10-07T17:30:00+02:00", "start": "17:30", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-478-standardising-terrestrial-and-uls-laser-scanning-processing-for-cross-site-data-sharing-and-applications", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/YE9XVA/", "title": "Standardising Terrestrial and ULS Laser Scanning Processing for Cross-Site Data Sharing and Applications", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "Authors: Linda Luck (GFZ), Ben Brede (GFZ), Johannes Wilk (GFZ), Arnan Araza (WUR), Geike De Sloover (UGent), Bert Gielen (University of Antwerp), Martin Herold (GFZ)\r\n\r\nTerrestrial laser scanning (TLS) and Uncrewed Aerial Vehicle laser scanning (ULS) provide highly detailed and reliable measurements of vegetation structure and have become an important tool for forest and ecosystem research. Despite its high value, openly available TLS/ULS datasets remain scarce. Previous initiatives to establish centralised data collection have faced challenges in gaining sufficient participation and maintaining long-term feasibility, highlighting the need for alternative approaches to improving accessibility and usability of TLS/ULS data.\r\n\r\nIn addition to making some of our data publicly available, we are developing a reproducible processing workflow that can be applied across sites and shared among partners. This workflow is currently being implemented for several contrasting ecosystems, including the deciduous mixed forest of Hohes Holz (Germany), the savanna ecosystem at Las Majadas (Spain), and additional sites currently under preparation. By standardising processing and derived outputs, the approach enables consistent generation of structural metrics that can be shared and integrated across projects.\r\n\r\nAs a first application example, we present the ESA Forest DTC project, where tree-level structural metrics derived from high-resolution TLS scans with manually corrected segmentation are combined with large-scale automated segmentation and feature extraction from UAV-based lidar to support ecosystem modelling.\r\n\r\nLooking ahead, cloud-based and online processing services - such as those provided by ForesSens and currently being developed within the 3D-Trees project - may represent a promising pathway for enabling broader access to TLS processing and derived products without requiring specialised local computing infrastructure.", "description": "", "recording_license": "", "do_not_record": true, "persons": [{"id": 501, "code": "MWKTCR", "public_name": "Linda Luck", "biography": "Linda Luck is a researcher at GFZ Helmholtz Centre for Geosciences, specialising in forest structure analysis using terrestrial laser scanning (TLS) and unmanned laser scanning (ULS). Her work focuses on integrating field-based forest inventory with remote sensing data to enable robust, scalable, and transferable forest metrics. She currently works on standardising processing workflows to support cross-site comparability and data sharing. Her work is informed by a multidisciplinary background in environmental and biological sciences.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 468, "guid": "9af1ac39-9a53-5259-84a0-9c446a5b43d1", "logo": "", "date": "2026-10-07T17:35:00+02:00", "start": "17:35", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-468-early-detection-of-reforestation-interventions-using-multi-sensor-satellite-time-series", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/ZWFDRC/", "title": "Early Detection of Reforestation Interventions Using Multi-Sensor Satellite Time Series", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "Large-scale reforestation is central to climate mitigation and ecosystem restoration, yet monitoring when and where restoration activities occur remains a major challenge. Existing satellite based approaches typically detect forest recovery only after canopy development, limiting their usefulness for timely monitoring, reporting, and verification (MRV) of restoration efforts.\r\nWe present a scalable framework for detecting reforestation interventions within one year of planting using multi-sensor satellite time series. The approach integrates Sentinel-1 radar and Sentinel-2 optical data to learn a characteristic temporal signature of restoration, capturing transitions from stable pre-intervention conditions to disturbance and early vegetation recovery. Training leverages a global dataset of verified reforestation sites combined with a synthetic control strategy to generate spectrally matched non restoration samples.\r\nOur results show that early stage reforestation can be identified at the pixel level across diverse climate zones, substantially improving the temporal resolution of forest monitoring. The poster will present global scale examples, model outputs, and temporal signatures illustrating how restoration signals emerge prior to canopy closure.\r\nThis work supports more timely and transparent monitoring of reforestation efforts and has direct relevance for carbon accounting, climate finance, and large-scale restoration initiatives.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 495, "code": "GEBDJ3", "public_name": "Angela John", "biography": "Am a PhD student at the University of Saarland ,working on reforestation and carbon offset monitoring", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 462, "guid": "a4cdd9f6-326c-5d17-a22c-1ec037dbca1e", "logo": "", "date": "2026-10-07T17:40:00+02:00", "start": "17:40", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-462-multi-sensor-fusion-for-large-scale-burned-area-mapping-the-role-of-nrbr", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/8YKTEM/", "title": "Multi-Sensor Fusion for Large-Scale Burned Area Mapping: The role of NRBR", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "This study presents the development and multi-regional application of the Normalized Radar Burn Ratio (NRBR), a novel Synthetic Aperture Radar (SAR)-based index designed to improve burned area detection under challenging observational conditions. Unlike traditional optical indices such as the differenced Normalized Burn Ratio (dNBR), NRBR exploits the complementary behavior of Sentinel-1 C-band co-polarized (VV: vertical transmit\u2013vertical receive) and cross-polarized (VH: vertical transmit\u2013horizontal receive) backscatter signals, enhancing the contrast between burned and unburned surfaces by capturing fire-induced structural changes in vegetation.\r\nThe NRBR formulation is based on the normalized difference between polarization-specific Radar Burn Ratios, effectively integrating post- to pre-fire backscatter dynamics while reducing speckle noise and topographic effects. Initial validation in Mediterranean ecosystems demonstrated that NRBR improves burned area delineation compared to conventional radar indices, achieving strong agreement with optical-based metrics and competitive segmentation performance when implemented within a U-Net deep learning framework.\r\nBuilding on these results, the index was further evaluated across diverse fire-prone regions including Portugal, Spain, California, and Canada, encompassing Mediterranean, chaparral, and boreal ecosystems. The results indicate that NRBR achieves performance comparable to, and in some cases exceeding, optical approaches, particularly in cloud-prone or smoke-affected conditions where optical data are limited. Additionally, a SAR\u2013optical fusion strategy combining NRBR and dNBR further improves mapping accuracy and spatial consistency at large scales.\r\nOverall, NRBR demonstrates strong potential as a robust and scalable alternative for burned area mapping, providing consistent performance across different land cover types and environmental conditions. Its cloud independence and sensitivity to vegetation structural changes position it as a valuable tool for operational wildfire monitoring and next-generation multi-sensor mapping frameworks.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 490, "code": "KDKMWE", "public_name": "Yonatan Tarazona Coronel", "biography": "PhD student at the University of Coimbra, Portugal. I am a geospatial scientist specializing in advanced Earth Observation with a core focus on Synthetic Aperture Radar (SAR) applications. I am the author of the novel Normalized Radar Burn Ratio (NRBR) index, a significant contribution to SAR-based burned area mapping. My research extensively leverages multi-sensor data fusion, integrating SAR and optical time series with machine and deep learning for detecting burned areas, deforestation, forest degradation, and other land cover changes. A skilled developer of open-source software and proficient in geocomputation with Python, R, and Google Earth Engine.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 451, "guid": "c26d87e9-054f-5d75-b9c8-794eb47947d4", "logo": "", "date": "2026-10-07T17:55:00+02:00", "start": "17:55", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-451-foundation-model-embeddings-predict-global-variation-in-forest-structural-diversity", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/VMEVPF/", "title": "Foundation-model embeddings predict global variation in forest structural diversity", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "Forest structural diversity - the spatial heterogeneity of canopy architecture across vertical and horizontal dimensions - is a fundamental component of ecosystem functioning. Yet its continuous global mapping remains constrained by the sparse orbital sampling of spaceborne LiDAR missions such as the Global Ecosystem Dynamics Investigation (GEDI). \r\nHere, we integrated globally distributed GEDI-derived structural diversity metrics  with dense-vector representations from a geospatial vision foundation model pretrained on multi-source satellite imagery. Specifically, we used the Google Satellite Embedding dataset, derived from the AlphaEarth Foundations model, which provides globally consistent 64-dimensional embeddings at 10 m resolution from multi-source satellite imagery. Our analysis spans GEDI's full tropical-to-temperate sampling domain (52\u00b0N\u201352\u00b0S), encompassing 14 major biomes from temperate conifer to tropical moist broadleaf forests.\r\nRandom forest regression models were fitted within a spatially blocked cross-validation framework stratified by biogeographic region. Cross-validated R\u00b2 was consistently high across structural diversity dimensions, with low inter-fold variance indicating robust transferability across held-out biogeographic regions. Predicted structural diversity revealed strong but metric-dependent spatial gradients, reflecting the distinct axes of canopy architecture \u2014 from height and complexity to vertical profile shape - captured across the global sampling domain.\r\nOur results demonstrate that geospatial foundation-model embeddings capture information across both vertical and horizontal dimensions of forest canopy architecture, thus providing a scalable pathway for wall-to-wall inference of forest structural diversity from existing spaceborne observations", "description": "This study presents a scalable remote sensing framework for continuous global mapping of forest structural diversity, extending inference beyond the spatial constraints of current spaceborne LiDAR missions", "recording_license": "", "do_not_record": true, "persons": [{"id": 477, "code": "AJVRU9", "public_name": "Marco Girardello", "biography": "Marco Girardello is interested in understanding how Earth's ecosystems are structured and how they are changing across space and time. He uses spaceborne LiDAR and multi-source Earth observation data to map ecosystem-level diversity at global scale, with a focus on translating dense EO data streams into ecologically meaningful products.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 442, "guid": "a062de83-d67a-50a2-8a31-c0f611d67e20", "logo": "", "date": "2026-10-07T18:00:00+02:00", "start": "18:00", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-442-a-framework-to-optimize-the-potential-restoration-achievement-and-ecosystem-services-trade-offs-applied-in-the-yellow-river-basin", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/KL7URJ/", "title": "A Framework to Optimize the Potential Restoration Achievement and Ecosystem Services Trade-offs applied in the Yellow River Basin", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "Forest and grassland restoration constitutes a central objective of global initiatives, including the United Nations Decade on Ecosystem Restoration. Nevertheless, the synergistic mechanisms and quantitative linkages between enhanced restoration potential and improved ecosystem services (ESs) remain insufficiently understood. In this study, we developed the Forest and Grassland Restoration Potential Achievement Efficiency (FGRPAE). By integrating remote sensing data, ecosystem service assessments, and nonlinear modeling, we constructed a comprehensive framework to evaluate restoration benefits in the Yellow River Basin (YRB), a representative region of large-scale ecological restoration. This framework systematically investigates the long-term spatiotemporal dynamics of FGRPAE, as well as its interactive patterns with ecosystem services and underlying nonlinear response mechanisms. The results show that FGRPAE increased at an average annual rate of 0.0083, corresponding to a cumulative growth of 53.73%. During 2000-2010, FGRPAE increased at an annual rate of 0.0096, yielding a cumulative increase of 32.45%. In contrast, from 2010 to 2020, the growth rate decelerated to 0.0063 per year, with a total increase of 16.02%, approximately 49.52% of the increase observed during 2000-2010. Concurrently, the proportion of areas exhibiting spatial trade-offs between FGRPAE and comprehensive ecosystem services (CES) rose by 76.12% between 2010 and 2020. A nonlinear enhancement relationship was identified between FGRPAE and CES. However, CES gains plateau when FGRPAE exceeds approximately 50%. This study shifts the analytical focus from restoration intensity to restoration efficiency, demonstrating that neglecting spatial trade-offs between FGRPAE and ESs may compromise the overall effectiveness of ecological restoration. Accordingly, we propose an optimized spatial configuration for restoration planning that emphasizes the integrated consideration of forest and grassland restoration potential and ecosystem service functions under resource constraints. The proposed framework supports the transition of ecological engineering from \u201carea expansion\u201d to \u201cfunction enhancement,\u201d offering actionable policy guidance for optimizing restoration strategies within ecological carrying capacity limits.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 476, "code": "WNNDMR", "public_name": "liuyuan", "biography": "A Ph.D. candidate in Forest Management, focusing on forest restoration and ecosystem services in vulnerable regions, as well as extreme climate events and their interrelationships. Committed to providing useful recommendations to government policymakers.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 435, "guid": "43e9c378-d0d6-5363-9764-00d11bfe035d", "logo": "/media/global-workshop-2026/submissions/SFZHLV/IMG_4931_dRZd8OX.JPG", "date": "2026-10-07T18:05:00+02:00", "start": "18:05", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-435-from-surface-drying-to-hydrological-response-an-integrated-diagnosis-of-flash-droughts-across-europe", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/SFZHLV/", "title": "From Surface Drying to Hydrological Response: An Integrated Diagnosis of Flash Droughts across Europe", "subtitle": "", "track": "Soil, water and agriculture", "type": "Poster presentation", "language": "en", "abstract": "Abstract\r\nFlash droughts\u2014characterized by abrupt onset and rapid soil moisture depletion\u2014are emerging as a consequential hydroclimatic extreme across Europe. Their fast evolution, strong sensitivity to atmospheric evaporative demand, and reinforcement through land\u2013atmosphere coupling challenge traditional drought monitoring approaches that were largely developed to track slowly evolving deficits. Despite growing attention, continental-scale understanding of how flash droughts initiate, propagate, and vary across Europe\u2019s diverse climate regimes remains limited.\r\nHerein, we propose a framework for flash drought detection and characterization using three complementary soil moisture perspectives: ASCAT satellite observations, ERA5-Land reanalysis, and GloFAS hydrological model soil moisture. The analysis covers 2007\u20132024 at dekadal (10-day) resolution. Flash drought onset is diagnosed from rapid short-timescale declines in near-surface soil moisture percentiles derived from ASCAT and ERA5-Land, while GloFAS is used to assess whether\u2014and where\u2014these surface drying signals propagate into catchment-scale hydrological response. To ensure comparability across datasets with differing process representations and effective soil depths, all soil moisture variables are expressed in a common percentile space, which isolates anomalous moisture states relative to local climatology.\r\nUsing this unified framework, we quantify key flash drought characteristics\u2014including frequency, mean duration, severity, and mean onset speed\u2014across Europe and examine how these metrics vary across major climate regimes. The findings highlight pronounced regional heterogeneity and systematic cross-system contrasts. ASCAT captures the sharpest and most immediate surface drying signals, whereas ERA5-Land and GloFAS provide complementary insight into physically consistent drivers and the potential for downstream hydrological impacts. Overall, the results emphasize that flash drought diagnosis benefits from combining observation-informed onset detection with process-oriented evaluation of drivers and hydrological propagation. This multi-perspective approach offers a consistent basis for strengthening monitoring and supporting early-warning readiness under Europe\u2019s intensifying hydroclimatic variability.\r\n\r\n\r\nKeywords: Flash drought; Soil-moisture; ASCAT, ERA5-Land; GloFAS, Hydrological response, Land\u2013atmosphere coupling, Europe.", "description": "Flash droughts can intensify within weeks, yet their transition from surface drying to broader hydrological response remains poorly understood at the continental scale. This study addresses that gap through an integrated Europe-wide framework that combines ASCAT, ERA5-Land, and GloFAS to track rapid soil-moisture depletion and evaluate its propagation across hydroclimatic systems. By linking observation-based flash drought onset with process-oriented hydrological interpretation, the work provides a stronger basis for drought monitoring, early warning, and climate-risk preparedness across Europe.", "recording_license": "", "do_not_record": false, "persons": [{"id": 472, "code": "TWSP3D", "public_name": "VAIBHAV KUMAR", "biography": "Dr. Vaibhav Kumar is a Postdoctoral Research Fellow at CNR-IRPI, Italy, working under the supervision of Dr. Luca Brocca. His research focuses on the integration of satellite observations, reanalysis, and hydrological model data for environmental monitoring, with particular emphasis on flash drought detection, soil moisture dynamics, and hydroclimatic extremes. He received his Ph.D. in Geomatics engineering from National Cheng Kung University, Taiwan. His expertise includes multi-sensor Earth observation, geospatial data harmonization, uncertainty analysis, and machine learning for large-scale environmental applications. His work supports engineering-oriented monitoring frameworks for hazard assessment, early warning, and climate resilience.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 430, "guid": "c6f3db1b-f2ad-5ded-88d0-4d7ee92c5bf0", "logo": "", "date": "2026-10-07T18:10:00+02:00", "start": "18:10", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-430-ai-driven-early-detection-of-chickpea-ascochyta-blight-from-controlled-hyperspectral-analysis-to-uav-multispectral-field-monitoring", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/9G3MQF/", "title": "AI-Driven Early Detection of Chickpea Ascochyta Blight: From Controlled Hyperspectral Analysis to UAV Multispectral Field Monitoring", "subtitle": "", "track": "Soil, water and agriculture", "type": "Poster presentation", "language": "en", "abstract": "Fungal diseases such as Ascochyta remain a major obstacle to chickpea production, leading to significant yield losses if not detected early. Whilst hyperspectral imaging (HSI), combined with machine learning, has demonstrated strong potential for early and non-destructive detection under controlled laboratory conditions, its transferability to real-world field environments remains a major challenge. This study aims to validate detection models developed in the laboratory under field conditions using multispectral images acquired by a drone. Following promising results obtained using hyperspectral data (400\u20131000 nm) and advanced machine learning pipelines, we have extended our approach to drone-based multispectral detection to assess its robustness in real-world agricultural scenarios. Field data were acquired using drone-mounted sensors capturing key spectral bands relevant to vegetation health and stress detection. A comprehensive processing pipeline was implemented, comprising radiometric correction, image pre-processing, vegetation index calculation, and feature extraction. The previously developed classification framework was adapted and applied to multispectral data, incorporating both spectral and statistical features. The results demonstrate that the proposed approach can be successfully applied from the laboratory to field conditions, achieving high detection performance with a classification accuracy of over 90% in distinguishing healthy chickpea plants from infected ones. Furthermore, the system proved capable of detecting signs of infection at an early stage in the canopy, despite environmental variability such as changes in light intensity and ground background effects. These results confirm the feasibility of deploying AI-based disease detection systems using drone-based multispectral imaging in real agricultural environments. This work represents a significant step towards operational precision agriculture solutions, enabling large-scale monitoring, early intervention, reduced chemical inputs, and improved crop management strategies. Future work will focus on validation over multiple seasons, integration with close-range detection, and extension to other plant-pathogen systems.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 469, "code": "D9CBKW", "public_name": "Mohamed", "biography": "Fourth-year PhD candidate specializing in Artificial Intelligence, Computer Vision, and Data Science applied to Smart Agriculture and Precision Farming. Experienced in developing AI-driven preprocessing and modeling pipelines for early disease and pest detection using drone and proximal sensing data.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 424, "guid": "a494a76f-1008-5c70-b4cd-c4796963ede7", "logo": "", "date": "2026-10-07T18:15:00+02:00", "start": "18:15", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-424-iterative-bayesian-updating-for-near-real-time-mangrove-deforestation-monitoring-a-multi-sensor-fusion-approach-in-semarang-demak-indonesia", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/DJBM9P/", "title": "Iterative Bayesian Updating for Near Real-Time Mangrove Deforestation Monitoring: A Multi-Sensor Fusion Approach in Semarang-Demak, Indonesia", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "The coastal border of Semarang and Demak in Central Java, Indonesia, faces unprecedented mangrove deforestation driven by rapid land subsidence, sea-level rise, aquaculture expansion, and industrialization. Traditional optical remote sensing approaches are severely constrained by persistent cloud cover in this tropical environment, resulting in detection lags of weeks to months that preclude timely intervention. This study presents an iterative Bayesian updating framework for near-real-time mangrove deforestation monitoring through multi-sensor fusion of Sentinel-1 Synthetic Aperture Radar (SAR) and optical imagery from Landsat-8/9 and Sentinel-2. We formulate a probabilistic change detection model where posterior deforestation probabilities are sequentially updated with each new satellite observation, incorporating VH-polarized backscatter from Sentinel-1 alongside three complementary optical indices: Normalized Difference Vegetation Index (NDVI), Mangrove Vegetation Index (MVI), and Enhanced Mangrove Index (EMI). Four experimental scenarios were evaluated across the 2018-2025 period: (1) SAR-Optical Baseline (VH + NDVI), (2) Structure-Focused (VH + MVI), (3) Moisture/Soil-Focused (VH + EMI), and (4) Full Integrated Suite (VH + EMI + NDVI + MVI). Validation through field surveys, high-resolution imagery, and comparison with existing deforestation maps demonstrated that Scenario 4 achieved the highest F1-score (0.89) and lowest detection lag (8.3 days median), reducing false positives from tidal flooding by 67% compared to single-sensor approaches. The integration of structural information from SAR and MVI with spectral-moisture signals from EMI and NDVI enabled robust discrimination between genuine deforestation events and natural tidal dynamics. Mathematical formulations for prior specification, likelihood functions, and posterior updating are presented in detail, alongside practical implementation considerations for tropical coastal environments. These findings provide actionable guidance for local coastal management agencies in Semarang-Demak to implement operational near-real-time monitoring systems that can trigger rapid response to illegal logging and land conversion.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 465, "code": "ZPTHKY", "public_name": "Munawaroh Munawaroh", "biography": "Junior Researcher at National Research and Innovation Agency of Republic of Indonesia specializing in Remote Sensing applications", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 447, "guid": "51369f00-a4a1-5295-bfa1-b137d0cc392a", "logo": "", "date": "2026-10-07T18:25:00+02:00", "start": "18:25", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-447-transformer-based-adaptive-multimodal-fusion-model-for-remote-sensing-large-scale-winter-wheat-yield-prediction", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/E8HUES/", "title": "Transformer-Based Adaptive Multimodal Fusion Model for Remote  Sensing Large-scale Winter Wheat Yield Prediction", "subtitle": "", "track": "Soil, water and agriculture", "type": "Poster presentation", "language": "en", "abstract": "Large-scale and highly accurate wheat yield prediction is of great importance for \r\nensuring food security, supporting agricultural policymaking, and guiding grain \r\nallocation. In recent years, the rapid development of remote sensing technologies and \r\ndeep learning algorithms has provided powerful tools for large-scale crop yield \r\nprediction. However, crop yield is jointly influenced by multiple environmental factors, \r\nsuch as climate, soil, and topography. Existing studies often adopt simple feature \r\nconcatenation or fixed-weight fusion strategies, lacking adaptive modeling of relative\r\nmodality importance, which limits further improvement in prediction accuracy. To \r\naddress this issue, this study proposes a Transformer-based multi-modal adaptive Gated \r\nFusion model (TMMGF). The model employs Transformers to model dynamic time \r\nseries of remote sensing spectral data and climate variables, applies multilayer \r\nperceptrons (MLP) to handle static environmental factors including soil and topography. \r\nMultiple modalities are then integrated through a gated fusion mechanism to achieve\r\nadaptive weighted fusion. This study was conducted across the conterminous United \r\nStates, based on county-level winter wheat yield records from 2008 to 2023. The \r\nTMMGF was systematically compared with an LSTM-based multimodal adaptive \r\nGated Fusion model (MMGF), Transformer single-modal remote sensing model, \r\nTransformer single-modal climate model, MLP single-modal soil model, and MLP \r\nsingle-modal topography model. The results show that TMMGF achieves the best \r\nperformance, with an average R\u00b2 of 0.813, RMSE of 0.571 t/ha, and MAPE of 14.49% \r\nin 10-fold cross-validation, significantly outperforming the baseline models. In \r\nparticular, compared with the LSTM-based multimodal model MMGF (R\u00b2 = 0.796, \r\nRMSE = 0.598 t/ha, MAPE = 15.11%), TMMGF shows clear advantages in both \r\naccuracy and stability. This study demonstrates that a Transformer-based adaptive \r\nmultimodal fusion framework can effectively integrate heterogeneous data sources and \r\nprovides a promising technical pathway for high-accuracy large-scale wheat yield \r\nprediction.", "description": "This research is about an adaptive multi-modal deep learning model to achieve a higher accuracy in wheat yield prediction at a large scale. Most research only uses one single type data to conduct the yield prediction or simply combine more than one types data. This study is about an adaptive fusion about multi-modal model to better integrate the different datasets to further improve the performence of the prediction model.", "recording_license": "", "do_not_record": false, "persons": [{"id": 481, "code": "TWT8KQ", "public_name": "Haoran Meng", "biography": "I am a Phd student in the University of Barcelona. My research focus is about applying the deep learning algorithms and remote sensing data to conduct the crop yield prediction. I really hope that I could have a tremendous communication with you excellent scholars.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 456, "guid": "390706c1-498e-55d7-a254-66a51902c952", "logo": "", "date": "2026-10-07T18:30:00+02:00", "start": "18:30", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-456-ecosystem-functionality-of-catalonian-landscapes-change-assessment-of-ecosystem-functional-types-efts-using-sentinel-2-derived-ndvi", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/JRVYY9/", "title": "Ecosystem Functionality of Catalonian Landscapes: Change Assessment of Ecosystem Functional Types (EFTs) Using Sentinel-2 Derived NDVI", "subtitle": "", "track": "Forest and biodiversity", "type": "Poster presentation", "language": "en", "abstract": "The DynaFun project intends to showcase EFTs as a biodiversity indicator for non-stand shifts in forest ecosystems. EFTs are land delineations that result from similar energy and matter processes such as carbon storage or hydrological cycle. As such, vegetation indices are a well-accepted proxy indicator for ecosystem functionality. In this study Sentinel-2 satellite imagery has been used to derive remotely sensed NDVI to produce an EFT land classification over Catalonia. Plant carbon dynamics are inferred through the derivation of productivity (NDVImean), seasonality (NDVIcovariate) and phenology (NDVIDay of Maximum). Catalonia has a mixed land use land cover (LULC) system that is heavily influenced by its Mediterranean climate. It causes interannual, variable environmental changes reflected in its vegetation dynamics. Non-stand shifts occur before visible structural changes. This project presents an opportunity to enrich Land use land cover and habitat categories to determine their stability, resilience and drivers of change. This information is crucial for forest management and can act as an early warning indicator for biodiversity change for planners and policy developers.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 486, "code": "7HUTAE", "public_name": "Lynn Fanikiso", "biography": "I am a Pre-doctoral student in terrestrial ecology at the Autonomous University of Barcelona through the Centre for Ecological Research and Forestry Applications (CREAF) and work within the Remote Sensing and Geographic Information Systems (GRUMETS) research group.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 505, "guid": "b8b5ce3b-9db7-5826-9daa-754458a69369", "logo": "", "date": "2026-10-07T18:35:00+02:00", "start": "18:35", "duration": "00:05", "room": "Aula Magna", "slug": "global-workshop-2026-505-data-fusion-for-flood-monitoring", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/8YNN39/", "title": "Data fusion for flood monitoring", "subtitle": "", "track": "Climate and Health", "type": "Poster presentation", "language": "en", "abstract": "Flash flood events are increasing in frequency and intensity in Mediterranean regions, requiring rapid, reliable, and scalable monitoring approaches to support emergency response and climate adaptation. Earth Observation (EO) offers a powerful means to provide timely spatial intelligence; however, single-sensor approaches remain limited by cloud cover, revisit frequency, and data latency. This work presents an automatic, multi-sensor, modular, and open-source flood mapping framework designed to deliver actionable information for emergency responders through near-real-time flood detection coupled with a first-pass impact assessment.\r\nThe proposed methodology integrates Synthetic Aperture Radar (Sentinel-1) and multispectral imagery (Sentinel-2 and Landsat 8) with ancillary geospatial datasets within a unified processing pipeline. A change detection approach is applied to pre- and post-event observations, followed by automated thresholding and morphological filtering to generate consistent flood extent maps. To reduce noise sensitivity, outputs from multiple sensors are then fused at the pixel level to generate flood extent, severity, and damage assessment maps. \r\nThe framework was validated against ground-truth data from the October 2024 flash flood event in Valencia, with results clearly demonstrating the value of automated multi-sensor data fusion by increasing the likelihood of acquiring usable observations by up to ~60%. This modular architecture is fully reproducible and designed for extensibility, enabling the integration of additional sensors and seamless deployment within open EO ecosystems and distributed data infrastructures.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 516, "code": "YRXJPZ", "public_name": "Ana Linares Barrio", "biography": "Research technician at the Centre for Ecological Research and Forestry Applications (CREAF). The research presented here was developed as part of previous work at Ubotica Technologies.", "answers": []}], "links": [], "attachments": [], "answers": []}], "Rooms 12+14": [{"id": 445, "guid": "19753627-73e9-56bf-b66c-ccab19e13969", "logo": "", "date": "2026-10-07T15:00:00+02:00", "start": "15:00", "duration": "00:15", "room": "Rooms 12+14", "slug": "global-workshop-2026-445-worldtensor-and-terranova-open-data-and-foundation-models-for-the-coupled-human-earth-system", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/TW9RF7/", "title": "WorldTensor and TerraNova: Open Data and Foundation Models for the Coupled Human\u2013Earth System", "subtitle": "", "track": "Climate and Health", "type": "Oral talk", "language": "en", "abstract": "Foundation models for Earth systems have advanced rapidly for weather and climate prediction, but remain largely confined to physical variables, omitting the human systems that drive emissions, shape land use, build infrastructure, and mediate vulnerability. We argue that this gap is fundamentally a data problem: the information exists but is fragmented across incompatible grids, projections, temporal frequencies, and formats. We present two complementary contributions that address this challenge.\r\nFirst, WorldTensor is a harmonised global dataset that aligns over 750 environmental and socioeconomic variable families onto a common 0.25\u00b0 latitude\u2013longitude grid and annual temporal framework. It integrates climate,  emissions, land use, satellite vegetation indices, gridded population and GDP products, power plant registries, and natural hazard and conflict catalogues into a single ML-ready NetCDF corpus. Constructing WorldTensor required solving nontrivial harmonisation problems including regridding across heterogeneous native resolutions, rasterising point and vector datasets into spatially meaningful fields, and reconciling temporal coverages spanning daily observations to sparse multiyear socioeconomic snapshots. The dataset and processing code will be released under open licenses.\r\nSecond, TerraNova is a foundation model designed to learn from WorldTensor's multimodal structure. It combines coordinate-based spatial encoding, learned country-level embeddings, Fourier temporal encoding, and a hypernetwork decoder to jointly predict climate, land surface, socioeconomic, and infrastructure variables in a unified multi-task framework. Early results demonstrate successful learning across multiple heterogeneous Earth system tasks simultaneously, validating that foundation models can learn shared representations across the coupled human\u2013Earth system.\r\nTogether, WorldTensor and TerraNova provide an open, end-to-end pipeline from harmonised planetary data to multimodal foundation model training, supporting applications in climate impact assessment, cross-domain pattern discovery, and evidence-based environmental policy.", "description": "", "recording_license": "", "do_not_record": true, "persons": [{"id": 478, "code": "NEFXXX", "public_name": "Carlos Rodriguez-Pardo", "biography": "Carlos Rodriguez-Pardo is a postdoctoral researcher at Politecnico di Milano and the RFF-CMCC European Institute on Economics and the Environment, where he works on deep learning for climate change mitigation as part of the ERC-funded EUNICE project. His current research focuses on foundation models for coupled human\u2013Earth system modeling, multimodal geospatial data harmonisation, and neural methods for climate-economic decision making under uncertainty. He has published in Nature, Nature Scientific Data, Nature Climate Change, TMLR, CVPR, Eurographics, and ACM Transactions on Graphics, among others. He holds a PhD in Computer Science from Universidad Rey Juan Carlos and an MSc in Artificial Intelligence from the University of Edinburgh. He has received the SCIE\u2013Fundaci\u00f3n BBVA Young Researcher Award, the CEIG Best PhD Thesis Award, and multiple outstanding reviewer recognitions at CVPR, NeurIPS, ECCV, and AISTATS. He co-convenes the EGU 2026 session on machine learning for carbon cycle science and co-organised the first CMCC AI for Carbon Workshop.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 463, "guid": "928bbab4-2ab6-5089-ba54-6af97f17b349", "logo": "/media/global-workshop-2026/submissions/TURRVV/Session_presentation_6Ad6ZDu.png", "date": "2026-10-07T15:15:00+02:00", "start": "15:15", "duration": "00:15", "room": "Rooms 12+14", "slug": "global-workshop-2026-463-biomazon-a-multimodal-benchmark-for-full-vertical-structure-and-biomass-modeling-in-the-amazon-basin", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/TURRVV/", "title": "Biomazon: A Multimodal Benchmark for Full Vertical Structure and Biomass Modeling in the Amazon Basin", "subtitle": "", "track": "Forest and biodiversity", "type": "Oral talk", "language": "en", "abstract": "Accurate characterization of tropical forest vertical structure is critical for carbon accounting and ecosystem monitoring, yet most machine-learning pipelines reduce GEDI's rich waveform information to a single scalar, typically canopy height or a high relative-height percentile. This simplification discards the ordered height distribution that GEDI encodes across its full relative height (RH) profile, and that its own biomass algorithms depend on. We introduce Biomazon, an open, ML-ready multimodal benchmark dataset at 20 m resolution over the Amazon Basin, designed to support joint prediction of the full GEDI RH profile (RH0 to RH100) together with above-ground biomass density (AGBD). The dataset pairs GEDI-derived targets with multi-sensor predictors including Sentinel-1, Sentinel-2, ALOS-2 PALSAR-2, Copernicus DEM, Dynamic World land cover, and geospatial foundation model embeddings, all co-registered on a common grid with standardized spatial splits and evaluation protocols to enable reproducible comparison of methods. We formulate RH prediction as structured output learning with a monotonicity constraint that enforces physical consistency across percentiles, and we provide baseline results from systematic ablations over model scale, sensor contributions, and the role of AlphaEarth embeddings, both as standalone predictors and in fusion with raw modalities. Results are contextualized against existing gridded products to assess practical relevance. Biomazon addresses a gap in current benchmarking by shifting the task formulation from scalar regression toward structure-aware modeling, and by providing the community with an open, multi-sensor dataset and protocol for investigating when and how different data sources, including learned representations, contribute to forest structure and biomass retrieval in tropical forests.", "description": "This talk presents Biomazon, an open multimodal benchmark dataset for predicting forest vertical structure and biomass in the Amazon Basin from multi-sensor Earth Observation data. The dataset and protocols will be publicly released, supporting reproducible comparison of methods for full GEDI relative height profile and AGBD prediction.\r\nThe talk is relevant to researchers and practitioners working on forest monitoring pipelines, foundation model evaluation, and carbon-relevant mapping. We will show controlled comparisons between raw sensor inputs (Sentinel-1/2, ALOS-2 PALSAR-2) and AlphaEarth embeddings under identical training conditions, providing evidence on how learned representations help. We will further contextualize Biomazon baseline performance through regionally aligned comparisons with existing gridded products, including GEDI L4D, Wagner et al., Lang et al., Potapov et al., Tolan et al., and ESA CCI AGBD. Finally, we will discuss why treating vertical structure as a structured prediction target, rather than a scalar canopy height proxy, matters for biomass estimation and carbon accounting at scale.\r\nAll data, code, and evaluation protocols are designed to be open and reusable.", "recording_license": "", "do_not_record": false, "persons": [{"id": 491, "code": "GZTBS3", "public_name": "Sayan Mandal", "biography": "Sayan Mandal received his B.Tech. in Computer Science from University of Petroleum and Energy Studies, India, in 2017 and M.Sc. in Computer Science (major: Machine Learning, minor: Visual Computing), with distinction, from Technische Universit\u00e4t Graz, Austria, in 2024. Before joining Masters, he worked in the field of Computer Vision for over 4 years with two leading startups in India. For his M.Sc. thesis, he worked as a Student Project Assistant in FutureWoods Project at ICG, TU Graz, Austria, funded by FFG - Austrian Research Promotion Agency and the Vienna Scientific Cluster supercomputer. He is currently pursuing his Ph.D. degree in Electrical and Computer Engineering from University of Iceland in conjunction with the \u201cAI and ML for Remote Sensing\u201d Simulation and Data Lab, JSC, Forschungszentrum J\u00fclich, Germany. His main research interests include developing robust deep learning models for remote sensing applications, foundation models and exploring AI efficiency, using HPC systems.", "answers": []}, {"id": 492, "code": "ZERAER", "public_name": "Rocco Sedona", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 481, "guid": "4e9c883b-480c-579d-97a0-ac937d0c25e2", "logo": "/media/global-workshop-2026/submissions/MZEPKT/dggs_S6JKhQE.png", "date": "2026-10-07T15:35:00+02:00", "start": "15:35", "duration": "00:15", "room": "Rooms 12+14", "slug": "global-workshop-2026-481-from-sentinel-2-stac-to-dggs-native-data-cubes-with-dggs-jl", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/MZEPKT/", "title": "From Sentinel-2 STAC to DGGS Native Data Cubes with DGGS.jl", "subtitle": "", "track": "Forest and biodiversity", "type": "Oral talk", "language": "en", "abstract": "Discrete Global Grid Systems (DGGS) tessellate the earth\u2019s surface into zones of equal area and very similar shape, minimizing spatial distortions in geospatial data processing. Here we present DGGS.jl, a tool to create and visualize data cubes with DGGS coordinates. We applied it to create such a data cube of Europe from quarterly cloudless Sentinel-2 mosaics of the Copernicus Data Space Ecosystem.", "description": "Discrete Global Grid Systems (DGGS) tessellate the earth\u2019s surface into zones of equal area and very similar shape, minimizing spatial distortions in geospatial data processing. DGGS are not only used for geocoding but also offer a highly efficient data structure by eliminating tile overlap compared to traditional grids like UTM used in Sentinel-2 products. In addition, many real-world applications, such as visualization or convolutions, require efficient handling of higher-order neighbor queries based on spatial distances, motivating a multidimensional DGGS coordinate system.\u00a0This leads into DGGS native data cubes, in which the data is stored in such a DGGS grid to improve the performance on such operations.\r\nIn response to these challenges, we introduce DGGS.jl (https://danlooo.github.io/DGGS.jl), a Julia package specifically developed to create and utilize DGGS native data cubes optimized for indirect neighbor queries. Our package employs the DGGRID Q2DI index to store\u00a0data on a grid based on the Icosahedral Snyder Equal Area projection, enabling compact and efficient data cube arrays. We have implemented methods to seamlessly convert raster data between geographic and Q2DI coordinates, access neighbor disks around a given cell, and visualize these data on a global scale. In addition, we developed an XYZ tile server, allowing us to view DGGS native data cubes in QGIS and in the browser. Finally, we used DGGS.jl to create such a data cube of Europe from quarterly cloudless Sentinel-2 mosaics of the Copernicus Data Space Ecosystem.", "recording_license": "", "do_not_record": false, "persons": [{"id": 91, "code": "REJEED", "public_name": "Daniel Loos", "biography": "I'm a postdoctoral researcher at the Max Planck Institute for Biogeochemistry in Jena, Germany. Originally coming from a bioinformatics background, I now work on software and data formats making geospatial data like satellite imagery less distorted.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 455, "guid": "137f812a-7068-51ad-91ae-12c24ea583e8", "logo": "/media/global-workshop-2026/submissions/PEKSXV/Session_image_6nbzkLZ.png", "date": "2026-10-07T16:45:00+02:00", "start": "16:45", "duration": "00:15", "room": "Rooms 12+14", "slug": "global-workshop-2026-455-mapping-global-forest-litterfall-dynamics-at-500-m-resolution-via-geoai-implications-for-forest-ecosystem-functioning-and-soil-respiration", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/PEKSXV/", "title": "Mapping Global Forest Litterfall Dynamics at 500-m Resolution via GeoAI: Implications for Forest Ecosystem Functioning and Soil Respiration", "subtitle": "", "track": "Forest and biodiversity", "type": "Oral talk", "language": "en", "abstract": "The organic carbon flux entering the pedosphere through forest litterfall is a critical indicator of forest ecosystem functioning and a primary driver of soil respiration (RS). However, accurately quantifying litterfall spatiotemporal dynamics at the global scale remains a major challenge due to the scarcity of high-resolution Earth Observation (EO) frameworks coupled with extensive ground observations. \r\nHere, we present a novel GeoAI-driven approach that synthesizes 14,912 in-situ observations across 843 sites globally with multi-source remote sensing data. By leveraging machine learning algorithms, we decoupled complex biogeochemical mechanisms and generated a 500-m spatial resolution global forest litterfall product. Furthermore, we integrated these high-resolution EO derivatives into an Olson legacy model to quantify the impact of litterfall on RS across different forest biomes. \r\nOur results reveal significant spatial heterogeneity in biogeochemical coupling, highlighting asymmetric microbial responses between tropical forests (characterized by high turnover rates) and temperate/boreal forests (exhibiting biogeochemical inertia). This study demonstrates the profound potential of integrating open Earth Observation data and machine learning to monitor global forest dynamics. Our 500-m global product provides a vital, scalable data infrastructure for next-generation Earth system models, biodiversity conservation, and forest carbon management. \r\n(Note: This research has been recently published in Remote Sensing of Environment, 2026, https://doi.org/10.1016/j.rse.2026.115373)", "description": "This 20-minute oral presentation is based on our recent publication in Remote Sensing of Environment (2026). The talk will comprehensively introduce a novel GeoAI-driven framework for mapping global forest litterfall and exploring its biogeochemical coupling with soil respiration.\r\nThe presentation will be structured as follows:\r\n1. Introduction & Background (approx. 4 mins)\r\nThe critical role of forest litterfall in the global carbon cycle and pedosphere carbon flux;\r\nCurrent limitations in Earth Observation (EO) and scaling issues in traditional meteorological proxies.\r\n2. Data Synthesis & GeoAI Methodology (approx. 6 mins)\r\nData Foundation: Synthesizing an unprecedented dataset of 14,912 in-situ observations across 843 sites globally;\r\nMachine Learning Integration: Detailing the framework used to fuse multi-source remote sensing data to overcome uncertainty;\r\nGenerating the 500-m spatial resolution global forest litterfall product.\r\n3. Key Findings & Biogeochemical Mechanisms (approx. 5 mins)\r\nIntegrating the high-resolution EO derivatives into the Olson legacy model to quantify litterfall's impact on soil respiration (RS);\r\nUncovering the spatial heterogeneity: Discussing the asymmetric microbial responses between tropical forests (high turnover rates) and temperate/boreal regions (biogeochemical inertia).\r\n4. Implications & Conclusion (approx. 5 mins)\r\nHow this 500-m global product provides scalable data infrastructure for next-generation Earth System Models (ESMs);\r\nImplications for biodiversity conservation and global forest carbon management;\r\nQ&A session.\r\nWe believe this comprehensive GeoAI pipeline perfectly aligns with the \u201cForest and biodiversity\u201d track and will provide valuable methodological insights for the Open Earth Monitor community.", "recording_license": "", "do_not_record": false, "persons": [{"id": 485, "code": "3KNUAV", "public_name": "Chunsheng Wang", "biography": "Chunsheng Wang is a Ph.D. candidate at the International Institute for Earth System Science, Nanjing University, China. His research primarily focuses on the intersection of Earth Observation, GeoAI, and global biogeochemical cycles.\r\nSpecifically, he leverages multi-source remote sensing data and machine learning algorithms to map large-scale forest ecosystem functioning, monitor litterfall dynamics, and model soil respiration. His goal is to reduce uncertainties in traditional meteorological proxies and provide scalable data infrastructure for next-generation Earth System Models. His most recent breakthrough in evaluating global forest litterfall dynamics and its biogeochemical coupling has been published in the prestigious journal Remote Sensing of Environment.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 449, "guid": "05be6fe9-fb6d-5f26-aa05-dcecd3a775a3", "logo": "", "date": "2026-10-07T17:00:00+02:00", "start": "17:00", "duration": "00:15", "room": "Rooms 12+14", "slug": "global-workshop-2026-449-from-earth-observation-to-farm-decisions-designing-platforms-for-decision-making", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/NZJHKC/", "title": "From earth observation to farm decisions: Designing platforms for decision making", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "The way we monitor soils, water resources, and agricultural landscapes has been transformed by Earth Observation and environmental modelling over the last few years. Nevertheless, real decision-making remains a major challenge, as turning complex datasets into tools is not yet trivial for human purposes. \r\n\r\nIn this talk, the audience will learn about lessons learned from designing platforms such as Soils Revealed, Aqueduct, Foodscapes, and Landgriffon. These tools combine satellite indicators, global environmental datasets, and workflows to help users better understand soil degradation, water risks, and food system dynamics, and to translate environmental data into platforms that support decision-making across scales, from regional planning to global analysis. \r\n\r\nWe will also reflect on the challenges of moving from data to decision tools, combining scientific outputs with user needs, based on human-centered design to support exploration and comparison, and ensuring that complex environmental information is both scientifically rigorous and accessible. By combining Earth observation, modelling and interface design, these platforms demonstrate that environmental data is trustful acctionable knowledge to help inform land and water management.", "description": "In this session, Sergio will share lessons from his experience working at the intersection of Earth observation, environmental science, and design. His work focuses on translating complex datasets and models into operational platforms that support decision-making for governments, NGOs, and research institutions. By acting as a bridge between scientific outputs and user needs, he helps transform data into tools that enable exploration, comparison, and informed action.", "recording_license": "", "do_not_record": false, "persons": [{"id": 483, "code": "JTJDL9", "public_name": "Sergio Estella", "biography": "Sergio Estella is a designer and entrepreneur with over 25 years of experience working at the intersection of data, technology, and environmental impact. He is the co-founder of Vizzuality, a European company that designs digital platforms to make complex scientific data accessible and actionable.\r\n\r\nHis work focuses on translating Earth Observation data, environmental models, and large-scale datasets into tools that support decision-making across climate, nature, and sustainability challenges. Sergio has led the design of platforms that help detect forest loss, monitor supply chains, map illegal fishing, and explore climate futures.\r\n\r\nHe has collaborated with organisations such as the United Nations, the World Resources Institute, the World Bank, the European Space Agency, and leading academic institutions, including Cambridge, Stanford, and Yale, helping turn scientific knowledge into operational tools with real-world impact.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 448, "guid": "2d15da68-82bd-5ed0-b1c7-3b529cbb89d0", "logo": "", "date": "2026-10-07T17:15:00+02:00", "start": "17:15", "duration": "00:15", "room": "Rooms 12+14", "slug": "global-workshop-2026-448-global-organic-soil-disturbance-and-emissions-leveraging-earth-observation-based-geospatial-data-within-an-ipcc-framework", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/E7NZH7/", "title": "Global organic soil disturbance and emissions: leveraging Earth observation\u2013based geospatial data within an IPCC framework", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "Peatlands and other organic soils occupy a small fraction of the land surface but store a large share of the global soil carbon. Drainage and fire in these systems are major sources of greenhouse gas (GHG) emissions, yet remain poorly mapped. Remote sensing enables global monitoring of proxies for peatland disturbance, but no monitoring system currently links the extent of organic soils, disturbance, and emissions at high spatial resolution. Here we develop a 0.00025\u00b0 (approximately 30 m) global geospatial framework that overlays organic soils extent with multi-temporal land cover and land use data, drainage infrastructure, plantations, peat extraction areas, coastal wetlands, and burned area to delineate disturbed organic soils. Using IPCC Wetlands Supplement default (Tier 1) methods, we estimate CO2, CH4, N2O, and CO emissions for disturbed organic soils over 2001\u20132024. Baseline results indicate that disturbed organic soils emitted about 4.9 Gt CO2e yr-1 (4.5\u20135.1 Gt CO2e yr-1 across five inventory periods), with roughly three quarters from drainage and one quarter from fires. Emissions and disturbed area are heavily concentrated in a small group of countries and land uses, dominated by Russia and Indonesia, particularly cropland and settlements in boreal and temperate zones and plantations on organic soils in the tropics. Sensitivity experiments that vary the extent of organic soils, the drainage radius around infrastructure, and IPCC default (Tier 1) emission factors yield a plausible range of approximately 3\u20137 Gt CO2e yr-1. These estimates should not be interpreted as a correction to existing peatland-specific emission estimates, but as complementary, more comprehensive monitoring of disturbed organic soil systems under a harmonized, globally consistent framework. The resulting 30 m global maps of organic soil state, disturbance, and emissions demonstrate how multi-temporal Earth observation can be combined with GHG inventory methods to monitor peatland disturbance drivers, identify high-emitting hotspots, and provide an updatable resource for inventories, nationally determined contributions, and peatland conservation and restoration planning.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 482, "code": "PAXAJ8", "public_name": "Erin Glen", "biography": "Erin Glen is a GIS Research Associate with Land & Carbon Lab at the World Resources Institute, where she develops and applies geospatial data, remote sensing, and spatial analysis to support forest carbon monitoring, land use, and natural climate solutions. Her work focuses on improving monitoring and decision-support tools for land managers and advancing global analyses of land sector greenhouse gas emissions.", "answers": []}], "links": [], "attachments": [], "answers": []}], "Room 18": [{"id": 436, "guid": "3f58ea30-8a33-5e37-bded-0a56f213eb9a", "logo": "/media/global-workshop-2026/submissions/QF38UE/IMG_4931_ysR2Ov5.JPG", "date": "2026-10-07T16:15:00+02:00", "start": "16:15", "duration": "00:15", "room": "Room 18", "slug": "global-workshop-2026-436-emerging-flash-drought-risk-across-europe-insights-from-multi-model-root-zone-soil-moisture-projections", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/QF38UE/", "title": "Emerging Flash Drought Risk across Europe: Insights from Multi-Model Root-Zone Soil Moisture Projections", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "Abstract\r\nFlash droughts are increasingly recognized as a distinct class of hydroclimatic extremes marked by rapid soil-moisture depletion over only a few weeks. Because of their abrupt onset, these events can severely affect agricultural production, terrestrial ecosystems, and regional water resources before conventional drought indicators fully capture their development. Recent drought episodes across Europe have reinforced the need to better understand how flash drought behaviour may evolve under continued climate warming. Yet substantial uncertainty remains, partly because many previous assessments rely on meteorological indicators or single datasets that do not adequately represent the subsurface soil-moisture processes governing rapid drought emergence.\r\nThis study proposes to investigate the future evolution of flash drought characteristics across Europe using root-zone soil moisture simulations from a multi-model ensemble of global hydrological models, including WaterGAP, H08, and CWatM, forced by bias-adjusted CMIP6 climate projections. Daily soil-moisture outputs will be aggregated to pentad scale (5-day averages) to reduce high-volatility while preserving the rapid depletion signals associated with flash drought onset. Root-zone soil moisture will then be transformed into grid-specific climatological percentiles, enabling a temporally and spatially consistent identification of flash drought events across models and time periods. A key methodological contribution of this study is the integration of pentad-scale root-zone soil moisture percentiles with a multi-model hydrological ensemble, enabling a consistent and process-relevant assessment of future flash drought dynamics across Europe.\r\nUsing this framework, the study will assess potential changes in flash drought frequency, duration, severity, and onset speed under historical conditions and future projections for SSP1-2.6, SSP2-4.5, and SSP5-8.5. The analysis is intended to advance understanding of future rapid drought development and to support drought risk assessment, climate adaptation planning, and early-warning strategies across Europe.\r\n\r\n\r\n\r\nKeywords: Flash drought; Root-zone soil moisture; Global hydrological models; CMIP6; Europe.", "description": "This study examines how flash drought characteristics may change across Europe under future climate scenarios using multi-model root-zone soil moisture simulations from global hydrological models forced by CMIP6 projections. The framework combines pentad-scale percentile diagnostics with ensemble-based analysis to provide physically grounded insights for drought risk assessment and early-warning planning.", "recording_license": "", "do_not_record": false, "persons": [{"id": 472, "code": "TWSP3D", "public_name": "VAIBHAV KUMAR", "biography": "Dr. Vaibhav Kumar is a Postdoctoral Research Fellow at CNR-IRPI, Italy, working under the supervision of Dr. Luca Brocca. His research focuses on the integration of satellite observations, reanalysis, and hydrological model data for environmental monitoring, with particular emphasis on flash drought detection, soil moisture dynamics, and hydroclimatic extremes. He received his Ph.D. in Geomatics engineering from National Cheng Kung University, Taiwan. His expertise includes multi-sensor Earth observation, geospatial data harmonization, uncertainty analysis, and machine learning for large-scale environmental applications. His work supports engineering-oriented monitoring frameworks for hazard assessment, early warning, and climate resilience.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 477, "guid": "47875fda-ede0-5b11-a134-92c1a15211f0", "logo": "", "date": "2026-10-07T16:30:00+02:00", "start": "16:30", "duration": "00:15", "room": "Room 18", "slug": "global-workshop-2026-477-limitations-of-current-operational-systems-based-on-remote-sensing-and-models-for-the-characterization-fo-extreme-hydrometeorological-events", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/7GBGPT/", "title": "Limitations of current operational systems based on remote sensing and models for the characterization fo extreme hydrometeorological events", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "Extreme hydrometeorological extremes are one of the main focuses of operational early warning systems for natural hazards. The ongoing integration of remote sensing datasets into the monitoring pipelines is aimed at contributing to the refinement of the forecasts and the accurate identification of the risks. However, very few studies have specifically addressed the inherent uncertainties of the remote sensing datasets in the range of extreme events. Multiple factors in the processing of these datasets can impact the capabilities of each type of data to effectively detect potentially hazardous events due to unrealistic recognition of the tails of the distribution of events. \r\n \r\nThis study is devoted to the intercomparison of remote sensing, model-based and reanalysis products of key variables of the water cycle (rain, soil moisture, flow) to evaluate the consistency of common current operational products for the portrayal of extreme events. The procedure comprises specific extreme value analysis of the distributions of the datasets with special attention to the characterisation of the magnitude and temporal dimensions of the events. In this way, metrics of frequency, duration and intensity are applied to assess the suitability of each product for proper extremes identification against ancillary data of multiple events of well-known impact. \r\n\r\nThe results indicate relevant differences among products well before the range of true extreme events, which partly explains the struggle of current operational monitoring systems to accurately characterise impactful events. Discussion on the factors influencing such notable differences in the products apprise of multiple aspects of datasets generation and handling that led to distorted capabilities in the tail range of the distributions that need review and coordination between the actors in charge of the generation and application of datasets. \r\n\r\nThe study encourages further attention to the evaluation of data in the range of their most relevant application, risk assessment, in order to avoid undesired inherited constraints to their application, jeopardising the confidence in early warning systems or the remotely\u2013sensed data.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 192, "code": "SFDNQZ", "public_name": "Jaime Gaona", "biography": "Jaime Gaona was born in Burgos, Spain in 1986. Jaime has a background specialized in hydrology during his Civil Engineering studies from the University of Burgos (2013) and his M.Sc. in Hydraulics and Environment from the Polytechnic University of Valencia (2015).\r\n\r\nJaime holds a PhD supported by an Erasmus Mundus Joint Doctorate scholarship in river Sciences (2019) from Freie Universit\u00e4t Berlin and Universit\u00e1 Degli Studi di Trento, associated with the Leibniz Institute of Freshwater Ecology (Berlin IGB), focused on characterizing and modeling the groundwater-surface water interactions (hyporheic exchange) using innovative measurement techniques such as FO-DTS and hydrogeophysics directed by J\u00f6rg Lewandowski and Alberto Bellin.\r\n\r\nHe started as postdoc in 2019 to study soil moisture and evaporation in the Spanish National Science Project HUMID devoted to the analysis of Iberian drought based on remote sensing and land surface modelling at Ebro Observatory with Pere Quintana-Segu\u00ed, while helping to lecture hydraulics and irrigation systems at the Polytechnic University of Barcelona (2020). \r\n\r\nJaime was from 2021 JCYL-supported researcher at the University of Salamanca, Spain, group of Water Resources led by Jos\u00e9 Mart\u00ednez Fern\u00e1ndez at the Research Institute of Agrobiotechnology (CIALE), working on the analysis of soil moisture relevance to vegetation responses.\r\n\r\nJaime is currently researcher working in soil moisture analysis at the Hydrology group led by Luca Brocca of the Research Institute for Geo-Hydrological Protection IRPI of the Italian National Research Council in Perugia, Italia. The group focus on evaluation of remote sensing tools for hydrology and related fields, with special attention to soil moisture as key variable mediating the water, matter and energy exchanges in the critical zone.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 452, "guid": "ec681c3a-4bfb-52f6-9610-6a056a520799", "logo": "", "date": "2026-10-07T16:45:00+02:00", "start": "16:45", "duration": "00:15", "room": "Room 18", "slug": "global-workshop-2026-452-high-resolution-global-maps-of-coffee-farms-extent", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/WHG977/", "title": "High-Resolution Global Maps of Coffee Farms Extent", "subtitle": "", "track": "Forest and biodiversity", "type": "Oral talk", "language": "en", "abstract": "Robert N Masolele1, Katja Berger2, Zoltan Szantoi3, Camilo Zamora2, Johannes Reiche1\r\n\r\n1 Wageningen University, Wageningen, The Netherlands; robert.masolele@wur.nl\r\n2 GFZ, German GeoResearch Center Potsdam, Germany\r\n3 Directorate of Earth Observation Programmes, European Space\r\nAgency (ESA), Frascati, RM, Italy\r\n\r\nCoffee cultivation underpins agricultural economies worldwide, supporting millions of livelihoods and contributing significantly to global production [1]. At the same time, coffee is among the leading commodities associated with global deforestation risks linked to European Union (EU) consumption. However, accurately mapping coffee farm locations remains challenging due to the heterogeneous landscapes in which coffee is grown, including dense vegetation, diverse land cover types, varying management practices, and phenological stages [2], [3], [4]. Existing mapping efforts are largely limited to major producers such as Brazil, Vietnam, Ethiopia, and Colombia, leaving substantial gaps across other coffee-growing regions [5].\r\nTo address this, we first present a global benchmarking framework for commodity crop mapping. We evaluate a combination of Sentinel-1 and Sentinel-2 data, alongside locational variables. Using a comprehensive reference dataset spanning >40 coffee-producing countries, we show that models integrating Sentinel-1 and Sentinel-2 data with location encoding achieve the highest performance (F1-score: 89%), outperforming models without contextual information [4].\r\nBuilding on this, we apply the best-performing deep learning framework to generate the first high-resolution global map of coffee farm extent, achieving an F1-score of 86%. The integration of Sentinel-1 (radar) and Sentinel-2 (optical) data enables robust feature extraction across diverse conditions, while location encodings enhance geographic contextualization of coffee systems.\r\nThis work delivers a consistent, high-resolution global coffee map, supporting sustainable land management, supply chain transparency, and conservation in tropical regions. It directly aligns with the EU Deforestation Regulation (EUDR, Regulation (EU) 2023/1115), which requires monitoring the deforestation footprint of seven key commodities, including coffee relative to the December 31, 2020 cut-off date. The approach is being operationalized within cloud-based platforms (e.g., Copernicus Data Space Ecosystem), facilitating access for policymakers, certification bodies, and stakeholders.\r\n\r\n[1]\tR. Gr\u00fcter, T. Trachsel, P. Laube, and I. Jaisli, \u2018Expected global suitability of coffee, cashew and avocado due to climate change\u2019, PLoS One, vol. 17, no. 1, p. e0261976, Jan. 2022, doi: 10.1371/JOURNAL.PONE.0261976.\r\n[2]\tD. A. Hunt et al., \u2018Review of Remote Sensing Methods to Map Coffee Production Systems\u2019, Remote Sensing 2020, Vol. 12, Page 2041, vol. 12, no. 12, p. 2041, Jun. 2020, doi: 10.3390/RS12122041.\r\n[3]\tG. Maskell, A. Chemura, H. Nguyen, C. Gornott, and P. Mondal, \u2018Integration of Sentinel optical and radar data for mapping smallholder coffee production systems in Vietnam\u2019, Remote Sens. Environ., vol. 266, Dec. 2021, doi: 10.1016/j.rse.2021.112709.\r\n[4]\tR. N. Masolele et al., \u2018Mapping the diversity of land uses following deforestation across Africa\u2019, Sci. Rep., vol. 14, p. 1681, 2024, doi: 10.1038/s41598-024-52138-9.\r\n[5]\tA. Escobar-L\u00f3pez, M. \u00c1. Castillo-Santiago, J. F. Mas, J. L. Hern\u00e1ndez-Stefanoni, and J. O. L\u00f3pez-Mart\u00ednez, \u2018Identification of coffee agroforestry systems using remote sensing data: a review of methods and sensor data\u2019, Geocarto Int., vol. 39, no. 1, p. 2297555, 2024, doi: 10.1080/10106049.2023.2297555;WGROUP:STRING:PUBLICATION.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 82, "code": "UBMC3H", "public_name": "Robert Masolele", "biography": "Geoinformation Scientist leveraging AI and satellite technology to map our planet's changing landscape. I transform petabytes of satellite data into actionable insights on agricultural expansion, deforestation, and biodiversity, bridging the gap between advanced algorithms and environmental policy.\r\n\r\nMy work focuses on developing scalable deep learning models to monitor commodity crops (e.g., oil palm, cocoa, coffee, soy) and assess their environmental impacts, using a combination of radar, optical imagery, and cloud computing.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 511, "guid": "e08c7a26-c43c-5c88-9438-266c1cfbb331", "logo": "", "date": "2026-10-07T17:00:00+02:00", "start": "17:00", "duration": "00:15", "room": "Room 18", "slug": "global-workshop-2026-511-global-monitoring-of-grassland-and-livestock-current-status-challenges-and-next-steps", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/HGTPJN/", "title": "Global monitoring of grassland and livestock: Current status, challenges and next steps", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "While forest monitoring has reached high levels of maturity, grassland ecosystems remain a critical \"blind spot\" in global conservation. To address this, Global Pasture Watch (GPW) has established a comprehensive baseline using 30m multi-decadal datasets (2000\u20132022) covering grassland extent, vegetation height, and livestock density. However, the inherent heterogeneity and rapid seasonality of these landscapes present significant current challenges for traditional pixel-based classification. To overcome these barriers, our next steps involve transitioning to next-generation machine learning models that utilize Sentinel-2 spatial-temporal embeddings. By moving beyond simple spectral signatures to rich, high-dimensional latent representations, we can better capture the nuances of managed vs. natural grasslands and monitor Gross Primary Productivity (GPP) with unprecedented precision. This evolution in our workflow aims to deliver near-real-time, actionable insights, transforming how we track land-use conversion and guide sustainable restoration across the world\u2019s most vulnerable non-forest biomes.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 40, "code": "K8AZA9", "public_name": "Leandro Parente", "biography": "Leandro Parente is a senior researcher at OpenGeoHub Foundation with more than 15 years of experience in processing Earth Observation (EO) data and developing Machine Learning (ML) pipelines for producing continental and global maps.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 513, "guid": "74ca81a2-b16c-5cc5-aadd-7cb72a809e3d", "logo": "", "date": "2026-10-07T17:15:00+02:00", "start": "17:15", "duration": "00:15", "room": "Room 18", "slug": "global-workshop-2026-513-high-resolution-grassland-gpp-estimation-with-landsat-and-sentinel-2", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/E3KZMH/", "title": "High-Resolution Grassland GPP Estimation with Landsat and Sentinel-2", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "We present an updated generation of the Global Pasture Watch (GPW) gross primary productivity (GPP) products for grassland ecosystems at 30 m spatial resolution. This new release builds on the original Landsat-based light use efficiency framework by integrating improved MODIS land surface temperature (MOD21) and updated photosynthetically active radiation inputs, while also introducing an experimental Sentinel-2-based GPP product. The combined use of Landsat and Sentinel-2 observations strengthens the capacity to monitor grassland productivity dynamics with improved spatial detail and temporal consistency across local to global scales. Beyond long-term ecosystem assessment and grassland monitoring, the updated GPW GPP products are also intended to support near-real-time (NRT) grassland biomass estimation within the Time2Graze project.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 247, "code": "FWUSQK", "public_name": "Mustafa Serkan Isik", "biography": "-", "answers": []}], "links": [], "attachments": [], "answers": []}]}}, {"index": 2, "date": "2026-10-08", "day_start": "2026-10-08T04:00:00+02:00", "day_end": "2026-10-09T03:59:00+02:00", "rooms": {"Aula Magna": [{"id": 393, "guid": "02830f19-2ab2-55d1-961f-3e3e84c36ff9", "logo": "/media/global-workshop-2026/submissions/7NRN3X/Drowing_wisdom_yZWTYYN.jpg", "date": "2026-10-08T10:30:00+02:00", "start": "10:30", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-393-from-data-to-information-and-policy-to-implementation", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/7NRN3X/", "title": "From Data to information and Policy to Implementation", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Satellite data have transformed our ability to observe land-use dynamics, forest change, and environmental pressures at unprecedented spatial and temporal scales. Yet a critical challenge remains: translating vast volumes of data into actionable information that meaningfully informs policy and leads to real-world implementation. This talk highlights the importance of open and transparent data, with a particular emphasis on the ease of accessing information and answering practical questions using data to drive evidence-based decision-making. It underscores the need to integrate satellite-derived land-use and forest data, along with information on change and its impacts on climate, nature, and people, into operational platforms and planning processes. By doing so, governments, supply chains, and local stakeholders can better assess risks, target interventions, and track outcomes. Transforming data into decision-ready insights is essential for strengthening land-use governance, advancing sustainable forest management, and delivering measurable environmental and social impacts.", "description": "Keynote", "recording_license": "", "do_not_record": false, "persons": [{"id": 452, "code": "QX9LVP", "public_name": "Fred Stolle", "biography": "Fred Stolle is Deputy Director of Global Nature Watch and Global Forest Watch at the World Resources Institute (WRI), where he has worked since 2003. He is an internationally recognized expert in the use of geospatial data to understand land-use dynamics and their implications for climate change, ecosystems, and sustainable development. His work focuses on quantifying environmental drivers and translating complex spatial data into actionable insights for policymakers, practitioners, and decision-makers worldwide.\r\nTrained in Geographic Information Systems (GIS) and remote sensing, Fred has lived and worked across Latin America, Africa, Asia, Europe, and the United States, bringing a global perspective to environmental monitoring and policy-relevant analysis. His professional experience includes roles with UNEP in Nairobi and collaborations with UNESCO, the World Agroforestry Centre (ICRAF), and the Center for International Forestry Research (CIFOR) in Indonesia. He has also served as an adjunct professor at Johns Hopkins University\u2019s School of Advanced International Studies (SAIS), as lead technical assessor for forest carbon monitoring systems for the World Bank\u2019s BioCarbon Fund, and as a contributor to multiple international working groups on spatial data and environmental monitoring. Fred is based in Washington, DC, and holds an MSc in Biology and a PhD in Geography.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 538, "guid": "6acdb6b0-afcd-5334-9393-585b0b15386d", "logo": "", "date": "2026-10-08T11:00:00+02:00", "start": "11:00", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-538-keynote", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/AADXE7/", "title": "Keynote", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Keynote talk by Xavier Pons. Abstract and title to be provided.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 540, "code": "T73WA8", "public_name": "Xavier Pons", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 531, "guid": "17fdeb77-e9ca-5468-a3aa-b7fd099b247c", "logo": "", "date": "2026-10-08T11:30:00+02:00", "start": "11:30", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-531-ai-for-climate-resilience-from-data-to-decisions-that-matter", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/NWX9DD/", "title": "AI for Climate Resilience: From Data to Decisions that Matter", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Artificial Intelligence offers powerful tools to understand and respond to the climate crisis, but there are no shortcuts or silver bullets. Bigger models or geoengineering schemes alone won't solve our challenges. What matters is applying AI where it can make a real difference and for those who need it most: monitoring crops and ensure food security levels, tracking air quality, predicting floods and wildfires, and supporting vulnerable communities on the frontlines of climate change. In this talk, I will share how combining satellite data, local knowledge, and advances in explainable and causal AI can turn information into actionable insights. From anticipating extreme weather to guiding humanitarian responses, these applications show how AI can strengthen decision-making and build climate resilience, helping policymakers act today for a more sustainable tomorrow.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 518, "code": "BUPUPV", "public_name": "Gustau Camps-Valls", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 466, "guid": "a28fb37f-9d60-535a-9ec5-fe632042e56a", "logo": "", "date": "2026-10-08T12:00:00+02:00", "start": "12:00", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-466-openeo-from-an-idea-in-a-whitepaper-to-a-community-standard-in-the-geospatial-data-processing-", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/XM77A8/", "title": "openEO from an idea in a whitepaper to a community standard in the geospatial data processing.", "subtitle": "", "track": "Forest and biodiversity", "type": "Keynote lecture", "language": "en", "abstract": "Acknowledging the value of earth observation data and sharing the frustration in the difficulty of working with it, just shy of 10 years ago a group of earth observation scientists and practitioners set out to described their vision (https://r-spatial.org/2016/11/29/openeo.html) of how they would like to work with this treasure of data without falling into the traps of a vendor lock-in, custom codes for data access and the need to deal with 15 different data formats. Inspired by the way gdal solved the latter of these problems for raster data driven GIS systems, they envisioned an API agnostic to both the clients programming language and the server site implementation of EO processing workflows. I joined this group of like-minded researchers in the Horizon 2020 project openEO that was funded about a year after.\r\nDuring this keynote I will talk about the importance of open-source development and community building in conjunction with the importance of public funding from the European Commission and the European Space Agency as the two main supporters of making this idea a reality. OpenEO is based on an approach of co-design and co-development, involving both earth observation data analysts and researchers as well as software developers and industry service providers right from the start. It is now available as part of many operational service offerings, such as openEO platform, the Copernicus Data Space Ecosystem and Destination Earth.  openEO is not only the foundation of individual service offerings, but even federations of multiple implementations, sharing data and processing resources leveraging efficient interoperability based on cloud native data formats and harmonized specifications for, data discovery, access, processing and sharing of results. It is fully embracing the FAIR data principles, while supporting researchers and data analyst to focus on what the want to do instead of how the implementations needs to be optimized for modern scalable data infrastructures.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 109, "code": "NBVUM3", "public_name": "Alexander Jacob", "biography": "Alexander Jacob is the Vice-Head of the Institute for Earth Observation at Eurac Research in Italy and coordinator of the research group Advanced Computing. He is passionate about geographic data and software development since his times as a student of geodesy and geoinformatics in Darmstadt, Germany and Stockholm, Sweden. He is an Italian representative towards the Group on Earth Observation (GEO) for the Data & Knowledge working group as well as one of the co-chairs of the Open Geospatial Consortium (OGC) GeoDataCubes Standards Working Group. He has served as an advisor for the European Space Agency (ESA) and the Joined Research Centre (JRC) of the European Commission (EC) in questions of Earth Observation Data Management and Computing.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 533, "guid": "aaaf5d04-aaba-5dc2-9aab-b29227b6da0d", "logo": "", "date": "2026-10-08T12:30:00+02:00", "start": "12:30", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-533-from-land-cover-change-to-greenhouse-gases-an-open-geospatial-monitoring-framework", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/TLBCMP/", "title": "From Land Cover Change to Greenhouse Gases: An Open Geospatial Monitoring Framework", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Greenhouse gas (GHG) emissions from Agriculture, Forestry and Other Land Uses (AFOLU) account for roughly one-quarter of global net anthropogenic emissions, yet consistent monitoring remains challenging. We present a global, open, spatially explicit monitoring framework developed by WRI\u2019s Land & Carbon Lab and partners that combines Earth observation data, geospatial models, and IPCC inventory methods to map land-related emissions and removals from 2016\u20132024. Accessible through Global Nature Watch and other platforms, the system integrates datasets on land cover change, forest dynamics, fire, biomass, soils, livestock, and agricultural management. We highlight applications for governments, civil society, companies, researchers, and policymakers supporting climate action and progress tracking.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 535, "code": "SNCGX7", "public_name": "Nancy Harris", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 464, "guid": "fbf2d458-626b-5ca7-8050-0d3c70813604", "logo": "", "date": "2026-10-08T16:15:00+02:00", "start": "16:15", "duration": "00:15", "room": "Aula Magna", "slug": "global-workshop-2026-464-soil-moisture-memory-as-a-regulator-of-hydrologic-response-in-the-po-river-basin-italy-", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/MRHJ3P/", "title": "Soil-Moisture Memory as a Regulator of Hydrologic Response in the Po River Basin (Italy)", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "Hydroclimatic forcing of similar magnitude can produce contrasting hydrologic responses within the same basin. Here, we investigate how soil-moisture memory (SMM) regulates the translation of atmospheric anomalies into basin-scale hydrologic response across the Po River Basin. To address this question, we developed an open and reproducible Earth-observation workflow based on a multi-source data cube that integrates Sentinel-1 observations with hydroclimatic forcing represented by the Precipitation\u2013Evapotranspiration Anomaly Index (PEAI), derived from HYPER-P precipitation and GLEAM evapotranspiration for 2016\u20132022. This framework enables assessment of how SMM varies across land-surface types and during major hydroclimatic transition episodes. \r\n\r\nThe analysis reveals marked contrasts across the basin. Irrigated agricultural areas exhibit the strongest memory, with median persistence close to 3 weeks and low instability (~0.19), whereas changed surfaces show weaker and more volatile behavior, with persistence of about 1.7 weeks and instability approaching 0.24. Non-irrigated agricultural areas define a distinct intermediate regime, characterized by lower persistence and higher instability than irrigated areas, but less volatility than changed surfaces. At the basin scale, major forcing episodes affect approximately 80\u201390% of the basin, yet response hotspots typically occupy only 20\u201340%, indicating that atmospheric anomalies are not expressed uniformly but are selectively filtered by antecedent basin state and land-surface conditions. \r\n\r\nEvent-based analysis further shows that the hydrologic expression of forcing reversal depends strongly on antecedent SMM conditions. A continuous 28-day drought\u2013flood abrupt alternation (DFAA) sequence in May\u2013June 2020, automatically detected from the 2016\u20132022 record, includes a major drought-to-flood transition (DTF) from 21 May to 4 June and a major flood-to-drought transition (FTD) from 4 to 18 June. Although the two phases exhibit near-equivalent PEAI amplitudes, reversing from -1.195 to 2.176 during the DTF phase (\u0394 = 3.371) and from 2.176 to -1.250 during the subsequent FTD phase (\u0394 = 3.426), the resulting basin-scale responses are asymmetrical, indicating that forcing reversal of similar magnitude is not translated into equivalent hydrologic expression. These results indicate that hydrologic response to forcing reversal depends more strongly on antecedent soil-moisture memory than on forcing amplitude alone. \r\n\r\nAdditional comparisons among automatically detected FTD events with similar forcing trajectories reinforce this interpretation. Two major transitions, detected on 5 March 2020 and 13 May 2021, show comparable forcing duration and amplitude but differ substantially in timing, coherence, and post-transition evolution. These contrasts are consistent with distinct memory regimes: the 2020 event is associated with low persistence (~0.20) and sustained high instability (~0.75), whereas the 2021 event combines very low persistence at transition (~0.13) with rapid recovery toward higher persistence and lower instability thereafter. Overall, the results show that antecedent soil-moisture memory and land-surface conditions exert a strong control on how hydroclimatic forcing is translated into basin-scale hydrologic response.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 410, "code": "3SMXY3", "public_name": "imane serbouti", "biography": "Imane Serbouti received the M.S. degree in GIS and Remote Sensing for Geosciences and Environment and the Ph.D. degree in Geospatial Big Data and Geosciences, both with excellence, from Hassan II University, Casablanca, Morocco. She is currently a researcher at the National Research Council of Italy (CNR). She was previously a postdoctoral researcher at Mohammed VI Polytechnic University (UM6P), where she worked on geospatial urban big data. Her main research interests lie in remote sensing, satellite Earth observation, geospatial data analysis, and GeoAI for applications in environmental monitoring, disaster risk assessment, climate resilience, and sustainable land and water systems.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 499, "guid": "a8c7c1b6-7957-5f38-83c7-7793a11d34ab", "logo": "", "date": "2026-10-08T16:30:00+02:00", "start": "16:30", "duration": "00:15", "room": "Aula Magna", "slug": "global-workshop-2026-499-how-fair-is-geospatial-data-an-assessment-of-oemc-datasets", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/X97YJS/", "title": "How FAIR Is Geospatial Data? An Assessment of OEMC Datasets", "subtitle": "", "track": "Climate and Health", "type": "Oral talk", "language": "en", "abstract": "As FAIR principles become increasingly central to open science and research data stewardship, a persistent gap remains between their broad endorsement and their consistent practical validation in real-world repositories. This challenge is particularly visible for geospatial datasets, where domain-specific requirements such as spatial formats, metadata richness, and interoperability standards are not always captured by general FAIR assessment approaches. In this work, a structured FAIR assessment was applied to datasets produced within the Open-Earth-Monitor Cyberinfrastructure (OEMC) project. To support the evaluation, we developed a FAIR assessment tool tailored to geospatial data entries published on Zenodo, while designing the underlying framework to remain flexible and transferable to other repository environments. The assessment identifies both strengths and recurring gaps in current data publication practices and provides actionable recommendations for improving the long-term usability, transparency, and scientific value of geospatial datasets.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 205, "code": "3QHGZS", "public_name": "Imma Serra", "biography": "Research technician at the Centre for Ecological Research and Forestry Applications (CREAF) in the research group of Remote Sensing and Geographic Information Systems (GRUMETS).", "answers": []}, {"id": 247, "code": "FWUSQK", "public_name": "Mustafa Serkan Isik", "biography": "-", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 489, "guid": "4822532c-a5c9-5fe1-bf35-38542cd86bea", "logo": "", "date": "2026-10-08T16:45:00+02:00", "start": "16:45", "duration": "00:45", "room": "Aula Magna", "slug": "global-workshop-2026-489-working-with-and-visualizing-geofoundational-ai-embeddings", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/BPWMLF/", "title": "Working with and visualizing GeoFoundational AI embeddings", "subtitle": "", "track": "Forest and biodiversity", "type": "Workshop proposal", "language": "en", "abstract": "GeoFoundation embeddings encode huge amounts of Earth Observation data and by condensing this into a small vector of numbers, they can make many downstream analyses much easier to perform. However, the embeddings represent a latent state and as such can be abstract to understand. \r\nThis workshop aims to demonstrate how embeddings can be used and explore how to visualize them and make them more usable.", "description": "Workshop structure:\r\n\r\nGeoFoundation embeddings demonstration (15 mins) - \r\nDemonstration of the embeddings and their use so far:\r\n- Pixelwise landuse classification from labels\r\n- Detecting solar panels\r\n\r\nVisualizing & understanding embeddings (15 mins) - \r\nDemonstration of visualizing embeddings and building intuition for these latent representations\r\n\r\nWorking with embeddings discussion (15 mins) - \r\nDiscussion: \r\n- What do you want to use embeddings for?\r\n- Where are embeddings useful compared to raw imagery?\r\n- What functionalities do you want to interact with Tessera embeddings?", "recording_license": "", "do_not_record": false, "persons": [{"id": 456, "code": "PNXLNE", "public_name": "Zhengpeng (Frank) Feng", "biography": "Zhengpeng (Frank) Feng is a second-year Ph.D. candidate in the Energy and Environment Group, Department of Computer Science and Technology, at the University of Cambridge. His research interests lie at the intersection of machine learning and earth sciences, with a particular focus on developing self-supervised learning methods in remote sensing.", "answers": []}, {"id": 499, "code": "BDSN9P", "public_name": "Mike Harfoot", "biography": "Mike Harfoot is an interdisciplinary ecological scientist with over 15 years of experience building models that try to make sense of life on Earth, from individual organisms up to entire ecosystems. He is best known for co-developing the Madingley General Ecosystem Model, one of the first mechanistic models to simulate the full complexity of terrestrial and marine ecosystems, and has contributed to major international biodiversity frameworks including IPBES. He works as a Scientist at Vizzuality and is an Adjunct Professor at Dalhousie University. His recent work includes a high-profile review of AI for nature and a climate risk index for marine biodiversity.\r\n\r\nAlongside his research, Mike is the Founder and Chair of OpenNature, a growing coalition of over 20 organisations working to improve how biodiversity knowledge is created and shared. Prior to joining Vizzuality he led ecology and biodiversity modelling projects at UNEP-WCMC.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 459, "guid": "df6da50a-eada-54ff-8044-f62057793dee", "logo": "/media/global-workshop-2026/submissions/QGFTAX/1774351273309_N44o1x4.jpeg", "date": "2026-10-08T18:00:00+02:00", "start": "18:00", "duration": "00:45", "room": "Aula Magna", "slug": "global-workshop-2026-459-the-1-km-illusion-in-remote-sensing-for-hydrology", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/QGFTAX/", "title": "The 1-km illusion in remote sensing for hydrology", "subtitle": "", "track": "Soil, water and agriculture", "type": "Workshop proposal", "language": "en", "abstract": "Sampling is not actual resolution: the 1 km illusion in satellite hydrology refers to the discrepancy between a dataset's digital sampling grid and its true physical resolution. The \"rush\" to create high-resolution data has outpaced the ability to validate it on the ground due to missing in situ monitoring networks required to independently validate 1 km algorithms on a global scale. While many modern satellite hydrological products are labeled as \"1 km\" resolution, this often reflects how the data is stored on a grid rather than what the sensor actually \"sees\". These products frequently remain \"physically blind\" to hyper-local anomalies. The fundamental challenge resides in the intrinsic trade-off between spatial resolution and temporal frequency.\r\n\r\nWith regard to satellite soil moisture products, active radar sensors (e.g. Sentinel-1) provide true 1 km spatial acuity but suffer from temporal gaps, while passive radiometers (e.g. SMAP) offer excellent daily tracking but produce oversampled illusions at the 1 km scale. For practitioners, the selection of a dataset must be dictated by the physical scale of the hydrological event\u2014ranging from farm-scale irrigation to continental-scale drought\u2014rather than the digital label on the file.\r\n\r\nIn the workshop, a series of real-world stress tests of the \"1 km illusion in satellite hydrology\" will be presented. These stress tests will demonstrate the hydrological applications of the 1 km illusion, including the mapping of localised summer storms, the estimation of irrigation at the field scale, and the impact of wildfires on water infiltration.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 20, "code": "8RHQVS", "public_name": "Luca Brocca", "biography": "https://www.irpi.cnr.it/en/persona/brocca-luca/", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 483, "guid": "06f1c6da-322c-58cf-a7d9-98098813d257", "logo": "", "date": "2026-10-08T18:45:00+02:00", "start": "18:45", "duration": "00:15", "room": "Aula Magna", "slug": "global-workshop-2026-483-democratizing-field-boundary-delineation-in-the-global-south-with-ai-", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/QEER9E/", "title": "Democratizing Field Boundary Delineation in the Global South with AI.", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "Accurate crop field boundary delineation is foundational for agricultural mapping, yield estimation, and decision support systems. Yet existing AI models, trained predominantly on data from the Global North, perform poorly in underrepresented farming systems such as those in Sub-Saharan Africa (typically under 2 hectares, irregularly shaped) and South America (characterized by shifting cultivation and complex morphologies). This data gap misleads agricultural statistics, weak policies, and inefficient resource allocation. \r\n\r\nWe leveraged AI and open-source remote sensing data to automatically delineate field boundaries in both regions using transfer learning, adapting pretrained global models to local contexts. In South America, we annotated over 46,000 field boundaries for model training and generated more than 10 million boundaries continent-wide. In East Africa's Great Rift Valley, we automatically detected over 400,000 farms from just 6,000 samples, incorporating multi-stakeholder annotation workflows and quality assurance pipelines refined from lessons learned in South America. \r\n\r\nOur results show that models trained on limited but high-quality local annotations scale effectively to out-of-sample regions. In Africa, delineated fields have enabled field level crop type and yield data collection, in preparation for field level crop type mapping, yield estimation and monitoring of agroecological and regenerative agriculture practices. In South America, they have supported supply chain auditing for deforestation-free commitments, EUDR compliance, country-level crop forecasting, and scope 3 emissions estimation. Across both regions, the approach has strengthened national and subnational agricultural data systems and climate resilience frameworks. \r\n\r\nBy demonstrating AI model transferability across contrasting geographies, this work charts a pathway toward open, inclusive, and scalable Earth observation systems that close critical data gaps in the Global South, positioning AI as a core enabler of sustainable agricultural monitoring at national and subnational scales.", "description": "We piloted the project in South America and used the lessons learnt to apply it in Africa. While the scientific approach was similar, the methodology of application from data collection to use case development differed between South America and Africa. \r\nWe will provide a guide on stakeholder collaboration and coordination and use case development based on lessons learnt in Africa.", "recording_license": "", "do_not_record": false, "persons": [{"id": 506, "code": "ER9XUL", "public_name": "Christine Muthee", "biography": "\u200bAI mapping of smallholder crop data \u2013 Scientific Data Research Highlight (2025). \r\ndoi: https://doi.org/10.1038/d44148-025-00280-5 \r\n\r\n\u200bAsamoah Oppong, Z. (2022). AI\u2011Driven Crop Yield Prediction Models for Smallholder Farmers in Sub\u2011Saharan Africa. Iconic Research and Engineering Journals, Volume 5 Issue 9. \r\n\r\n\u200bBecker\u2011Reshef, I., et al. (2023). Strengthening food security monitoring through satellite\u2011based crop type and yield estimation. Remote Sensing Environment, 292, 113577. \r\n\r\n\u200bGeyman et\u202fal. (2025). An Africa\u2011wide agricultural production database to support policy and satellite\u2011based measurement systems. Scientific Data (Nature). \r\n\r\n\u200bGokool, S., Mahomed, M., Brewer, K., Naiken, V., Clulowa, A., Sibanda, M., Mabhaudhi, T. (2024). Crop mapping in smallholder farms using unmanned aerial vehicle imagery and geospatial cloud computing infrastructure. Heliyon, 10 (2024) e26913. \r\n\r\n\u200bGuo, Z. (2024). From Space to Soil: Advancing Crop Mapping and Ecosystem Insights for Smallholder Agriculture. \r\n\r\n\u200bJayne, T.S., Muyanga, M., Wineman, A., et al. (2019). Are medium-scale farms driving agricultural transformation in sub-Saharan Africa? Agricultural Economics, 50:75\u201395. \r\nhttps://doi.org/10.1111/agec.12535 \r\n\r\n\u200bKerner, H., Chaudhari, S., Ghosh, A., Robinson, C., Ahmad, A., Choi, E., Jacobs, N. et al. (2024). Fields of The World: A Machine Learning Benchmark Dataset for Global Agricultural Field Boundary Segmentation. arXiv preprint arXiv:2409.16252. \r\n\r\n\u200bLida, K., Rahim, S., Hutber, C., Grau, G., Moss, C., & Douglas, O. (2026). Government AI Readiness Index 2025. Oxford Insights. \r\n\r\n\u200bMusoni, M., & Adeniyi, D. (2025). How AI can benefit smallholder farmers in Africa: Opportunities for EU\u2011Africa. ECDPM Discussion Paper No. 396. \r\n\r\n\u200bNakalembe, C., et al. (2025). Challenges and opportunities for crop type mapping in smallholder systems of sub\u2011Saharan Africa. Remote Sensing, 17(2), 412. \r\n\r\n\u200bOmotoso, A.B., & Omotayo, A.O. (2024). The interplay between agriculture, greenhouse gases, and climate change in Sub-Saharan Africa. Regional Environmental Change, 24, 1 (2024). \r\nhttps://doi.org/10.1007/s10113-023-02159-3 \r\n\r\n\u200bPotapov, P., Turubanova, S., Hansen, M.C. et al. (2022). Global maps of cropland extent and change show accelerated cropland expansion in the twenty\u2011first century. Nature Food 3, 19\u201328 (2022). \r\nhttps://doi.org/10.1038/s43016-021-00429-z \r\n\r\n\u200bRahman, A.N., Kotu, B.H., Tetteh, F.M., Karikari, B., Akinseye, F.M., Ansah, T., Mutungi, C., & Kizito, F. (2024). Editorial: Sustainable intensification of smallholder farming systems in Sub\u2011Saharan Africa and South Asia. Frontiers in Sustainable Food Systems, 8:1399430. \r\ndoi: 10.3389/fsufs.2024.1399430 \r\n\r\n\u200bUnited Nations Department of Economic and Social Affairs. (2024). World population projections. \r\n\r\n\u200bUNFCCC (2025, November 15). Ethiopia: Press Briefing on hosting COP 32 in Ethiopia. Bel\u00e9m, Brazil. \r\n\r\n\u200bWang, S., Waldner, F., & Lobell, D.B. (2022). Unlocking Large-Scale Crop Field Delineation in Smallholder Farming Systems with Transfer Learning and Weak Supervision. Remote Sensing 14 (22): 5738. doi:10.3390/rs14225738. \r\n\r\n\u200bWRI Africa (2026). AI Mapping for Small-Scale Farm Transformation. \r\nhttps://africa.wri.org/initiatives/ai-mapping-small-scale-farm-transformation\u200b", "answers": []}, {"id": 509, "code": "CTMG7H", "public_name": "Tristan Grupp", "biography": "Tristan Grupp is an Agricultural Data Scientist in the Food, Land, and Water Program and Data Lab at the World Resources Institute. He collaborates closely with Land and Carbon Lab. His current research focuses on applying remote sensing and machine learning to monitor deforestation and natural land conversion driven by agricultural supply chains, supporting commodity traceability and corporate sustainability compliance, including under the EU Deforestation Regulation (EUDR). His work spans forest change monitoring, climate adaptation, and the intersections of food systems and natural landscapes. Beyond WRI, Grupp has contributed to research on climate change adaptation tracking in support of national adaptation planning under the UNFCCC, protected area policy evaluation in the EU, and tropical forest dynamics in the Peruvian Amazon. He has presented his work at international venues including AGU, COP, and the UN National Adaptation Planning Conference.", "answers": []}], "links": [], "attachments": [], "answers": []}], "Rooms 12+14": [{"id": 506, "guid": "10760485-3aaa-55c8-8590-c4346ba6734e", "logo": "", "date": "2026-10-08T16:00:00+02:00", "start": "16:00", "duration": "00:45", "room": "Rooms 12+14", "slug": "global-workshop-2026-506-driades-a-collaborative-browser-based-forest-monitoring-dashboard-built-on-cloud-native-geospatial-formats", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/WQBUZF/", "title": "Driades: A Collaborative, Browser-Based Forest Monitoring Dashboard Built on Cloud-Native Geospatial Formats", "subtitle": "", "track": "Forest and biodiversity", "type": "Workshop proposal", "language": "en", "abstract": "Monitoring forest cover change, wildfire risk, and post-fire recovery demands integrating heterogeneous data sources (i.e. satellite imagery, field observations, weather feeds, and alert systems) into a shared operational picture. Yet existing tools force a choice: either powerful but expensive proprietary platforms, or open-source solutions that require significant server infrastructure and maintenance.\r\n\r\nThis workshop introduces Driades, an open-source, self-hosted geospatial tool developed by h4ck1ng.science that runs entirely in the browser with no backend server. By leveraging cloud-native formats (Zarr, GeoParquet, and PMTiles among others) served directly from S3-compatible object storage, Driades enables users to visualise satellite imagery, execute spatial SQL queries via WASM, and run basic transformations using WebGPU. Heavy computational tasks (such as machine learning inference for burn scar detection) can be offloaded to remote APIs, keeping the client lightweight while providing access to geospatial foundation models hosted on model registries like Hugging Face.\r\n\r\nDriades aims to reduce the friction of accessing and sharing geospatial data, providing non-experts with a simple interface to explore, annotate, and distribute interactive results among collaborators without requiring specialised infrastructure.", "description": "During the 45-minute hands-on session, participants will: (1) load and explore Sentinel-2 imagery and other geospatial datasets from static files on cloud storage, with zero server configuration; (2) run in-browser spatial analytics using SQL; (3) collaboratively annotate areas of interest on a shared map; and (4) submit a region to an AI model for automated semantic segmentation and visualise the results as a map layer.\r\n\r\nParticipants are invited to write to hi@h4ck1ng.science with proposals on which data would they like to work with.", "recording_license": "", "do_not_record": false, "persons": [{"id": 517, "code": "8DTQJQ", "public_name": "Carlos Vivar R\u00edos", "biography": "Hi! I'm Carlos, a Biologist and Data Engineer with experience spanning genomics, microscopy and satellite multidimensional image analysis, cellular biology modelling, and web development. I currently work as a Senior Data Engineer at the Swiss Data Science Center at EPFL, where I focus on building tools and pipelines for scientific data. I'm passionate about learning across disciplines and am a frequent hackathon participant; there's nothing better than building something unexpected with extraordinary people in 48 hours. \r\n\r\nCheck out my GH -> github.com/caviri", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 492, "guid": "416ec413-37ad-55f4-91dd-b9a2948ac25b", "logo": "/media/global-workshop-2026/submissions/YKFVG9/Tom_Hengl_Landsat_V2_2026_Utrecht_EufEnlD.jpg", "date": "2026-10-08T16:45:00+02:00", "start": "16:45", "duration": "00:45", "room": "Rooms 12+14", "slug": "global-workshop-2026-492-landsat-monthly-cloud-free-complete-consistent-mosaics-2000-2025", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/YKFVG9/", "title": "Landsat monthly cloud-free complete consistent mosaics 2000-2025", "subtitle": "", "track": "Soil, water and agriculture", "type": "Workshop proposal", "language": "en", "abstract": "One of the most significant deliverables of the OEMC project are global, cloud-less Landsat monthly time series from 2000\u20132025 at 30 m resolution. The Landsat global mosaics (V1) are explained in detail in Consoli et al. (2025; https://peerj.com/articles/18585/). The Landsat V2 is at the order of magnitude more ambitious aiming at monthly products in 16bit format and will significantly less artifacts. The  pipeline uses a four-step process for improved quality, including gap-filling using spatial and temporal neighbours, data fusion and final gap filling using global models. The results of cross-validation show improvements in accuracy in consistency. Major project challenges include needing 1PB of storage and securing post-2025 commercial services. Landsat V2 can also be used to derive embeddings for 2000-2025.", "description": "Landsat bimonthly is available via https://browser.stac.dataspace.copernicus.eu/collections/opengeohub-landsat-bimonthly-mosaic-v1.0.1?.language=en", "recording_license": "", "do_not_record": false, "persons": [{"id": 1, "code": "8QMFTU", "public_name": "Tom Hengl (OpenGeoHub)", "biography": "Tom has more than 25 years of experience as an environmental modeler, data scientist and spatial analyst. Tom has a background in soil mapping and geo-information science (PhD at Wageningen University / ITC). He continuously runs hands-on-R training courses to promote use of Open Source software for spatial analysis / spatial modeling purposes. He is currently the project leader of the Open-Earth-Monitor project (https://doi.org/10.3030/101059548) and Director at the OpenGeoHub foundation. Tom is recipient of the Clarivate Highly Cited Researchers for 2021, 2022, 2023, 2024 and 2025. Several of his paper have received the best paper awards including the \"Finding the right pixel size\" (https://doi.org/10.1016/j.cageo.2005.11.008), \"Soil property and class maps of the conterminous USA\" (https://doi.org/10.2136/sssaj2017.04.0122), his articles published in PeerJ are among top 10 most cited of all time; his PLOS One paper (https://doi.org/10.1371/journal.pone.0169748) is listed among the most cited in the field.", "answers": []}, {"id": 504, "code": "CEMWWL", "public_name": "Sajed", "biography": "Sajed Sarabandi is a software engineer and junior researcher specializing in remote sensing at the OpenGeoHub Foundation. He holds a Master\u2019s degree in Computer Science from Leiden University.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 476, "guid": "d6e0841b-2349-53e6-9ae9-251021dd44d2", "logo": "", "date": "2026-10-08T18:00:00+02:00", "start": "18:00", "duration": "00:45", "room": "Rooms 12+14", "slug": "global-workshop-2026-476-the-fluxnet-shuttle-enabling-access-to-globally-distributed-flux-tower-data", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/NS7Z9N/", "title": "The FLUXNET Shuttle: Enabling Access to Globally Distributed Flux Tower Data", "subtitle": "", "track": "Forest and biodiversity", "type": "Workshop proposal", "language": "en", "abstract": "The collaboration among PIs of eddy covariance sites, Research Infrastructures and Regional Data Hubs gave birth to a new system for sharing globally distributed, standardized flux tower datasets: the FLUXNET Data System Initiative. The system is a milestone for the ecosystem flux community and its stakeholders (e.g. satellite and modeling communities), for it allows to shift from static, periodic releases (FLUXNET2015) to a quasi-real-time approach, in which datasets become findable as soon as they are processed and quality-controlled. The FLUXNET Data System Initiative is built upon three pillars: uniform (meta)data formatting; a unique processing software (ONEFlux) used by the three Regional Hubs (ICOS, AmeriFlux and OzFlux/TERN); a data access tool based on APIs: the FLUXNET Shuttle, developed in the context of the OEMC project. Written in Python and available on GitHub, the Shuttle is a one-step access system that enables users to find and download open-licensed eddy covariance datasets worldwide with simple queries executed via command line or graphical interfaces. Different search criteria are available to discover the datasets, no matters where they have been collected and by which of the three Regional Hubs they have been processed. The Shuttle enables the definition of new standards for flux data interoperability. \r\n\r\nParticipants to this workshop will be able to search and download eddy covariance datasets from different sites. A quick overview of the datasets characteristics (data format, metadata available, variables included) will be provided at the beginning, and then attendees will install the Shuttle on their own devices and explore its functionalities. By the completion of two exercises, participants will become acquainted with potential use cases of global flux tower datasets, like comparison of ecosystem responses to stressors across different climate conditions.", "description": "References:\r\nhttps://github.com/fluxnet/shuttle\r\nhttps://fluxnet.org/fluxnet-data-system/\r\nhttps://github.com/fluxnet/ONEFlux", "recording_license": "", "do_not_record": false, "persons": [{"id": 93, "code": "PV3JKJ", "public_name": "Simone Sabbatini", "biography": "Simone Sabbatini has a PhD in Forest Ecology, obtained in 2014 at the DIBAF department of the University of Tuscia, Viterbo, Italy. His background consists in a BSC in Forestry and Environmental Science, and a MSC in Management of Forestry Systems, both held at the University of Florence, Italy. Currently he is a Researcher at the Euro-Mediterranean Center on Climate Change (CMCC), where he is involved in the activities of the ICOS Ecosystem Thematic Center (ETC), dealing with giving support to the ICOS stations concerning eddy covariance measurements, meteorological data collection, data and metadata file submission, as well as contributing to the implementation of new variables for CAL/VAL activities at ICOS stations. He coordinates the processing of FLUXNET sites from China, Japan and South Korea in the FLUXNET Data System Initiative. In addition, he is also supervising the activities of PhD students at the DIBAF.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 399, "guid": "a8b3b3ce-3c84-5b75-89b9-7886b9515d63", "logo": "", "date": "2026-10-08T18:45:00+02:00", "start": "18:45", "duration": "00:15", "room": "Rooms 12+14", "slug": "global-workshop-2026-399-from-eo-data-to-urban-woody-vegetation-structure-a-reproducible-workflow-for-national-scale-tree-and-shrub-mapping", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/TETSF9/", "title": "From EO Data to Urban Woody Vegetation Structure: A Reproducible Workflow for National-Scale Tree and Shrub Mapping", "subtitle": "", "track": "Forest and biodiversity", "type": "Oral talk", "language": "en", "abstract": "High-resolution information on woody vegetation structure is increasingly required for biodiversity monitoring, urban planning, and environmental assessment, particularly in heterogeneous urban and peri-urban landscapes where trees and shrubs are poorly represented in conventional land-cover products. While Earth observation (EO) data provide new opportunities to capture fine-scale vegetation structure, many workflows remain closely tied to specific data environments and lack transparent, transferable implementation.\r\nThis contribution presents an open and reproducible workflow for mapping trees and shrubs across urban areas in Switzerland at national scale. The approach integrates airborne LiDAR-derived canopy height models with authoritative Swiss reference datasets, including cadastral data (AV) and the Topographic Landscape Model (TLM) to extract structurally distinct woody vegetation elements. Object-based segmentation and rule-based classification are implemented using LAStools and R, with explicit processing steps designed for transparency and reproducibility.\r\nThe workflow focuses on the delineation of above-ground woody structures, distinguishing individual trees and shrub patches based on canopy height, spatial configuration, and their relationship to reference datasets such as the national tree inventory (TLM). While airborne LiDAR provides detailed vertical information, the methodological logic can be adapted to alternative height sources such as photogrammetric surface models, stereo imagery, or emerging spaceborne products, where LiDAR is unavailable.\r\nResults from the national case study demonstrate how EO-derived above-ground structural information can complement existing cadastral and land-use datasets by providing spatially explicit woody vegetation objects in complex urban landscapes. Beyond the Swiss application, this work discusses key considerations for developing reproducible EO workflows, including data dependency management, scalability, and transferability. The presented workflow aims to support the Open-Earth-Monitor community by providing a transparent and adaptable framework for structural habitat mapping using high-resolution EO data.", "description": "Natalia Kolecka1*, Bronwyn Price1, Christian Ginzler1\r\n1Swiss Federal Research Institute WSL, Z\u00fcrcherstrasse 111, CH-8903 Birmensdorf, Switzerland\r\n*Corresponding author: natalia.kolecka@wsl.ch", "recording_license": "", "do_not_record": false, "persons": [{"id": 458, "code": "7CDHJ7", "public_name": "Natalia Kolecka", "biography": "https://www.linkedin.com/in/natalia-kolecka-76b18b168/", "answers": []}], "links": [], "attachments": [], "answers": []}], "Room 18": [{"id": 508, "guid": "aeb3fb61-14c8-5a01-abc0-f2dbb34eedd8", "logo": "", "date": "2026-10-08T18:00:00+02:00", "start": "18:00", "duration": "00:45", "room": "Room 18", "slug": "global-workshop-2026-508-accessing-global-multi-decade-landsat-cloud-free-time-series-in-cdse", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/9Q7PZY/", "title": "Accessing global multi-decade Landsat cloud-free time-series in CDSE", "subtitle": "", "track": "Soil, water and agriculture", "type": "Workshop proposal", "language": "en", "abstract": "In this workshop, the participants will have access to harmonized, analysis-ready, gap-filled and complete Landsat global mosaics from 1997 onward in cloud-optimized GeoTIFF (COG) format (130 TB of data) in CDSE (https://browser.stac.dataspace.copernicus.eu). Spanning over 25 years and structured in 7 spectral bands (RGB, NIR, SWIR-1, SWIR-2 and thermal), this data is instrumental for long-term monitoring applications of land cover change, soil proprieties, vegetation productivity, land degradation, vegetation height and other environmental characteristics. The global mosaics were produced via the Time-Series Iteration-free Reconstruction (TSIRF) framework over the entire Global Land Analysis and Discovery (GLAD) ARD Landsat archive (https://doi.org/10.7717/peerj.18585). Participants will learn about the implemented methodologies and use several python libraries (stacstac, scikit-map) JupyterLab.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 40, "code": "K8AZA9", "public_name": "Leandro Parente", "biography": "Leandro Parente is a senior researcher at OpenGeoHub Foundation with more than 15 years of experience in processing Earth Observation (EO) data and developing Machine Learning (ML) pipelines for producing continental and global maps.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 515, "guid": "9bbb5275-5cc4-5d19-a264-f5701c00bce1", "logo": "", "date": "2026-10-08T18:45:00+02:00", "start": "18:45", "duration": "00:15", "room": "Room 18", "slug": "global-workshop-2026-515-regional-earth-observation-foundational-models-improving-representation-of-domain-specific-patterns", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/H7T3W3/", "title": "Regional Earth Observation Foundational Models: Improving  Representation of Domain-Specific Patterns", "subtitle": "", "track": null, "type": "Oral talk", "language": "en", "abstract": "EO foundational models transform satellite images from a space-time grid of raw values into high-dimensional latent spaces called embeddings. These embeddings encode relationships between pixel values and the corresponding biophysical characteristics. Seasonal crop phenology (plant life cycle events), urban patterns, and forest canopy texture are each represented in different combinations of embedding dimensions. Researchers use these embeddings to train lightweight, downstream models for specific tasks, such as LULC (land use and land cover) classification, biomass estimation, or deforestation detection. These tasks require only a fraction of the computational power and labelled data.\r\nThe trend is to build massive, global-scale foundational EO models (such as TESSERA or AlphaEarth). Nevertheless, there is a strong case for developing dedicated regional foundational models. Global foundation models inherently seek universal statistical patterns, pushing representations toward generalised, highly simplified categories. A regional foundational model avoids this homogenization by optimising representations for local landscapes. By pre-training a foundation model on regional Earth observation data cubes, the latent space represents those specific regions. This prevents the model\r\nfrom importing spatial biases learned from entirely different continents, resulting in much higher-quality embeddings for local downstream tasks.\r\nThis presentation will show how to build regional EO foundational models using an easy-to-use API associated with the R/Python package SITS. Users can merge various sources, such as optical, radar, topographic, and climate data. The resulting EO embeddings will be better suited to regional applications than global products.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 11, "code": "WRMKR3", "public_name": "Gilberto Camara", "biography": null, "answers": []}, {"id": 31, "code": "FYV9YM", "public_name": "Felipe Carlos", "biography": null, "answers": []}, {"id": 519, "code": "3LEGDB", "public_name": "Rolf Sim\u00f5es", "biography": null, "answers": []}, {"id": 520, "code": "KRTZUC", "public_name": "Alexandre Assun\u00e7\u00e3o", "biography": null, "answers": []}, {"id": 521, "code": "XXRLBZ", "public_name": "Felipe Souza", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 480, "guid": "a8b8209f-afbe-5298-9819-c608fd198302", "logo": "", "date": "2026-10-08T19:00:00+02:00", "start": "19:00", "duration": "00:15", "room": "Room 18", "slug": "global-workshop-2026-480-a-multi-layer-gap-filling-pipeline-for-continuous-monthly-landsat-data-1997-2025-", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/A98WPB/", "title": "A Multi-Layer Gap-Filling Pipeline for Continuous Monthly Landsat Data (1997\u20132025)", "subtitle": "", "track": "Climate and Health", "type": "Oral talk", "language": "en", "abstract": "Time series and spatial modeling are commonly used to generate cloud- and gap-free satellite imagery. Most existing approaches reconstruct the entire dataset using advanced models, which requires high computational resources and time. In this study, we introduce a new, computationally efficient pipeline to reconstruct monthly Landsat data without gaps or clouds. The pipeline includes four levels of gap filling. In the first step, we apply a clean mask to biweekly Landsat data and create a 7-image weighted window spanning the current and neighbouring months. For each band and month across the 28-year period, we generate 25th and 75th percentile thresholds and calculate a weighted median, giving 50% weight to the current month and 25% to neighboring months, using only values within the 25th\u201375th percentiles. In the second step, remaining gaps are filled using an annual land cover classification derived from the GLAD dataset and Landsat data from up to ten previous years, restricted to pixels in the same land cover class. The third step fills small gaps of up to 2\u00d72 pixels using a 4\u00d74 averaging kernel. These steps fill approximately 40\u201360% of land pixels depending on tile location. Finally, a pretrained temporal model is applied to fill the remaining gaps. We tested this pipeline on a CPU server with 96 threads and 1 TB RAM. Each tile can be processed in under 2000 seconds. Parallelization across tiles and bands enables global processing in under six weeks, significantly reducing the computational time compared to full dataset reconstruction, which would take approximately six months. The resulting dataset provides clean, gap- and cloud-free monthly Landsat imagery suitable for a variety of research applications. Limitations remain, mostly related to input/output operations, and future work could apply embedding models to reduce dataset size and produce abstract representations for faster access.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 504, "code": "CEMWWL", "public_name": "Sajed", "biography": "Sajed Sarabandi is a software engineer and junior researcher specializing in remote sensing at the OpenGeoHub Foundation. He holds a Master\u2019s degree in Computer Science from Leiden University.", "answers": []}], "links": [], "attachments": [], "answers": []}]}}, {"index": 3, "date": "2026-10-09", "day_start": "2026-10-09T04:00:00+02:00", "day_end": "2026-10-10T03:59:00+02:00", "rooms": {"Aula Magna": [{"id": 539, "guid": "9cae62b1-8144-58e0-8a39-bcd1350015be", "logo": "", "date": "2026-10-09T10:30:00+02:00", "start": "10:30", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-539-keynote", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/BCLNKW/", "title": "Keynote", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Keynote talk by Coco Antonissen. Abstract and title to be provided.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 541, "code": "TSDDHM", "public_name": "Coco Antonissen", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 391, "guid": "8748a47e-c7f2-592e-a058-eaf481782524", "logo": "", "date": "2026-10-09T11:00:00+02:00", "start": "11:00", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-391-earth-embeddings-learning-mental-maps-for-open-interoperable-geoai", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/GCLJMU/", "title": "Earth Embeddings: Learning \u201cMental Maps\u201d for Open, Interoperable GeoAI", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Earth Observation is entering an era of abundance\u2014global satellite archives, growing in-situ networks, and an expanding open-source ecosystem\u2014yet turning this distributed wealth into decision-ready environmental information remains difficult because data are heterogeneous, incomplete, and hard to combine across sensors, resolutions, and regions. This keynote outlines Earth Embeddings: compact, AI-native \u201cmental maps\u201d that summarize what makes a location unique by learning directly from imagery and context. Using an intuitive \u201cSatellite GeoGuessr\u201d contrastive training setup, neural networks learn place-specific visual and contextual signatures and distill them into dense vectors that can serve as portable location tokens in downstream models, enabling reuse across tasks and regions. This talk will give an overview over different strategies to generate embeddings and outline research gaps and steps forward towards global interoperable FAIR embeddings.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 450, "code": "7MRGZM", "public_name": "Marc Ru\u00dfwurm", "biography": "Marc Ru\u00dfwurm is a Junior Research Group Leader of the MEO-lab at the University of Bonn. He was previously Assistant Professor of Machine Learning and Remote Sensing at Wageningen University. His background is in Geodesy and Geoinformation, and he obtained a Ph.D. in Remote Sensing Technology at TU Munich. During his Ph.D., he visited the European Space Agency and the University of Oxford as a participant in the Frontier Development Lab (2018), and conducted research stays at the Obelix Laboratory in Vannes and the Lobell Lab at Stanford. As a postdoctoral researcher, he joined the Environmental Computational Science and Earth Observation Laboratory at EPFL, Switzerland. His research focuses on modern machine learning for Earth observation, with an emphasis on geospatial representation learning and Earth Embeddings. He develops methods that enable robust, transferable analysis of geospatial data and applies them to challenges such as agriculture, species mapping, and marine litter monitoring, with a particular interest in domain shifts and transfer learning in geographic settings.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 514, "guid": "18a2ce29-60db-5bed-8701-a9c758764b62", "logo": "", "date": "2026-10-09T11:30:00+02:00", "start": "11:30", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-514-optimizing-representations-at-test-time", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/3MAMRS/", "title": "Optimizing Representations at Test Time", "subtitle": "", "track": "Forest and biodiversity", "type": "Keynote lecture", "language": "en", "abstract": "Deep learning represents a powerful tool to interpret Earth observation data at large geographic scales. However, in cases where abundant reference data is not available and cannot easily be collected, new approaches are needed to benefit from this technology. Several Earth observation tasks, especially in environmental remote sensing, remain challenging due to the limited number of samples and the geographic and temporal bias in the reference data. Furthermore, mapping biophysical variables from single sensor inputs often leads to high ambiguities. Multimodal models pretrained in a self-supervised fashion promise to overcome such challenges.\r\n\r\nIn this talk, I will first present our recent research project MMEarth-Bench, a multimodal benchmark dataset for environmental remote sensing. I will discuss our evaluation of existing pretrained models and present our test-time adaptation approach that adapts any model at test time using multimodal data to construct adaptation signals. Lastly, I will present SuperF, an approach for multi-image super-resolution. This test-time optimization approach based on implicit neural representations makes use of repeated observations with sub-pixel shifts and does not require any high-resolution training data. Under a static scene assumption, it can be applied to super-resolve e.g. Sentinel-2 time series for any place on Earth.\r\n\r\n- Personal website: https://langnico.github.io/\r\n- MMEarth-Bench project: https://mmearth-bench.com/\r\n- SuperF project: https://sjyhne.github.io/superf/", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 419, "code": "9PTJVH", "public_name": "Nico Lang", "biography": null, "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 431, "guid": "bfe7df4a-3016-59d2-8c1b-e9f82216e598", "logo": "/media/global-workshop-2026/submissions/TJHTLR/fair2_hNLoQs6.png", "date": "2026-10-09T12:00:00+02:00", "start": "12:00", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-431-to-be-fair-we-re-open-how-open-standards-can-power-earth-observation", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/TJHTLR/", "title": "To be FAIR, we're Open! How open Standards can power Earth Observation", "subtitle": "", "track": "Climate and Health", "type": "Keynote lecture", "language": "en", "abstract": "It is estimated that the deep web, the part of the web that is not indexed through search engines, accounts for more than 90% of all the web content. Although in some cases the content may be hidden intentionally, in many others there is just a failure in delivering it to the users; even after finding the information, there may still be some challenges in understanding what it covers and accessing it in a suitable format.\r\n\r\nThis talk will elaborate on how geospatial Standards can help us to address these challenges, and ensure that EO data can live up to the promise of being used and reused.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 461, "code": "ALTKUE", "public_name": "Joana Simoes", "biography": "Joana is a data engineer with a strong background in geospatial tech. Her pursuit to make geospatial information F.A.I.R. has led her to the board of GSDI and to OGC, where she leads relations with the developer community. Committed to advancing the open-source geospatial ecosystem, Joana is a OSGeo board member and project contributor.\r\nJoana is the founder of ByteRoad, a boutique company in the field of Spatial Data Infrastructures. She is also a reviewer for the European Commission, and has been involved in education, teaching the next generation of full-stack developers and data analysts.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 397, "guid": "65351445-2263-554a-9273-feff147f5ac4", "logo": "/media/global-workshop-2026/submissions/8S3XVA/session_image_LyWKgy3.png", "date": "2026-10-09T12:30:00+02:00", "start": "12:30", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-397-tessera-a-foundation-model-for-label-efficient-and-multi-modal-earth-observation-at-scale", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/8S3XVA/", "title": "TESSERA: A Foundation Model for Label-Efficient and Multi-Modal Earth Observation at Scale", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Satellite Earth Observation (EO) time series are fundamental to monitoring our planet's changing environment. However, inconsistent revisit times and frequent cloud obstruction in optical data (Sentinel-2) often force practitioners to rely on lossy data compositing, which discards critical phenological information.\r\nIn this keynote, we introduce TESSERA (Temporal Embeddings of Surface Spectra for Earth Representation and Analysis), a pixel-wise foundation model designed to overcome these challenges. TESSERA leverages multi-modal fusion of Sentinel-1 (radar) and Sentinel-2 (optical) data, employing a self-supervised learning framework based on Barlow Twins and random temporal sampling. This approach ensures high robustness to irregular sampling and missing data without requiring expensive ground-truth labels.\r\nA key highlight of TESSERA is its scale and commitment to Open Science: trained on a global dataset spanning 2017\u20132025, the model provides high-dimensional temporal embeddings that capture the \"spectral fingerprint\" of the Earth's surface. In alignment with the FAIR principles, we are committed to making TESSERA an open-access resource for the community. We will demonstrate how TESSERA achieves state-of-the-art performance in downstream tasks such as crop type mapping and land cover classification with minimal labeled data, paving the way for the next generation of open-source, distributed GeoAI monitoring systems.", "description": "In this keynote, we will dive deeper into the practical implications of the TESSERA foundation model for the Earth Observation and GeoAI communities. Beyond the architectural innovations presented at CVPR 2026, this session will focus on three key pillars:\r\n\r\n1. Breaking the \"Label Bottleneck\": We will discuss how TESSERA\u2019s self-supervised temporal embeddings allow researchers and organizations to build high-performing monitoring tools with 10x to 100x less labeled data than traditional supervised methods.\r\n2. A New Paradigm for Multi-Modal Integration: We will showcase how TESSERA natively fuses Sentinel-1 SAR and Sentinel-2 optical data at the pixel level, providing a robust solution for regions with persistent cloud cover.\r\n3. Commitment to Open & Distributed Science: In line with the Open-Earth-Monitor mission, we will outline our roadmap for releasing next-gen pre-trained weights and the global embedding dataset (2017\u20132025).", "recording_license": "", "do_not_record": false, "persons": [{"id": 456, "code": "PNXLNE", "public_name": "Zhengpeng (Frank) Feng", "biography": "Zhengpeng (Frank) Feng is a second-year Ph.D. candidate in the Energy and Environment Group, Department of Computer Science and Technology, at the University of Cambridge. His research interests lie at the intersection of machine learning and earth sciences, with a particular focus on developing self-supervised learning methods in remote sensing.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 394, "guid": "9bc357bb-027d-555c-999d-d6dc100011ff", "logo": "", "date": "2026-10-09T13:30:00+02:00", "start": "13:30", "duration": "00:30", "room": "Aula Magna", "slug": "global-workshop-2026-394-pangeo-openness-for-sovereignty-innovation-and-sustainable-communities", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/7LHAUP/", "title": "Pangeo: Openness for Sovereignty, Innovation, and Sustainable Communities", "subtitle": "", "track": null, "type": "Keynote lecture", "language": "en", "abstract": "Earth observation is generating data at unprecedented scales, and new analytical methods offer powerful ways to extract insights from it. But realising this potential depends on the infrastructure beneath: how data is stored, accessed, and processed\u2014and crucially, who builds and maintains that infrastructure. Openness is not just a technical preference. It is a practical strategy for sovereignty, a driver of innovation, and the foundation for communities that can sustain this work over the long term.\r\nOpenness for sovereignty: In the current political and economic climate, dependence on infrastructure that can become inaccessible, unaffordable, or restricted is a real risk. Proprietary platforms can change pricing, alter terms, or disappear entirely. The environmental research community works on challenges spanning decades\u2014climate change, biodiversity loss, ecosystem degradation. The tools we build today must remain available and adaptable regardless of corporate decisions, funding changes, or geopolitical shifts. Open-source software and open standards provide this guarantee: there is no licence to be revoked, no single point of failure, no dependency on decisions made elsewhere.\r\nOpenness for innovation: When tools are open, anyone can extend them. New capabilities emerge because the need exists and the ecosystem allows it\u2014no permission required, no vendor roadmap to wait for. xDGGS, which brings Discrete Global Grid Systems to the Python ecosystem, was built by contributors who saw a gap and filled it. Open standards like Zarr mean new tools can interoperate immediately, compounding each other's value. This is how innovation actually happens: not through proprietary development cycles, but through communities identifying problems and sharing solutions. The pace of improvement accelerates because every contribution benefits everyone.\r\nOpenness for sustainable communities: Software without a community is software with an expiration date. Open source survives because people can join, contribute, and take ownership. There are no gatekeepers deciding who gets to participate. When someone learns from the codebase, improves it, and teaches others, the community grows stronger. Initiatives like the Environmental Data Science Book, the Pangeo community meetings, and training programmes across Europe are not just about spreading knowledge\u2014they are about ensuring that the next generation of researchers and developers can maintain and extend these tools. Shared ownership means shared responsibility, and that is what makes infrastructure last.\r\nThe Pangeo ecosystem: Pangeo embodies these principles. It provides the toolkit for scalable Earth science\u2014Xarray for labelled arrays, Dask for distributed computing, Zarr for cloud-native storage, xDGGS for grid systems\u2014built by a global community and available to all. Pangeo@EOSC, deployed on European infrastructure through collaboration between EGI and research institutions, demonstrates that this model works: open tools, running on open infrastructure, maintained by a community with shared stakes in its success.\r\nMaking data analysis-ready: Underlying this is the practical challenge of data. Most Earth observation data was not designed for modern workflows\u2014it comes in heterogeneous formats, different projections, inconsistent resolutions. Discrete Global Grid Systems and cloud-optimised formats like Zarr address this by creating common frameworks where data is ready for use the moment it is published. These are open standards that anyone can implement and build upon.\r\nWhat this talk will cover: Concrete examples of what Pangeo makes possible today, who is building these tools, and how openness enables sovereignty, accelerates innovation, and grows communities that last. The message is simple: open infrastructure is working, it is being built by people who believe in it, and there is room for more to join.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 453, "code": "CMDENR", "public_name": "Anne Fouilloux", "biography": "Anne Fouilloux\u00a0is Chief Technology Officer at LifeWatch ERIC. She has over 20 years of experience in high-performance computing and Earth system science, with her career spanning data-intensive computing and optimisation at CNRS-IDRIS (France), software development at the European Centre for Medium-Range Weather Forecasts (ECMWF, UK), research software engineering at the University of Oslo (Norway), and project leadership at the Nordic e-Infrastructure Collaboration (NeIC). Anne is an active contributor to the Pangeo community and has been championing open-source tools for big data geoscience, particularly efforts to grow and sustain this ecosystem in Europe. She focuses on building scalable, open, and sustainable digital infrastructures, and advocates for approaches such as Discrete Global Grid Systems and cloud-optimised formats like Zarr that remove technical barriers and enable meaningful reuse of environmental data. Her work is driven by the conviction that research infrastructures must serve society and remain accessible to all.", "answers": []}], "links": [], "attachments": [], "answers": []}], "Rooms 12+14": [{"id": 496, "guid": "a0d92263-c0f2-512f-9764-b08bd73f68a7", "logo": "/media/global-workshop-2026/submissions/JSFE9H/logo_6Vh6rrP.png", "date": "2026-10-09T14:00:00+02:00", "start": "14:00", "duration": "00:15", "room": "Rooms 12+14", "slug": "global-workshop-2026-496-deadtrees-earth-crowdsourced-drone-data-for-global-tree-mortality-maps", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/JSFE9H/", "title": "deadtrees.earth - Crowdsourced Drone Data for Global Tree Mortality Maps", "subtitle": "", "track": "Forest and biodiversity", "type": "Oral talk", "language": "", "abstract": "Elevated forest disturbances and excess tree mortality are increasingly reported worldwide. Yet existing assessments are either based on patchy terrestrial observations or on large-scale satellite products, which are limited in resolution to pixel-level, binary tree loss detection. This leaves a blind spot on fine-scale disturbances where only a few trees are declining in an otherwise intact canopy.\r\n\r\nIn this talk, we give an overview of the deadtrees.earth initiative and how we leveraged crowdsourced drone data to build globally generalizing models for mapping tree mortality and disturbances from drones, airplanes, and Sentinel-2. This talk will further go into details of our upscaling approach where centimeter-scale drone data is leveraged to calibrate a model that processes multi-year Sentinel-2 time series around the globe.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 510, "code": "N93DD3", "public_name": "Clemens Mosig", "biography": "Clemens Mosig is a researcher at Leipzig University working at the intersection of remote sensing, computer vision, and vegetation mapping. He has co-created the deadtrees.earth initiative. Clemens is a strong advocate of open data, science, and idea sharing. He holds a Bachelor and Master's degree in Computer Science from Freie University Berlin.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 444, "guid": "cc443e8e-09ee-5a5b-a9e2-e5a471402fd4", "logo": "", "date": "2026-10-09T14:15:00+02:00", "start": "14:15", "duration": "00:15", "room": "Rooms 12+14", "slug": "global-workshop-2026-444-satellite-gravity-observations-for-scalable-global-precipitation-monitoring", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/P3DBXT/", "title": "Satellite Gravity Observations for Scalable Global Precipitation Monitoring", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "Satellite observations from the GRACE mission and its successor GRACE-FO have significantly advanced our ability to monitor terrestrial water storage (TWS) at regional to global scales. However, their limited spatial and temporal resolution hampers the reliable separation of individual hydrological fluxes, particularly precipitation. However, their coarse spatial and temporal resolution makes the individual separation of different hydrological fluxes from TWS a challenging problem. These limitations in current gravity mission concepts can be addressed by a joint collaboration between NASA and ESA initiated the Mass-change And Geosciences International Constellation (MAGIC), which can provide enhanced spatio-temporal observations of mass change and therefore enable improved monitoring of hydrological extremes and dynamics. The primary objective of this work to access how improving the spatial and temporal resolution of future gravity missions impacts precipitation estimation by developing a number of global synthetic experiments. The precipitation data used as forcing of ESM will be compared with the \u201ctrue\u201d precipitation for testing the reliability of the SM2RAIN approach (Brocca et al., 2014) using as input EWH data (in the past it was implemented by using surface soil moisture data). Simulated precipitation estimates derived from different gravity mission configurations (GRACE-C, NGGM, and MAGIC) were evaluated against reference precipitation to quantify performance improvements. The global correlation analysis shows median and mean correlation coefficients of 0.67 and 0.63, respectively, indicating satisfactory performance of the EWH based SM2RAIN framework across most terrestrial regions. Stronger correlations are observed over Northern Hemisphere mid-latitudes, including Europe, northern Asia, and North America, reflecting robust performance in temperate climates, while reduced performance is evident in several tropical regions such as central Africa, parts of the Amazon Basin, and Southeast Asia. Subsequently, synthetic experiments were developed using filter and unfiltered configurations of GRACE-C, NGGM, and MAGIC missions. The performance of NGGM and MAGIC filtered configurations indicates their capability to capture precipitation dynamics effectively as compared to unfiltered ones. The results of the study clearly highlight the  added value of next generation gravity missions for global hydrological monitoring and develops new scalable EO based precipitation estimation systems that support emerging open and distributed EO infrastructures. The proposed framework enables improved assessment of water cycle dynamics as well as enhanced monitoring of hydrological extremes such as droughts and floods.\r\n\r\nReferences\r\n\r\nBrocca, L., Ciabatta, L., Massari, C., Moramarco, T., Hahn, S., Hasenauer, S., Kidd, R., Dorigo, W., Wagner, W., & Levizzani, V. (2014). Soil as a natural rain gauge: Estimating global rainfall from satellite soil moisture data. Journal of Geophysical Research: Atmospheres, 119(9), 5128\u20135141.", "description": "", "recording_license": "", "do_not_record": false, "persons": [{"id": 415, "code": "MJEFVN", "public_name": "Muhammad Usman Liaqat", "biography": "As an engineer, modeler, and data analyst, I have 8+ years of experience in geoinformatics and Earth observation applications for environmental systems. My research focuses on integrating GIS, remote sensing, and data driven modelling approaches to understand hydrological processes, climate variability, and water resource dynamics. Experienced in ArcGIS, QGIS, Python, and R for spatial analysis, geostatistics, and environmental modelling. \r\nResearch Interests:\r\nHydrologic modelling | Geoinformatics & GIS | Climate Dynamics | Earth Observation Hydrology | Flood and Drought Risk Assessment | Machine Learning |", "answers": []}], "links": [], "attachments": [], "answers": []}], "Room 18": [{"id": 453, "guid": "b8bf1510-f48a-55f7-9db8-6746cbdfbb19", "logo": "", "date": "2026-10-09T14:00:00+02:00", "start": "14:00", "duration": "00:15", "room": "Room 18", "slug": "global-workshop-2026-453-large-scale-snow-monitoring-multi-mission-data-integration-and-scalable-processing-strategies", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/LEYYXN/", "title": "Large-scale snow monitoring: multi-mission data integration and scalable processing strategies", "subtitle": "", "track": "Soil, water and agriculture", "type": "Oral talk", "language": "en", "abstract": "Accurate snow monitoring requires high spatial and temporal resolution to capture rapid processes such as melt and accumulation. However, current satellite missions present inherent trade-offs: optical sensors such as Sentinel-2 provide high spatial resolution (tens of meters) but limited revisit times, while sensors like MODIS offer daily observations at coarser spatial resolution (\u223c500 m). In addition, different sensors retrieve complementary snow properties, including snow cover extent from optical data and wet/dry snow conditions from SAR observations. \r\n\r\nTo overcome these limitations, multi-mission data integration is essential. Furthermore, robust estimation of Snow Water Equivalent (SWE) requires the coupling of remote sensing observations with physically-based or conceptual snow models driven by meteorological forcing. The increasing volume and complexity of such datasets demand scalable, cloud-based processing solutions, particularly for large-scale applications. \r\n\r\nIn this contribution, we present a scalable workflow for large-scale snow water equivalent (SWE) estimation, aimed at generating daily high-resolution (50 m) SWE data across extensive regions, such as for example the extratropical Andes within the SNOWCOP project and South Tyrol within the Open-Earth-Monitor project. The workflow explores alternative cloud-based processing strategies, including (i) data access through Copernicus Data Space Ecosystem or other STAC APIs combined with containerized processing environments (Docker), enabling flexible and reproducible workflows without systematic local data download, and (ii) data-proximate processing using openEO. These complementary approaches allow us to evaluate trade-offs between flexibility, scalability, and computational efficiency for multi-source data fusion and large-scale snow monitoring applications.", "description": "Contributors: Valentina Premier, Hans Vanrompay, Jeroen Dries, Michele Claus, Alexander Jacob, Carlo Marin", "recording_license": "", "do_not_record": false, "persons": [{"id": 202, "code": "H8YUKK", "public_name": "Valentina Premier", "biography": "Valentina Premier received in 2022 her Ph.D. degree in Information Engineering and Computer Science at the University of Trento, Trento, Italy, within the Remote Sensing Laboratory and with Eurac Research, Bolzano, Italy, within the Institute for Earth Observation. Previously, she held a Master's in Environmental Engineering in 2016. Her activities focus on snow cover and snow water equivalent retrieval using remote sensing data. She is currently involved in different projects of the group for Mountain Cryosphere, such as SNOWCOP, Snowtinel and Open Earth Monitor.", "answers": []}], "links": [], "attachments": [], "answers": []}, {"id": 475, "guid": "13f155e8-5a82-53d5-92ad-238b3154404f", "logo": "", "date": "2026-10-09T14:15:00+02:00", "start": "14:15", "duration": "00:15", "room": "Room 18", "slug": "global-workshop-2026-475-from-earth-observation-to-ecosystem-service-indicators-integrating-biodiversity-spatial-modelling-and-nature-based-solutions-across-scales", "url": "https://pretalx.earthmonitor.org/global-workshop-2026/talk/GUPY7L/", "title": "From Earth Observation to Ecosystem Service Indicators: Integrating Biodiversity, Spatial Modelling and Nature-Based Solutions Across Scales", "subtitle": "", "track": "Forest and biodiversity", "type": "Oral talk", "language": "en", "abstract": "Earth Observation (EO), GIS and open geospatial workflows are transforming how biodiversity and ecosystem services can be assessed and applied to environmental decision-making. In this talk, I present an integrative research framework that combines EO-based mapping, biodiversity indicators, spatial modelling and nature-based solutions to generate ecosystem service indicators across multiple socioecological contexts. The presentation draws on concrete examples from projects in Europe, Africa and Latin America. These include MaSOT, which advances the mapping of ecosystem services from Earth Observations; ASEBIO, a national-scale assessment of biodiversity and ecosystem services in Portugal that combines stakeholder engagement, scenario analysis and WebGIS tools; MozambES, which uses GIS and remote sensing to map mangroves, assess pressures and support the valuation of mangrove ecosystem services in Mozambique; and FOREST-LED, which examines forest loss, forest expansion and carbon stocks in Spain under global change and natural hazards. Across these projects, I show how taxonomic, functional and phylogenetic dimensions of biodiversity can be combined with land-cover dynamics, ecosystem service indicators and economic valuation to support conservation prioritization and multifunctional landscape management. I also highlight recent studies on biodiversity indicators of ecosystem services, ecosystem service change under land-use dynamics, comparisons between model outputs and stakeholder perceptions, and the integration of eco-environmental factors into landslide susceptibility assessment through an eco-DRR perspective. Together, these examples show how open and reproducible EO workflows can connect environmental data, biodiversity science and applied modelling to produce scalable indicators for conservation, risk reduction and sustainability planning.", "description": "An integrative framework for ecosystem service indicators across scales, linking\r\nbiodiversity, spatial modelling and nature-based solutions.", "recording_license": "", "do_not_record": false, "persons": [{"id": 500, "code": "ZMRJX3", "public_name": "Felipe S. Campos", "biography": "Felipe S. Campos is a postdoctoral researcher at CREAF working at the interface of biodiversity, ecosystem services and ecological economics. His research uses GIS and remote sensing to investigate spatial patterns of biodiversity and ecosystem services, with a particular focus on indicators, monitoring and the ecological foundations of nature-based solutions. He develops spatial approaches that help link ecological knowledge with conservation research and practice.", "answers": []}], "links": [], "attachments": [], "answers": []}]}}]}}}