Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.

Machine learning is promoted as a game-changer for soil health assessment, offering new ways to model complex relationships and generate high-resolution soil property maps. However, while ML has shown promise, its application in soil science is often met with overstated expectations and underappreciated limitations. This keynote critically examines the role of ML in space-time soil mapping for soil health, highlighting both its strengths and pitfalls.

ML has certainly advanced soil mapping in an unprecedented way to achieve continental and even global maps at high resolution for numerous soil properties. Entangled soil processes and the variability of locations, all nearly having an individual set of soil-forming factors, result in complex space-time soil patterns. In the commonly used mapping approach, ML has to learn all this complexity fully data-driven from the surveyed soil samples and the environmental predictors such as remote sensing data or elevation models. For cases where no environmental predictor dataset can differentiate the observed soil property patterns, ML predictions will play save and predict the average observed value for similar locations. From a soil process knowledge perspective, the mean might often not be the best prediction. For example, a forest topsoil may be buffered by carbonates and have a pH around 8 or its pH might already have dropped to reach the aluminum buffer range of around 4. A mean pH of 5-6 likely to be predicted by ML is not often observed within unfertilized forests and, hence, is rather unlikely.

Similar limitations also appear while quantifying prediction uncertainty at each location. ML-based prediction intervals often contain value ranges that, from a soil process viewpoint, we already know are very unlikely. While certainly more field surveying is due to support unbiased mapping, it does not resolve the challenge. The marginal benefit of more data points for fully-data driven ML often decreases rapidly, more so in the presence of measurement errors. Soil sampling will always only provide a tiny fraction of the total 3D soil continuum we are interested in. Data-hungry ML techniques such as deep learning are therefore unlikely to excel in space-time soilmapping of soil health indicators.

Soil health indicators cover the biological, chemical and physical domains of soils. In this respect, just selecting agreed indicators of soil health, and measuring them, is difficult. Soil organic matter (which is about 58% carbon) is a headline indicator of soil health, but establishing a monitoring, verification and reporting (MRV) framework for just this one indicator is a challenge. I will present experiences of developing MRV frameworks for changes on soil carbon, and reflect upon how these could be built upon to untimately develop an MRV framework for for soil health, reflecting on the technological and scientific challenges in doing so.

I will briefly review methods and challenges of measuring SOC change directly in soils, before examining some recent novel developments that show promise for quantifying SOC. I will describe how repeat soil surveys are used to estimate changes in SOC over time, and how long-term experiments and space-for-time-substitution sites can serve as sources of knowledge and can be used to test models, and as potential benchmark sites in global frameworks to estimate SOC change. I briefly consider models that can be used to simulate and project change in SOC and examine the MRV platforms for soil organic carbon change already in use in various countries / regions. In the part of the talk, I will bring together the various components described in this review, to describe a new vision for a global framework for MRV of soil organic carbon change, and discuss how this related to soil health, to support national and international initiatives seeking to effect change in the way we manage our soils.

Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.

The Waste4Soil project is focused on developing sustainable, cost-effective fertilizing products from recycled biowastes sourced from local food industries. By recycling food processing residues (FPR) into soil improvers (SI), Waste4Soil aims to reduce environmental impacts while enhancing food security across Europe. The project’s main objective is to create viable pathways for recycling biowastes within a circular, regional, and systemic framework that involves all actors in the food chain, thus closing essential nutrient, organic matter, and water loops.
The Waste4Soil approach is implemented through Living Labs (LL) established in seven EU countries: Hungary, Finland, Spain, Greece, Italy, Poland, and Slovenia. These LLs facilitate experimentation in real-life settings, engaging key stakeholders—such as food industry representatives, waste managers, fertilizer manufacturers, commercial farms, and citizens—in collaborative activities that emphasize “show me” and “ready for practice” demonstrations of best practices. Through this co-creative approach, LLs aim to provide practical examples of sustainable waste-to-fertilizer applications that are regionally adaptable and environmentally beneficial.
Central to achieving Waste4Soil’s goals is the active involvement of diverse stakeholders at every stage of the project. From co-creating solutions to participating in planning, demonstrations, dissemination, and further demonstration phases, each actor plays a critical role. The project promotes ecosystem-based collaboration among farmers and their networks, food industries, waste management companies, fertilizer producers, research and educational institutions, local and regional authorities, and civil society. By fostering these collaborations, Waste4Soil aims to develop ecosystem solutions that improve FPR management practices, making soil improvers economically viable, environmentally sustainable, and socially acceptable, thereby advancing the circular economy in agriculture.

Soil health is foundational to sustainable agriculture, water resource management, and climate mitigation. However, the effectiveness of global soil health efforts is constrained by fragmented, inconsistent, and often inaccessible soil datasets. To address this, Varda has developed SoilHive, an interactive platform that aggregates and harmonizes soil data from various global sources, promoting open access and collaboration.

SoilHive is a central open repository, integrating and harmonizing diverse datasets to provide a comprehensive overview of soil data in any region. This benefits researchers, the private sector, multilateral organizations, and policymakers. The platform’s Data Availability Framework assesses the spatial distribution of soil data, aggregates it at multiple resolutions, identifies underserved areas, and guides targeted efforts to address data gaps. This approach encourages users to contribute data, fostering a culture of sharing and collaboration.

To further expand soil data access and facilitate soil data exchange, SoilHive has been developing ad hoc tools for data management and dissemination within research and collaborative projects. A private data hub enables stakeholders to securely share and access proprietary data, addressing privacy and intellectual property concerns while promoting interoperability and reusability. Each hubs allow organizations to share soil data for specific project durations while ensuring the discoverability of their metadata as well as access to to SoilHive’s broader dataset. Upon project completion, data can be released to the public domain via SoilHive.

In alignment with its broader mission, SoilHive also contributes directly to the EU-funded DeepHorizon project by enhancing data management and promoting data sharing and discoverability. This initiative involves extending existing ontologies to incorporate subsoil domains and functions, facilitating data sharing among diverse stakeholders, and creating the first European-level subsoil dataset. Furthermore, SoilHive enhances its capabilities to improve the discovery of subsoil data, including the ability to search at the horizon level.

In conclusion, SoilHive democratizes access to existing soil data while respecting data provenance and owner rights, fostering international collaboration and innovation. By engaging with both public and private entities, SoilHive enhances the breadth of available soil data, supporting global innovation and increasing our shared understanding of the soil system.

About 60% of European soils are currently polluted, contaminated, or in many ways compromised by centuries of urbanisation, industrial and rural development, and careless waste management. The EU Mission Soil, the EU Soil Observatory, the Soil Strategy and the Soil Monitoring Law represent a soild european basis to counteract such a negative evidence and trend. However, the issue of soil health - on top of its global relevance and urgency - also embeds a deep local meaning, in that it interferes in many respects with land destination and use regulations, practices and interests – therefore with spatial planning and governance decisions that are peculiar to local and regional policy and administrations. In this context is necessary the establishment of constructive dialogues among public authority representatives, academia, citizens, businesses, associations and other Quadruple Helix stakeholders to help policy makers to understand the problems of their soils and find viable solutions together. During the SOIL HEALTH NOW! workshop the participants will simulate the undertaking of all necessary steps to reintroduce soil related issues into the political agendas as priorities in a respectful, constructive and transformative manner. The workshop will present the instruments and use the tools developed by the HuMUS project and others Mission Soil projects and beyond, to facilitate the dialogue and the decision making processes on soil health.

David A. Robinson (1), Grant Campbell (2), Pete Smith (2).
(1) UK Centre for Ecology & Hydrology, (2) University of Aberdeen

Soil provides environmental, social and economic functions (Blum, 2005). Recognizing the importance of soil functions, different frameworks have been proposed to convey the importance of soils to society. Such frameworks usually have a construct based on values, where the definition of value is “a framework for identifying positive (better) or negative (worse) qualities in events, objects, or situations” (Edwards-Jones et al., 2000). Quality is something often sought after but difficult to define. Ultimately, quality matters because decision making, and subsequent actions taken, are often contingent on the interpretation of quality framings. Quality means different things in different contexts and can thus lead to frequent misunderstandings. Quality can refer to excellence (the degree of distinction or superiority), a standard (how good or bad something is), or a characteristic (a feature of something) (Cambridge Dictionary Online). Moreover, quality can be classified into five categories according to its usage, 1) exception, 2) perfection, 3) fit for purpose, 4) value for money and 5) transformative. In this presentation these framings are examined in the context of soil health and the Mission soil. Different framings are suitable for different scales and purposes, but also determine to some extent how indicators are selected, thresholds determined, and results interpreted.

Edwards-Jones, G., B. Davies, and S. Hussain. 2000. Ecological economics: An introduction. Blackwell Science, Oxford, UK

Sustainable soil management has been proposed as an effective nature-based solution to enhance the delivery of nature’s contributions to people (NCP). Sustainable soil management principles are at the core of organic farming. The European Commission has set a target of at least 25% of the EU’s agricultural land to be under an organic farming system by 2030 under the European Green Deal. To reach this target, farmers and policy makers need to be able to make informed decisions on what sustainable soil management practices to implement.

We present a framework to understand how soil management practices and key external drivers, like climate change and soil degradation, influence the delivery of NCPs. We developed a set of conceptual evidence chains that link management practices, key drivers, soil biodiversity, ecosystem properties, functions, and goods. For each of these linkages we performed a literature search to determine the direction of effect and the strength of evidence. This set of evidence chains provided the basis for informed data-driven analyses of these linkages between individual components in the system to quantify the effects. This operationalization was constrained by the availability of observational data to train the models that make up the linkages, as well as spatial data to predict at a European scale.

Here, we illustrate this framework with a case study, where we predict the effect of converting farm management from a conventional to an organic system on the delivery of NCPs including climate regulation, water quantity and flow regulation, and food production, and their economic valuation, across Europe. These models also enable exploration of different climate and policy scenarios. Furthermore, as the models are based on the conceptual evidence chains that include strength of evidence, each model output is associated with a level of confidence, related to the scientific consensus and the availability and quality of data, that can be reported along with the results. This modelling framework and its model predictions can support farmers and policy makers in understanding trade-offs and synergies that are associated with soil management practices to make informed decisions.

Developing Robust MRV Systems for Carbon Farming: Insights from the MARVIC and Credible Projects

Xu Hui1*, Ruysschaert Greet1, D’Hose Tommy1

1 Flanders Research Institute for Agriculture, Fisheries and Food (ILVO), Merelbeke-Melle, Belgium

*corresponding author

Soil Organic Carbon is a fundamental component of healthy soils and plays a crucial role in many ecological processes. With the increasing interest in carbon farming—which involves capturing and storing carbon in soils and woody plants—it's essential to develop robust systems for monitoring, reporting, and verification (MRV) and credible business models. Our study addresses this need by designing and testing a reliable MRV framework through the MARVIC project and by building a European network for carbon farming to collaboratively address current challenges through the CREDIBLE project.

Funded under the Soil Mission to support the Carbon Removal and Carbon Farming (CRCF) Regulation, MARVIC aims to create a framework for designing harmonized yet context-specific MRV systems applicable to diverse land uses such as arable land, grasslands, agroforestry/woody crops, and managed peatlands. This project explores the integration of various components like benchmark sites, sampling schemes, data layers, farm data, remote sensing, and modeling to establish comprehensive monitoring systems and operational processing chains. Additionally, the MARVIC team is actively engaged in the CRCF expert group and further contributes to discussions to achieve a good balance between minimizing risks of unjust payments, maximizing progress in the LULUCF sector, and minimizing costs.

At the 2nd Carbon Farming Summit organized by the CREDIBLE project, we will co-organize several sessions aimed at fostering collaboration between the public and private sectors on technical aspects like baseline approaches, data sharing and harmonizing. We will also engage with stakeholders—including farmers and companies—to build acceptance of the CRCF regulation, thereby promoting transparency and actionable steps.

In the conference, we will share our reflections on the Carbon Farming Summit. We will highlight key insights from our collaborative sessions on baselines, data sharing, harmonization, and strategies for farmer acceptance of the CRCF regulation.

Most soil properties are continuously varying over different scales in both space and time. An analysis of field sampled soil is the most accurate method for estimating the spatial distribution of soil properties and health indicators at field scale. The field scale spatiotemporal variation in properties, however, requires an effective, well selected and unbiased probability distribution based sampling framework leveraging the in-situ variability of the relevant environmental covariates. Covariates that can be used for modeling the soil properties over the entire study area. Typically such covariates are represented at spatial rasters derived from e.g. topographic data and satellite imagery. In this work, we introduce the probability based balanced stratified sampling algorithm compatible with the proposed European Soil Monitoring law. The algorithm distributes doubly balanced sampling locations over both geographical and feature space constrained by a maximum allowed error – in our case the coefficients of variation. The geographical feature space input data are selected covariates from the Soil Health Data Cube (https://shdc.ai4soilhealth.eu/). We target the covariates that reflect the distribution of soil health indicators tested or developed by the EU funded project AI4SoilHealth (https://ai4soilhealth.eu). To begin this process, a Bethel-inspired optimization approach is applied to stratify the study areas. The strata are then used for computing the approximately equal inclusion probabilities for all units and the number of samples for each strata allocated based on the available auxiliary information. The second stage of the process involves doubly balancing the algorithm, with the aim to select the optimal sampling locations over geographical and feature space with respect to the stratification. In our study, we compare the algorithm with 1) simple random sampling, 2) feature space coverage sampling and, 3) the EU wide Land Use and Cover Area frame Survey (LUCAS) algorithm using legacy data. The advantages of the novel algorithm are demonstrated in the optimized number of samples while preserving the accuracy of target estimates and mapping accuracy. In the first experiment, we subsample the legacy random grid samplings. In the second (numerical) experiment, we use the soil property maps of the Soil Health Data Cube as observed values to design new optimized sampling networks with no gridded location constraints.

There is a strong need to investigate soil health due to its big role in environmental and human health. In terms of this issue, there could be some elements to be explored. Heavy metals are important among these elements since their increase from specific thresholds would lead to soil pollution and ultimately impact human health. One of the heavy metals with a high influence on soil health is nickel (Ni). It is becoming more important in urban areas because of the high potential for growth through heavy transportation. In this study, 89 surface soil samples (0-20 cm) were collected from traffic areas nearby streets in Berlin, Germany in 2018. Then they were sieved and dried in the laboratory. Next, the amount of Ni and spectra in VNIR-SWIR bands were measured in the laboratory for each sample with an ASD FieldSpec5 spectroradiometer under controlled illumination conditions. The spectral reflectance data were transformed to absorbance values as a preprocessing method. In the next step, the data were split into two groups: training (80%) and test (20%) data. The first group was fed into random forest algorithm to develop a model for predicting Ni. Then the test set was utilized to validate the predicting ability of the model. Regarding the hyperparameter tuning of the model, GridSearchCV method was applied to find the best values for n_estimators, and max_depth. What is not considered in most of the similar studies is interpretability of a machine learning model produced leaving that in a black-box situation. Hence, in this study two explainable machine learning (eXML) methods, including MDI (Mean Decrease in Impurity), and permutation were applied to determine VNIR-SWIR bands with higher importance in the modeling and predicting of Ni. When it comes to the results, the validation of the random forest model yielded an R2 of 0.74 and an RMSE of 2.01. This proves that the models’ predictions align well with the actual Ni values. Furthermore, the results achieved from MDI method specified the wavelengths 2418nm, 2127nm, and 2147nm (short wave infrared) as three most important features in the random forest model generated for Ni. On the other hand, the features 2127nm, 401nm, and 2147nm were determined the most important features by permutation method for the model trained. This information could be very useful in using remote sensing sensors in Ni prediction in large scales specifically in an urban area.

This work presents a comprehensive framework for soil organic carbon density (SOCD) (kg/m3) modeling and mapping, based on spatiotemporal Random Forest (RF) and Quantile Regression Forests (QRF). 22,428 SOCD measurements and a wide range of covariate layers—particularly the 30m Landsat-based spectral indices were used to fit models and produce 30m SOCD maps for the entire EU at four-year intervals from 2000 to 2022 and for four soil depth intervals (0--20cm, 20--50cm, 50--100cm, and 100--200cm) each accompanied by per-pixel 95% probability prediction intervals (PI, between P0.025 and P0.975). The results of model evaluation indicate consistent accuracy of the predictions: based on both 5--fold spatial cross-validation with model refitting (MAE = 8.64 kg/m3, MedAE = 4.31 kg/m3, MAPE = 0.54 kg/m3 and bias = -2.95 kg/m3), and on independent testing (MAE = 7.73 kg/m3, MedAE = 3.54 kg/m3, MAPE = 0.45 kg/m3, and bias = -3.04 kg/m3), with both R2 values exceeding 0.7 and concordance correlation coefficients (CCC) greater than 0.8. Validation of PI estimation confirmed that PIs effectively capture uncertainty intervals, although with reduced accuracy for higher SOCD values. Exploratory analysis using Shapley values identified soil depth as the most important feature, with vegetation (Landsat biophysical indices) and long-term bio-climate features as the two main contributing feature groups. Although the uncertainty of the prediction per pixel is significant, further spatial aggregation has been shown to reduce the uncertainty by about 70%. Suggested uses of the data include: (1) time-series / trend analysis to detect potential land degradation hotspots, (2) optimization of sampling designs based on prediction uncertainty, and (3) prediction of future soil carbon potential by extrapolating models under different land use / climate scenarios. The data and code used are publicly available under an open license from https://doi.org/10.5281/zenodo.13754344 and https://github.com/AI4SoilHealth/SoilHealthDataCube/.

This study aims to identify critical soil health challenges in Southwest Europe, focusing on the Granada region, using an innovative quadruple helix approach that unites insights from scientists, local stakeholders, industry, and government entities. Given the widespread issues affecting soils in this area—including structural degradation, biodiversity loss, and reduced agricultural productivity—our project seeks a comprehensive understanding of these localized challenges to inform sustainable solutions. The first step of this work will conduct surveys with key stakeholders who rely on soil for their activities, including farmers and cooperatives in the Granada region. These surveys will aim to identify and understand the specific soil health challenges they face, such as soil degradation and nutrient loss. Additionally, we will gather information to understand basic aspects that will inform the design and implementation of effective strategies to improve soil health. By collecting this data, we aim to develop sustainable solutions tailored to local needs and enhance collaboration among the various actors involved in soil management.Findings from this study will directly contribute to the goals of SOILCRATES by supporting the development of science-backed, sustainable management strategies that address the specific needs of this region. Our approach will empower stakeholders in Granada with actionable, innovative solutions to mitigate soil degradation and protect the agricultural resources aligns with the EU Mission ‘A Soil Deal for Europe’.

The soil water retention curve (SWRC) represents the relationship between soil water content and matric potential, explaining how soil retains and releases water under various moisture conditions. Information on matric potential is vital for assessing soil's ability to store water for plant growth, and for quantification of its mechanical stability to prevent compaction damage. However, when direct measurements of matric potential are unavailable, and only soil water content data is accessible (e.g., from satellite observations), estimating matric potential becomes particularly challenging and relies on knowledge of SWRC. This complexity is further compounded by the highly variable, site-specific nature of the relationship between soil water content and matric potential, influenced by factors such as soil structure, seasonal fluctuations, and environmental stressors like drought. As a result, conventional methods based on an unambiguous pressure-saturation relationship often fail in capturing the dynamic behavior of soil moisture over time.
In this study, we address these challenges by employing a combined approach involving Seasonal-Trend decomposition using Locally estimated smoothing (STL) and an autoencoder neural network to monitor and predict changes in SWRC. STL is utilized to isolate seasonal patterns and long-term trends in water content data, capturing how environmental factors, especially prolonged drought, impact SWRC across multiple sites in Germany. The autoencoder neural network then compresses this information into a site- and period-specific feature called the "AUV" (Autoencoder Value), which represents the soil's water-holding properties and its response to changing environmental conditions. This AUV value is subsequently used to predict shifts in SWRC by modeling changes in matric potential resulting from significant alterations in the seasonal amplitude of water content or shifts in long-term trends following dry events.
Our approach was tested across several sites, where, in some locations, prolonged drought caused a noticeable reduction in seasonal amplitude and a decrease in trend values, which led to a corresponding decline in the AUV value. This decline in AUV was found to be indicative of reduced water retention capacity and decreased soil resilience. Overall, this method offers a practical solution to (i) predict dynamic changes in matric potential using only soil water content measurements, (ii) monitor shifts in SWRC over time to reflect changes in soil health and (iii) provide a scalable tool for assessing soil resilience to climate variability, making it particularly useful in regions where direct measurements of soil matric potential are not available.

Compaction reduces the infiltration capacity of the soil surface and may result in water ponding during heavy rainfall events. The same ponding effect is expected for soils with low organic content, limiting the formation of structural pores with high drainage capacity. The resulting presence of ponding water generates run-off and anaerobic conditions in the topsoil, increasing erosion rate and reducing the biological activity and productivity. The longer the duration of a rainfall event, the lower the infiltration capacity of the soil and the higher the risk that the infiltration capacity becomes limiting, defining the ‘ponding time’ as the time of onset of water accumulation at the surface. The ponding time is a comprehensive soil physical property, integrating aspects of soil water retention, hydraulic conductivity, and initial water content. The lower the ponding time for a certain precipitation rate, the more frequent is the expected occurrence of water ponding at the surface. In this study, we apply an analytical expression for ponding time to compute it at the Pan-European scale. Using maps of basic soil information (soil texture, organic carbon, and bulk density), we can estimate values of ponding time and thus the frequency of ponding (and run-off) by infiltration excess. This map provides a reference for the quantification of soil health by reducing ponding time by compaction and loss of organic carbon (‘unhealthy’) and increasing ponding time by structure formation (‘healthy’). Applying pedotransfer functions linking soil hydraulic properties with basic soil information and land use, we provide a sensitivity map to estimate the change in ponding time statistics by modifying land management. The generated maps have a spatial resolution of 1 km and allow a comparison with national statistics of hydromorphic constraints, revealing the relationship between infiltration excess and saturation excess. To apply ponding maps in soil health assessment and land use management, they must be developed at higher resolution. We will show the potential of providing ponding maps at higher resolution (30 m, Soil Health Data Cube for Europe) and linking them to remote sensing observations of ponding using satellite data.

One of the main objectives of Soil Mission ‘A Soil Deal for Europe’ is to develop a harmonised soil monitoring framework to assess policy impacts and trends in soil health. It is therefore necessary to integrate the current knowledge on existing monitoring programmes and harmonise the approaches used across Europe. It was emphasized in the Soil Mission implementation plan that current EU monitoring is hampered by inadequate or inactive soil monitoring programs in many EU Member States and limited availability or lack of relevant data. One of the current gaps in soil monitoring is the insufficient coverage of soils located in urban, forest or industrial areas. This is being addressed by the PREPSOIL project, whose main objective is to implement the 'A Soil Deal for Europe' mission in European regions, by helping key actors to reduce soil degradation, while increasing soil awareness and knowledge.
A detailed review of projects funded by the European Union related to soil monitoring issues and the soil health indicators used was carried out. In addition, existing national experiences on monitoring with a special focus on non-agricultural area were analysed. These results may constitute the basis for a broader discussion on future monitoring of non-agricultural soils especially in a context of implementation new directive on soil monitoring and resilience.

Acknowledgements
This research has been carried out within the framework of the PREPSOIL project ‘Preparing for the ‘Soil Deal for Europe’ Mission’ founded by European Union’s Horizon Europe programme under grant agreement No 101070045.

A cutting-edge molecular tracking technology for microbial-based products used in agriculture: There is a pressing need for farmer-friendly technologies allowing to detect and monitor microorganisms applied to soil as biostimulants or biopesticides. These technologies would optimise their application method (in terms of dose and timing) fostering efficacy. Researchers are increasingly committed to developing sensors to detect species-specific target microorganisms in soil. In SPIN-FERT, researchers from three Italian partners (CREA, CNR-NANO and INTA) are working together to scale up and validate a portable device for tracking and monitoring a beneficial bacterium (B. subtilis) in the soil.  The device is based on a chip containing a biological sensor (an aptamer), which was developed and patented by @crearicerca researchers in a previous EU-funded project (@excaliburh2020). This kind of device is expected to provide a breakthrough in the method of monitoring microbial-based products and evaluate also their impact on soil health and plant productivity.  A paper we recently published (the second one, regarding the device, will be submitted soon): https://doi.org/10.1007/s00253-023-12765-0

The website of SPIN-FERT is https://spinfert.eu/overview/.
You can also follow us on Instagram @spinfert.eu.

This workshop is an extension to the submitted oral talk “Probability based stratified sampling for both mapping and estimating the population parameters of the soil health indicators at field scale”. In the beginning of the workshop, the participants will become familiar with the appropriate (fit-for-purpose) sampling designs for monitoring the soil health indicators at the field based on the presence/absence of the legacy sampling data and environmental covariates. The brief introduction will be followed by practical coding secession in R using premade computational notebooks. The participants will compare the novel probability based balanced stratified sampling algorithm with 1) simple random sampling, and 2) feature space coverage sampling algorithm using legacy data. In the first experiment, the aim will be to optimize the number of sampling locations of the classic grid sampling performed in a real-world field using the available auxiliary Earth observation environmental layers from the Soil Health Data Cube (https://shdc.ai4soilhealth.eu/). In the second experiment, we will use the available soil maps from the datacube to design a new optimized sampling network for spatiotemporal predictive modeling. The target group of the workshop are non experts in the topic, i. e. soil managers, advisors, young researchers or soil scientists.

The Soils4Africa project, funded under the EU H2020 programme, aims to develop a soil information system that serves information on the prevalence and spatial distribution of soil quality indicators and constraints relevant for sustainable intensification of agriculture in Africa, that can be used as baselines for monitoring changes in soil conditions in the future.

Soil samples are currently being collected at over 16,000 locations for two depths across agricultural land. Uniform procedures for fieldwork as well as lab analysis, combining wet chemistry with spectroscopy analyses, are used to ensure consistency. Here we present the sampling scheme designed for continental assessment and monitoring of soil conditions of the agricultural land in Africa. The design is a three-stage sampling design with stratified random sampling (with stratification based on farming system) in the first stage, and simple random sampling in the second and third stage. Using probability sampling allows model-free and unbiased estimation of the soil (health) parameters of interest of the sample population (or relevant sub-areas thereof such as for land cover types, agro-ecological zones, etc.) and their associated uncertainty. Additionally we will showcase the design and functionality of the emerging, continental soil information system that will eventually be hosted by an Africa-based institution.

A detailed understanding of temporal and spatial dynamics of soil organic carbon is becoming of increasing global importance, as soil organic carbon is directly linked to greenhouse gas emissions and soil carbon sequestration. Additionally, soil organic carbon is a vital element in soil health, affecting many essential soil functions. Therefore, the importance of soil inventories at various scales, from national to pan-European, for quantifying soil organic carbon dynamics has increased. Consequently, numerous spatial and spatio-temporal predictions of soil organic carbon have been produced in recent years. However, it is currently unknown to what extent these inventories and their derived predictions align in terms of the magnitude and direction of soil organic carbon change.
Using data from repeated soil inventories at national and regional scales and data from LUCAS, we compare trends in soil organic carbon across Europe, focusing on mineral soils of agricultural land. For selected regions, the trends of soil organic carbon change are also compared to estimates from the recent maps of soil organic carbon density trends produced by the AI4SoilHealth project. These comparisons are somewhat limited due to differences in sampling and calculation methodology between countries, varying definitions of land uses, and differences in the time periods covered by the various data sources. Overall, the comparison of soil organic carbon dynamics across Europe is complex, and increased collaboration between countries can improve comparability of results and improve alignment of the estimates of soil organic carbon dynamics at both national and European scales.

Authors: Laura Sofie Harbo, Ali Sakhaee, Florian Schneider

A holistic approach that acknowledges the vital functions of soil is fundamental to soil health. Beyond crop production, soil health encompasses the soil's ability to mobilize and buffer nutrients, store carbon, filter and retain water, and support biological activity. Measuring and predicting these ecosystem services through soil health indices is essential for future generations of farmers to ensure sustainable field management.
However, soil health indices are still largely based on primary soil properties. Advances in instrument manufacturing, computational power, and artificial intelligence have enabled rapid and accurate assessments of these properties. Among emerging analytical methods, diffuse reflectance spectroscopy has demonstrated reliability in predicting soil chemical parameters and providing indirect insights into soil physical properties in-situ.
AgroCares offers an integrated solution that combines a portable soil spectroscopy sensor, a comprehensive soil database, and advanced deep learning algorithms to predict soil properties under field conditions. This approach has successfully provided a reliable assessment of soil chemical status and a semi-quantitative evaluation of physical properties which might be used for an estimation of the soil health in-situ by the farmers or land managers. In collaboration with the scientific community, AgroCares is willing to take up the challenge of inferring soil health via spectroscopy. By integrating chemical, physical, and biological properties, this solution aims to drive progress toward real-time, in situ soil health assessment.

Soils are increasingly rediscovered as a vital resource that underpins many natural and societal services. Over more than half a century, agricultural mechanization and a singular focus on plant production, supported by chemical fertilizers, have led to widespread soil degradation. This reductionistic perspective has relied on soil observations focused on physico-chemical properties; properties that can be boosted by chemical additions but ignore the biological and ecological status and functions of the soil. Recognizing the importance of natural soil processes, which have evolved and been fine-tuned over billions of years, a new set of indicators for describing soil health beyond the physico-chemical properties is required. These indicators should preferably be observable and analyzable by farmers, advisors, extension workers and other citizen scientists. Methods that directly or indirectly capture the biological and ecological functions include, for instance i) environmental DNA (eDNA) metabarcoding to characterize the diversity and composition of soil microbial communities, ii) activity rates of key enzymes involved in the main biogeochemical cycles, iii) the ratio of soil fungi to bacteria, an indicator of the extent of disturbance in soil ecosystems, iv) aggregate stability, which is important for soil erosion resistance, and water and nutrient holding capacity, and v) water infiltration capacity as a key measure of the soil water absorption, holding and release potentials. While eDNA requires specialist laboratories and databases, the other methods are currently available for “Do-It-Yourself” (DIY) testing. In this study, as part of the EU-funded project AI4SoilHealth (https://ai4soilhealth.eu) we sampled soils in Greece, Sweden, Finland, Croatia and Denmark. We applied the outlined methods alongside traditional wet chemistry analysis of properties such as carbon, pH and electrical conductivity, and the particle size distribution. These properties were also estimated by leveraging their correlations with diffuse reflectance Near InfraRed (NIR) spectra and applying machine learning models. We are testing both the robustness of the novel methods and their interdependence with more traditional physico-chemical properties and soil spectroscopy. We hypothesize that there is a significant positive correlation between novel indicators (e.g. eDNA richness is correlated to enzymatic activity, which is correlated to aggregate stability, which in turn is correlated to infiltration capacity) and that high scores of the biological and ecological properties are correlated with, for instance, soil carbon content. This study explores the potential of these novel methods for more holistic understanding of soil health.

Soil Aggregate stability is an important indicator of soil health. Aggregate stability corelates to critical soil ecosystem functions including water infiltration and storage, erosion resistance, and plant rooting. Unfortunately, traditional measures of soil aggregate stability are time- and labor-intensive which limits the applicability of aggregate stability as a widely available soil health indicator. Recent research efforts have developed image-based methods for aggregating stability measurements which generate comparable results to traditional methods in significantly less time. The Soil Health Institute and their partners at the University of Sydney have developed a smartphone application for measuring soil aggregate stability using image-based methods. The application, Slakes, is available for free on both android and iOS devices. was created by the Soil Health Institute in conjunction with the University of Sydney. The app calculates an aggregate stability index by monitoring changes in aggregate size before and after being submerged in water for 10 minutes. This method, while different from traditional approaches, has been shown to be sensitive to changes in agricultural management practices (e.g. cover crops and reduced tillage) and is a viable indicator of soil health. In this workshop, we will discuss the measurements of soil aggregate stability, guide users through aggregate stability measurements using Slakes, and discuss integrating Slakes results into soil health monitoring efforts.

The widespread use of conventional fertilizers during the 20th century was driven by the need to support global population growth, enhance crop yields, and improve soil fertility [1]. However, these fertilizers are prone to significant losses due to leaching or volatilization, leading to both economic inefficiencies and environmental challenges, such as eutrophication and ecosystem destabilization [2]. As a result, there is a growing interest in more sustainable alternatives. Among these, controlled release fertilizers (CRFs), particularly those developed from biochars, offer a promising solution, enabling a more gradual release of nutrients while also enhancing soil structure and health [3].
This study focuses on the production and optimization of CRFs using biochar produced from vineyard prunings, an undervalued agro-industrial residue with limited economic value. Four distinct biochars were prepared using different conditions: 1) untreated biochar produced at an industrial oven (Ibero Massa Florestal company) (BIMF), 2) thermal condition under CO2 flow (BCO2); and biochars chemically pre-treated with 3) magnesium chloride (BMgCl2) and 4) aluminium chloride (BAlCl3). The adsorption capacities for nitrogen (N), phosphorous (P) and potassium (K) were evaluated across a pH range between 2 and 13. Subsequent optimizations were carried out for N adsorption at pH 2 using the BIMF material and for P adsorption at pH 8 using the BMgCl2 material. After adsorption conditions optimization, the maximum Langmuir adsorption capacities were 10.4 mg N/g for BIMF and 12.7 mg P/g for BMgCl2. Current investigations are focusing on the nutrient release kinetics from the CRFs, aiming to assess their potential for gradual nutrient delivery and long-term soil fertility improvement.
This work highlights the potential of vineyard pruning biochars as a sustainable material to prepare CRFs, offering both agricultural and environmental benefits.

Bibliography
[1]. Wang, C. et al. Biochar-based slow-release of fertilizers for sustainable agriculture: A mini review. Environ. Sci. Ecotechnology 10, 100167 (2022).
[2]. Tomczyk, A., Kondracki, B. & Szewczuk-Karpisz, K. Chemical modification of biochars as a method to improve its surface properties and efficiency in removing xenobiotics from aqueous media. Chemosphere 312, 137238 (2022).
[3]. Biswas, B. et al. Magnesium doped biochar for simultaneous adsorption of phosphate and nitrogen ions from aqueous solution. Chemosphere 358, 142130 (2024).

The comprehensive characterization of soil microbiomes is pivotal for understanding ecosystem functions and managing soil health. The aim of the study is to develop a standardized metabarcoding pipeline utilizing universal genetic markers, such as the 16S rRNA and ITS and it is also possible for specific markers that target genes associated with critical metabolic functions. Sequencing is conducted using the MinION platform by Oxford Nanopore Technologies, enabling real-time data acquisition and analysis.

A key component of this pipeline is the creation of a qualified database comprising accurately annotated sequences derived from standardized metabarcoding protocols. This database, enhanced by the custom analysis tools available through the EPI2ME labs platform, serves as a foundational tool for ensuring reproducibility and comparability across studies, addressing the current challenge of data heterogeneity due to varied experimental and analytical methodologies. This database not only enhances the taxonomic resolution but can also potentially enrich the functional profiling of soil microbiomes.

The research incorporates two distinct series of soil samples: one from wheat fields cultivated in Sicily and another from greenhouse-grown tomatoes. These diverse agricultural settings provide two case studies with a broad spectrum of microbial communities, to test the robustness and applicability of the metabarcoding pipeline.

The standardized data from this qualified database can be exploited to train artificial intelligence (AI) models, aiming to identify predictive signatures of soil health and potential for reclamation from pollutants. By applying machine learning techniques to metabarcoding data, this approach promises to uncover novel correlations between microbial communities and soil conditions, potentially leading to innovative strategies for soil management and rehabilitation.

In summary, the establishment of a standardized metabarcoding pipeline and a qualified database on the MinION platform, enriched with data from diverse agricultural soils, represents a significant advancement in soil microbiology. This framework not only enhances our understanding of microbial diversity and function but also offers the possibility to apply AI technologies to predict and improve soil health on a global scale.

More than 90% of soils in Europe have been declared unhealthy, largely as a result of injudicious use of synthetic fertilizers and overexploitation of soil. This calls for an increased use of more sustainable types of fertilizers and soil amenders rich in carbon.
The Anaerobic digestion (AD), a process that is used to produce renewable energy with low CO2 footprint, can produce a valuable by-product, the digestate, that is used in agricultural activities as a soil improver or for fertilization of the fields. The digestate is actually the by-product of the valorization of waste materials. A wide variety of organic wastes-manure, food processing residues, municipal solid waste, and agricultural residues, are used in AD plants and the produced digestate is returned back to the fields, closing the loop in a circular economy approach.
However, it has been identified that the direct application of digestate is associated to several environmental issues. It is therefore required that the digestate is pre-processed in order that the nutrients, the carbon and water can be recovered and efficiently utilized, while potential pollutants are removed and not released to the environment, optimizing in this way the products’ composition according to particular agricultural needs with the adoption of an adequate separation system.
This work executes a Life Cycle Assessment on a membrane-based treatment process including a solid-liquid separation system with a screw press, microfiltration (MF), and ultrafiltration (UF) to produce a phosphorus- and potassium-rich soil amender and a Selective ElectroDialysis unit (SED) for nutrient recovery to produce fertilizers such as ammonium sulfate and struvite. Furthermore, reverse osmosis (RO) is applied for the recovery of clean water.
The environmental impacts that were considered and studied, were the greenhouse gas emissions, terrestrial acidification and eutrophication, ecotoxicity in freshwater, and marine environments, using input from experimental testing in the pilot scale and in real environment. The results showed that an integrated approach could achieve significant environmental improvements and enhance soil health, compared to conventional applications.

Transient soil properties are informative of many aspects of soil health. First, the directly measured properties such as drying rate and coloration changes can be informative of soil texture and mineral contents. Second, the changes in vegetation cover and the dynamics of biomass accumulation can serve as a proxy of the soil productivity and suitability for biomass production. Many of these traits can be readily retrieved from satellites, however, with limited temporal resolution. We developed a modular, low power IoT device combining multispectral radiometric capabilities (6 – 12 channels, 450 – 860nm) with simple weather station. The device harbors powerful industry-level SoC with onboard processing capability showing low power consumption, retrieving data in 15 minute intervals for two years on a single battery. During 2023 and 2024 five devices were set to maize crop fields for vegetation monitoring. The devices were positioned with GPS tracker to positions always covered by Sentinel 2-A tiles. Data analysis showed very strong correlations between proximally and remotely obtained vegetation indices. The usability of such data might be used during the cloudy days to support decision making processes. Moreover, the data can be interpolated to predict the regional dynamics during the cloudy weather. Such devices might also improve the monitoring capability of soil dynamics in forest vegetation where soil dynamics are not visible by optical sensing echnologies due to the tall vegetation cover. The usability of such devices will be discussed.

This study addresses the critical role of soil organic carbon (SOC) in maintaining soil health, particularly regarding compaction, infiltration, runoff, and erosion. SOC plays a vital role in maintaining soil structure and function, and its depletion is increasingly linked to reduced water retention and increased bulk density, and greater susceptibility to erosion and compaction. Conventional farming, with its intensive use of synthetic fertilisers and tillage, has been shown to have a negative effect on SOC, while organic farming practices are recognised for enhancing SOC through organic amendments and reduced soil disturbance. We modelled the effect of a 5% bulk density decrease on soil hydraulic properties across Europe. Using SoilGrids data – bulk density, SOC, volumetric water content at field capacity and the permanent wilting point, and soil texture –, we modelled hydraulic conductivity and soil water potential for mineral soils using Rosetta and Hydrus-1D, two widely used tools for predicting soil hydraulic properties. This modelling provides crucial insights into how organic and conventional practices influence soil water retention and erosion potential, and the importance of integrating SOC-enhancing practices into national and international soil monitoring systems. By understanding how a shift to organic farming influences soil health, we can better inform agricultural policies that aim to promote both productivity and sustainability in farming systems across Europe.

Soil salinization, referring to the excessive accumulation of soluble salt in soils, adversely influences nutrient cycling, microbial activity, biodiversity, plant growth and crop production thus affecting soil health and ecosystem functioning. Soil salinity quantification is a major step toward mitigation of its effects. Therefore, developing quantitative tools to predict soil salinity at regional and continental levels under different boundary conditions and scenarios is crucial for sustainable soil management and security of natural resources. This study proposes an AI-driven soil salinity quantification and projection approach focused on EU soils using a set of environmental covariates which consist of soil properties, terrain attributes, climate, and remotely sensed variables. A key aspect of this study is integration of the soil salinity point data from the LUCAS survey in the AI model, complemented by the WoSIS dataset. To improve the model performance, forward feature selection technique was applied. AI algorithms including Random Forest, LightGBM, and XGBoost were used in this study enabling us to evaluate the performance of each algorithm in predicting soil salinity across EU with the XGBoost algorithm producing the most accurate results. The output of the predictive model will be a gridded dataset illustrating the spatial and temporal (yearly) distribution of soil salinity across the EU, accompanied by the corresponding uncertainty map with the spatial resolution of 1-km. This information is crucial for identifying regions with elevated salinity levels and formulating necessary action plans to mitigate the situation.

The advent of modern satellite constellations–combined with significant advances in computational technology and resources–enables the systematic mapping of agricultural areas in high spatiotemporal resolution and through this provides a foundational building-block for the study and monitoring of soil health. In this context, parts of the Earth Observation and Machine Learning community have placed a growing focus on the development of capabilities to remotely identify crop types growing on agricultural cropland. These capabilities can support soil health monitoring efforts by providing systematic insights into crop rotations and cropping practices that affect soil health (e.g. cover crops). End users of these capabilities desire high accuracy across large areas with diverse agro-environmental conditions, as early in the season as possible.

Whilst recent efforts have typically shown strong performance on datasets that express limited spatial and/or temporal variability, the community is yet to explore performance across an adequate number of years at the pan-European scale to assess robustness both to the spatial variations between environmental & political zones and to the full range of variations in interannual weather patterns. To do so, there is still a need for datasets that provide sufficient spatial and temporal depth.

In Europe, the public release of historical LPIS and GSAA datasets by EU member states at either regional or national scales has made high quality crop type ground-truth data more available than ever before. The RapidCrops dataset combines these datasets across a range of countries and multiple years to provide a deep spatio-temporal stack of crop type ground-truth data; enabling assessments of generalization across both space and time. The dataset leverages harmonization standards developed under the EuroCrops initiative to standardize data from different countries. It adopts & extends the fiboa (https://fiboa.org) field boundaries data standard to make parcel boundaries and crop type labels available in an open, interoperable format. Finally, the dataset provides additional usability metrics for each parcel to help users identify and access the data most appropriate to their context, quickly.

Peatlands are unique ecosystems with high biodiversity and environmental services such as water filtration and retention as well as carbon storage. Interestingly, however, in contrast to other soils and ecosystems, little is known about the extent and health of European peatlands (Andersen et al., 2017). With increasing human-induced drainage, degradation and restoration, there is an even greater need to monitor the extent and health of European peatlands (Andersen et al., 2017). We developed a conceptual framework to (1) distinguish between (unforested) peatlands and surrounding areas (forest and grassland), and (2) separate drained/degraded from natural/rewetted peatlands. Our study includes 11 European peatlands across three Köppen-Geiger climate classes (Kottek et al., 2006). We use remote sensing data because they provide objective, spatially explicit and temporally extensive data (Chasmer et al., 2020). We use Sentinel 2 and Planet Scope optical bands with high spatial and temporal resolution, focusing on red, red edge, near infrared (NIR), and shortwave infrared (SWIR) band reflectances to discriminate between peatland vegetation and surrounding areas (Burdun et al., 2023). Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index Red (EVI). Green Normalized Vegetation Index (gNDVI), and Greenness Index (GI) were used as indicators of vegetation composition and health (Burdrun et al., 2023; Räsänen et al, 2022), while Normalized Moisture Index (NDMI) was used as measure for vegetation water stress (Räsänen et al., 2022). Ground truthing of our data was performed with biogeochemical analyses, including pyrolysis gas chromatography with integrated mass spectroscopy (PYGCMS) to study the molecular composition of surface soils. In particular, we investigated molecules specific to different vegetation classes and their transformation products. To verify our results, we also used established biogeochemical parameters such as C:N ratio and oxidation state (Cox), which are indicators of the degree of microbial transformation and decomposition processes in soils (Leifeld et al., 2020). As a first step, we separated peatlands from surrounding forest using existing European Forest layers. We further distinguished grasslands from peatlands using red edge and NIR reflectance data, which were significantly higher for grasslands than for peatlands (p<0.001). To distinguish between natural/rewetted and degraded/drained sites, we will correlate the specific reflectance with the molecular and biochemical data to establish a framework for an inventory of peatland sites and their health on a regional scale using a machine learning approach.

Soil water repellency (SWR) affects water dynamics from nano to ecosystem scales, and it is driven by intricate interactions between climate, vegetation, soil properties, and microorganisms. However, the spatial distribution of SWR at ecosystem level as well as the underlying drivers across diverse habitats, land uses and soils textures remain underexplored. This study presents a comprehensive survey of SWR in Denmark, with approximately 7,500 samples, and its predicted spatial distribution. We used digital soil mapping methods (Quantile Random Forest) to map and identify the relationship between SWR and various environmental variables, including vegetation (via satellite imagery), soil properties (texture and soil organic carbon), and landforms (slope and wetness index). The predicted maps at 10 m resolution revealed that SWR varies across different land uses and vegetation types, with higher values in natural areas (e.g., heathlands and coniferous forests) compared to grasslands and croplands (mostly hydrophilic). The analysis also identified soil organic carbon, Sentinel band 2 (SB3_spring) and clay content as key drivers of spatial variation in SWR at national level. Within natural habitats and grasslands, we found that soil texture significantly influences SWR intensity, which generally decreases as clay content increases across most habitat types, except for heathlands. While the predicted maps provided valuable insights into SWR distribution and its environmental drivers, further research is needed to explore the spatio-temporal dynamics of SWR within each habitat, particularly in relation to soil moisture changes. This study highlights the potential of combining machine learning and remote sensing to advance knowledge of SWR, and it can provide crucial spatial information for managing water resources and enhancing soil health and ecosystem resilience in the face of climate change.

Reduced tillage is an effective measure to increase soil organic carbon (SOC) contents in agricultural soils. However, most of the studies in the literature refer to gains of SOC at the top surface layer. Ignoring the subsoil carbon dynamics in deeper layers of soil fails to recognize potential opportunities for soil C sequestration and may lead to false conclusions about the impact of management practices on C sequestration. The global objective was to evaluate total SOC (and different pools) under three different sustainable management practices (no tillage, reduced tillage and reduced tillage plus green manure) compared to the traditional management in a 0-60 cm soil profile and go deeper on how different OC pools contribute to total SOC storage in depth. To reach these objectives five soil profiles from two experimental farms with similar environmental characteristics were sampled at the intervals 0-15, 15-30, 30-50 and 50-60 cm depth. In addition, a reference profile at each site, in an undisturbed natural area next to the woody orchards were sampled. Per each interval within a profile, three disturbed and undisturbed samples were collected. Bulk density, total OC and different OC pools (particulate organic carbon (POC), mineral associated organic carbon (MAC), hot water extractable carbon (HWC), short mineralization carbon (SMC)) and texture were analyzed. Aboveground carbon inputs in each management were also considered. Preliminary results indicate, a different pattern in the SOC stock with depth depend on the management and experimental farm and an increase in SOC stock at all depths when reduce tillage plus green manure and no tillage are implemented respect to the traditional management. Moreover, higher increase in SOC stock under reduce tillage plus green manure compared to traditional tillage was observed when considering the 0-60 cm profile than when considering the first 30 cm of soil indicating the importance of studying the OC at deeper layers. The contribution of labile OC pools to total SOC decreased, in general and about 50% from the surface layer to the deepest one in cultivated soils (regardless, intensive or reduced tillage) and about 10-20% under undisturbed natural conditions. The labile OC pool more sensitive to changes in management was POC and HWOC depending on the experimental farm.

Policy demands for robust soil health monitoring are steadily growing. Given that soil biota are critical to the ecosystem services soils provide, biological properties are well-suited as relevant indicators, complementing physicochemical characteristics. However, biological properties are highly dynamic across spatial and temporal scales, which presents a challenge when using them for monitoring purposes.
As part of AI4SoilHealth project, we conducted a comprehensive soil health assessment in the experimental grasslands of NEIKER, where a rotational grazing system has been in place since 2013, compared to a free grazing system. Our objectives were to test innovative methods for measuring soil health and to analyze the temporal dynamics of soil biological properties in relation to climatic and pasture conditions.
Plant and soil samples were collected every three weeks from April to November 2024 at two depths (0-20 cm and 20-50 cm). A broad array of descriptors related to pasture quality, production, and soil physicochemical and biological properties were assessed. Novel methods tested and compared to conventional approaches included: (i) DigitSoil – a tool that measures enzymatic activity, providing real-time data on organic matter decomposition and other key biological processes; (ii) microBIOMETER – a portable kit measuring microbial biomass and the fungi-to-bacteria ratio; (iii) Slakes – assessing aggregate stability through a mobile app; (iv) eDNA and eRNA metabarcoding of 16S rRNA and ITS, to differentiate total and active prokaryotic and fungal communities; (v) remote sensing from Planet to provide data on vegetation growth and greenness.
The novel diagnostic tools provided cost-effective and high quality soil health assessments. Nevertheless, preliminary results suggest that differences in soil biological properties were more pronounced across soil depths and over time than between grazing types. Therefore, their spatial and temporal variability must be considered when designing a soil health monitoring program.

There are approximately twelve million hectares devoted to olive groves in the world, and around seven million hectares are cultivated with vineyards. The majority of this cultivated area is located in the Mediterranean basin, with Spain and Italy being among the countries dedicating the largest area of land to these crops. Historically, these woody crops have been managed with traditional tillage to prevent competition for water and nutrients with the underlying vegetation. The use of alternative management practices such as cover crops improves the physical-chemical and biological properties of the soil, preventing erosion and enhancing soil structure due to increased levels of organic matter in the soil, while also improving other ecosystem services. Biological properties are generally sensitive to changes in soil management, with enzymatic activities being one of the most commonly used biological indicators for studying these processes. This study aims to compare the impact of contrasting soil management (traditional tillage versus management with spontaneous vegetation cover), on the soil enzymatic activities in olive groves and vineyards located in Sardinia (Italy). Two vineyards situated in Central and Eastern Sardinia, and two olive groves in North-western Sardinia were selected. In each of these locations, soil samples in the selected grove with vegetation cover and a nearby tilled plot were collected. Three composite samples were taken at two depths (0-10 cm and 10-30 cm). In each soil sample, β-glucosidase, arylsulfatase, urease and phosphatase activities were determined following ISO20130. An analysis of variance was performed with a general linear model (Statgraphics Centurion XVIII) considering soil management and depth as factors. Significant differences were found in all studied enzymatic activities except for phosphatase. Sardinian vineyards with cover crops showed significantly higher enzymatic activities than tilled vineyards for the enzymes β-glucosidase, arylsulfatase and urease. Oppositely, in the studied olive groves, enzymatic activity of β-glucosidase, arylsulfatase, and urease was higher in tilled olive groves than in those with cover crops. In conclusion, the use of cover crops in woody crops affects the activity of soil microorganisms. Nevertheless, factors such as main crop and plant cover characteristics as the inputs of organic matter, as well as soil type and soil physicochemical properties have to be taken into account to interpret the results.

Soil degradation poses critical challenges to sustainable food production and environmental stability. In this study, we integrate simulations from 18 global climate models under two combined SSP-RCP scenarios (SSP2-4.5 and SSP5-8.5) with land use fractions from the Land Use Harmonization (LUH2) dataset to assess future soil degradation risks across Europe. We adopt a machine learning framework to link a Soil Degradation Proxy (an index integrating multiple soil health indicators including erosion rate, pH, electrical conductivity, and soil organic carbon; SDP) to topography, soil characteristics, climatic factors, and land use practices, enabling projections of how these factors collectively influence future soil degradation trends.
Our projections indicate that under the higher-emission SSP5-8.5 scenario, approximately 54% of European soil observation sites could face increased vulnerability to degradation by the far future (2071–2100). This heightened degradation risk is especially evident in northern European regions, such as Estonia and Latvia, where SDP may rise by up to 16%, largely influenced by changing climate conditions. In contrast, southern regions of Europe (e.g., Spain and Italy) could experience a decrease in SDP, suggesting potential improvements in soil health tied to evolving land use practices.
By combining climate projections, land use practices, and soil type, this work provides new insights into future trends and patterns of soil degradation across Europe. These findings support the urgent need for developing targeted soil management strategies to mitigate the negative impacts of climate and land use change on soil health conditions.

Soil organic carbon (SOC) concentration is the fundamental indicator of soil health,
underpinning food production and climate change mitigation. SOC storage is highly
sensitive to several dynamic environmental drivers, with approximately one third of
soils degraded and losing carbon worldwide. Digital soil mapping illuminates where
hotspots of SOC storage occur and where losses to the atmosphere are most likely.
Yet, attempts to map SOC often produce widely differing results for the same region,
owing to differences in methodology and the representativeness of input data for
predictive mapping. Here we compare national scale SOC concentration map
products for Great Britain – a country where several digital SOC maps are available
and consists of soils spanning the full range of SOC concentrations. Our results
reveal generally strong agreement of data in mineral soils, with progressively poorer
agreement in organo-mineral and organic soils. Divergences in map predictions from
each other and survey data widen in the high SOC content land types we stratified.
Given the disparities are highest in carbon rich soils, efforts are required to reduce
these uncertainties to increase confidence in mapping SOC storage and predicting
where change may be important at national to global scales. This is particularly
important because the decline in SOC stocks from rising temperatures scales
proportionally with the size of the standing SOC stocks; thus, current uncertainties in
total SOC stocks presents a barrier to fully understanding the land carbon-climate
feedback. Our map comparison results could be used to identify SOC risk where
concentrations are high and should be conserved, and where uncertainty is high and
further monitoring should be targeted. Reducing inter-map uncertainty will rely on
addressing limitations with how representative observational data are for a region of
interest, as well as including covariates that capture the convergence of physical
factors that produce high SOC contents.

The SOILCRATES project, funded by the Horizon Europe Mission Soil programme, aims to enhance and monitor soil structure, biodiversity, and crop-growing conditions in mineral soils through the establishment of four living labs across the Netherlands, France, Ireland, and Spain. This poster focuses on the Irish living lab, highlighting the specific soil challenges faced in Ireland, the corresponding soil health indicators, and the key partners involved in the initiative.

The SOILCRATES project, funded by the Horizon Europe Mission Soil programme, aims to enhance and monitor soil structure, biodiversity, and crop-growing conditions in mineral soils through the establishment of four living labs across the Netherlands, France, Ireland, and Spain. This poster focuses on the Irish living lab, highlighting the specific soil challenges faced in Ireland, the corresponding soil health indicators, and the key partners involved in the initiative.

The SOILCRATES project, funded by the Horizon Europe Mission Soil programme, aims to enhance and monitor soil structure, biodiversity, and crop-growing conditions in mineral soils through the establishment of four living labs across the Netherlands, France, Ireland, and Spain. This poster focuses on the Irish living lab, highlighting the specific soil challenges faced in Ireland, the corresponding soil health indicators, and the key partners involved in the initiative.

The SOILCRATES project, funded by the Horizon Europe Mission Soil programme, aims to enhance and monitor soil structure, biodiversity, and crop-growing conditions in mineral soils through the establishment of four living labs across the Netherlands, France, Ireland, and Spain. This poster focuses on the Irish living lab, highlighting the specific soil challenges faced in Ireland, the corresponding soil health indicators, and the key partners involved in the initiative.

Agroforestry (AF) is a nature based intensive land management practice where trees and shrubs are intentionally integrated into crop and livestock management practices to optimize benefits arising from biophysical interactions among the components. Due to the interactions among the components, AF provides numerous ecosystem services including soil health (SH) benefits. Agroforestry was approved by both the afforestation and reforestation programs and under the Clean Development Mechanisms of the Kyoto Protocol for carbon sequestration (CS). The objective of this long-term alleycropping AF practice was to evaluate changes in soil carbon (SC) and selected soil physical parameters (infiltration, saturated hydraulic conductivity, porosity, and aggregate stability). Soil samples were collected from corn-soybean crop alleys, tree buffers, grass buffers, and grass waterways to quantify differences in SC and physical parameters by treatments. Results of the study indicated that SC%, stocks, and the rate of SC accumulation were greater in AF areas and grass buffer areas than crop areas. Soil C stocks were 106, 102, and 91 Mg ha-1 for tree buffer, grass buffer, and crop areas 25 years after establishment of buffers. Soil water infiltration, saturated hydraulic conductivity (Ksat), porosity, and aggregate stability were greater in tree buffer areas than the crop areas. Improvements in SH indicators can be attributed to increased litter material, roots, activities of soil fauna, and reduced disturbance. Results of the study show that adoption of agroforestry in corn-soybean rotations improve SH including soil carbon (SC), physical properties, and thereby enhance water quality and land productivity.

Boermarke-Zeijen is a 350-year old farmers collective in the North of the Netherlands. The farmer collective
owns 1200 hectares of land and consists of five dairy farms, four arable farms, two mixed farms, and one chicken
farm. The farmers are developing economically and ecologically sustainable farming practices to strengthen soil
fertility and biodiversity at company and regional scale. The soils are sandy with peat patches, which is
representative of the soils of the Netherlands. The farmers producing agricultural crops face subsoil compaction
and soil crusting, leading to decreased infiltration capacity. Some of the dairy farms face phosphate deficiencies.
As part of AI4SoilHealth project, Planet Labs is teaming up with the farmer collective and the regional water
board Noorderzijlvest, to correlate in-situ measurements with Planet’s satellite data products to demonstrate its
value for monitoring and decision making. The farmers have a specific interest in monitoring nutrient fluxes, soil
moisture, land surface temperature and biomass conditions, specifically for the sustainable application of
fertilizer.
The in-situ monitoring network collects location-specific, real-time information about the weather outlook, the
level of surface water and groundwater, the moisture content of the topsoil and the water quality. Legacy data
includes in-situ samples and soil profiles covering a range of soil parameters. A field sampling campaign is
planned in April 2025 to collect the AI4SoilHealth baseline indicators (texture, SOC, pH, CEC, nutrients, density)
and additional indicators (e.g. enzymatic activity, eDNA, Macrofauna, NIR-spectroscopy).
We have used Planet’s high spatial and temporal resolution satellite data [Planet Product] to monitor and
characterize the landscape of Boermarke Zijen, by looking at Vegetation health [PlanetScope, Crop Biomass];
Water balance [Soil Water Content]; Environmental stresses [Land Surface Temperature]; Soil health [Tanager,
Sentinel, PlanetScope] and Above ground carbon [Forest Carbon, Crop Biomass]. With the recent launch of
Planet’s Hyperspectral Mission Tanager, the pilot at Boermarken Zijen will also facilitate investigations into the
feasibility of soil property estimation using spaceborne hyperspectral sensors. Using our satellite data products
in combination with the in-situ sample data, will evaluate the water regime and the potential and effects of
year-round greenery to address some of the challenges that the farmers at Boermarke Zijen are facing.

Biological indicators play a critical role in assessing soil functions and overall soil health, yet they remain underrepresented compared to chemical and physical indicators. Soil health is strongly influenced by biological activity, which is essential for nutrient cycling, organic matter decomposition, and overall ecosystem productivity. Extracellular enzymatic activities (EEA), in particular, provide valuable insights into how soil biological activity responds to external factors such as management practices, climatic changes, or pollutants. However, traditional methods for measuring EEA typically require complex laboratory setups, which limits their application in real-time field assessments.
In this study, we introduce a novel, laboratory-independent soil enzyme activity reader (SEAR). SEAR utilizes an approach where soil enzymes react with fluorogenic substrates embedded in a transparent gel. Upon contact, the enzymes catalyze a reaction, producing fluorescent products that are detected on the opposite side of the gel. This enables a rapid and efficient assessment of multiple enzymatic activities, with the potential for analytical replicates and controls through the use of reaction plates with multiple gel compartments.
We validated SEAR by spiking sand samples with varying concentrations of different enzymes, thereby establishing operational limits for rate detection, precision, and substrate concentration ranges. Our results demonstrate that SEAR performs reliably across a wide range of soil types, including sandy to silty clay loam soils, acid forest soils (pH < 4), carbonate-containing agricultural soils, and soils with up to 18% organic carbon content. Furthermore, the device was tested under various environmental conditions, including soil moistures ranging from 2% to 173% of water holding capacity and temperatures from 6°C to 50°C, successfully demonstrating its versatility for field applications.
With SEAR, soil EEA measurements can be conducted quickly in the field, eliminating the need for laboratory access, sample storage, or pretreatment, which can alter results. The use of industrially manufactured reaction plates with strict specifications, combined with an automated data analysis pipeline, ensures standardized measurements without requiring specialized laboratory skills.
In conclusion, SEAR represents a significant advancement in soil biological assessment by enabling fast, accurate, and field-ready measurements of EEA. Its potential for standardization and ease of use positions it as a powerful tool for soil scientists and environmental managers to assess soil health and functionality in real time across diverse landscapes and conditions. SEAR will also enable ongoing monitoring of soil biological activity, supporting long-term studies and adaptive management practices for sustainable land use.

Divya Pandey, Valentina Tassone, Camilla Ramezzano
Social Sciences Group (Chair group: Education and Learning Sciences), Wageningen University & Research

The EU project LOESS aims to identify strategies to reorient education in Europe to strengthen soil health awareness. Here, we present findings from research conducted within LOESS, investigating the current ‘state’ of soil health education and the ‘wishes’ for its transformation across 15 LOESS partner countries. In each country, a triangulated approach combining desk-research, one focus group, and ten interviews was conducted to explore educational design at various levels (primary, secondary, tertiary, vocational and general public) investigating six dimensions: purpose (for what), collaborations (with whom), learning space (where), learning process (how), learning activities, and paradigm (from what assumption/worldview). The analyses followed an integration of knowledge from academic and practical expertise, and included a thematic analysis of focus groups and interviews.
A key finding was the general absence of the term 'soil health' within educational offerings. Here, the term soil (health) encompasses both explicit and broader content relevant for soil health. Current soil (health) education emphasizes knowledge acquisition (knowing) and, to a lesser extent, skills development (doing). Fostering personal connections to soil (being) is largely missing. The wishes are to strengthen experiential, doing-based activities (e.g., soil monitoring) and cultivating values and attitudes (being) (e.g., caring for soil) rather than relying on predominantly instructive activities (e.g., lectures). Additionally, there is a strong wish to shift from indoor (e.g., classrooms) to outdoor settings (e.g., gardens, forests) for immersive and sensory-rich learning. This further aligns with the wish to move beyond the dominant mechanistic paradigm—focusing on individual soil components towards an ecological paradigm that acknowledges the soil’s complexity and interconnections with ecosystems and humans.
To bridge these gaps changes are needed at the classroom (micro-level) and at system, policy and structural level (macro-level). A key micro-level need if to improve educator’s training specifically focusing on soil (health) related content and pedagogical skills for outdoor, doing-based, emancipatory and more systems-oriented approaches. At the macro-level, revising curricula to explicitly include soil (health) topics and highlight their connections to sustainability goals emerged as crucial. Additionally, structural support is needed to enhance collaborations and facilitate outdoor learning opportunities.
https://loess-project.eu/

The increasing use of neodymium (Nd) in high-tech industries, particularly in electronics, renewable energy, and other advanced technologies, raises concerns about their accumulation in soils and potential long-term ecological impacts. As demand for these rare earth elements grows, understanding their environmental fate and behavior is crucial. This study assesses the bioavailability, ecotoxicological effects, and enzymatic responses in three soils with contrasting properties, each contaminated with varying concentrations of Nd, to provide a comprehensive understanding of their potential toxic or beneficial effects on soils and resident organisms. Additionally, it explores the biogeochemical cycles of these elements within the technosphere and their possible biological roles. The results will help to indicate if Nd, as a representative technology-critical element, is bioavailable, and therefore accessible for biological uptake. If so, we expect that high concentrations of these elements, due to increased use, could induce stress responses in soil organisms, potentially disrupting vital metabolic pathways and contributing to a decline in soil health. Our findings will help elucidate whether Nd, despite offering technological benefits, might present ecological challenges if its environmental footprint is left unmanaged. Overall, this study underscores the importance of understanding the behavior of Nd in soil systems—not only to mitigate its potential ecological risks but also to inform future guidelines for sustainable industrial use of these technology-critical elements.

As soil health becomes a pivotal focus in sustainable agriculture, the role of soil functions in delivering ecosystem services has garnered increasing attention. Key soil functions include primary productivity, nutrient cycling, water purification & regulation, climate regulation & carbon sequestration, and biodiversity & habitat provision. To evaluate these functions and guide management practices, we developed a suite of qualitative multi-criteria assessment models tailored to the North China Plain, building on the EU Soil Navigator framework. These models enable a systematic assessment of soil function performance and support decision-making for improved field management.

To illustrate, we present the nutrient cycling model as an example. This approach integrates key inputs—soil properties, climatic variables, and agricultural practices—to classify nitrogen (N) and phosphorus (P) cycling performance into “Suitable,” “Neutral”, or “Unsuitable” categories. It incorporates hierarchical evaluations of N and P cycling based on processes related to nutrient availability, risk of nutrient losses, and crop uptake. The framework was developed by integrating knowledge from literature, process-based nutrient models, and expert judgements. The model was tested using datasets from long-term field experiments and smallholder farms, with N and P use efficiencies serving as proxy indicators. Furthermore, the model was applied to evaluate optimized management strategies, such as manure application, enhanced-efficiency fertilizers, and fertigation, demonstrating their potential to improve nutrient cycling and mitigate environmental risks.

The nutrient cycling model is one component of a broader suite of soil health assessment models, each designed to evaluate a specific soil function. Future integration of these models will provide a comprehensive, multi-functional evaluation framework for soil health. This example highlights the broader potential of our soil health models as diagnostic and prescriptive tools, enabling end-users like farmers, farm advisors, and researchers to evaluate soil health and implement targeted interventions that enhance soil multifunctionality and promote sustainable agroecosystem management.

Authors: Ali Sakhaee, Laura Sofie Harbo, Florian Schneider

High-resolution spatio-temporal predictions of various soil health indices, such as soil organic carbon density (SOCD), for the period 2000 to 2023 have recently been published at a pan-European scale by the AI4SoilHealth project. These data offer new opportunities to deepen our understanding of changes in soil health indices and address challenges in sustainable land management by identifying areas at risk of degradation as well as those areas with potential for improvement of soil health, for example by increasing SOCD. Such insights are essential for both policymakers and farmers to make informed, data-driven decisions to protect and improve soil health in Europe.
In this study, we applied linear regression models to assess spatial predictions of soil health indices at 30-meter resolution and to analyze trends over time. Our findings reveal patterns of both increase and decrease of soil health indices across European regions. The largest decrease in SOCD of the top 10 cm of the soil is observed in the eastern and southern parts of Europe, while the largest increase in SOCD for the same layer is found in northern and central regions of Europe. These insights provide a clearer picture of soil health dynamics in Europe and highlight areas where targeted interventions are crucial for effective soil management for improved soil health.

Droughts and heat waves jeopardize terrestrial ecosystem carbon sequestration and hinder EU's goal of being climate-neutral by 2050. Developing an open digital twin of the soil-plant system can help monitor and predict the impact of extreme events on ecosystem functioning. We illustrate how our recently developed STEMMUS-SCOPE model, via linking comprehensive soil-plant processes to novel satellite observables (e.g. solar-induced chlorophyll fluorescence), contributes to building such a digital twin. This approach allows a mechanistic window for tracking above- and below-ground ecophysiological processes with remote sensing techniques. Following Open Science and FAIR principles for data and research software, we present the soil-plant digital twin's building blocks that include three pillars: process-based soil-plant model, physics-informed machine learning, and the assimilation of Earth Observation data.
Applying the soil-plant digital twin to simulate the ecosystem's water-energy-carbon fluxes facilitates a swirled evolving loop between the digital twin and the soil-plant physical twin, in terms of enhancing the digital representation of physical system. Such swirled evolving process pushes the frontiers of process-based model developments, for example, to include dynamic vegetation growth, integrated unsaturated-saturated processes, and explicit plant hydraulic pathways into the STEMMUS-SCOPE model. However, it also leads to a major bottleneck of applying such advanced process-based model at regional to global scale, due to the expensive computational cost. The machine learning algorithm helps enable a computationally effective yet physically consistent technique to approximate the original model with a surrogate model to bypass such computational burden. This study emphasizes the importance of FAIR-enabling digital technologies, which translate research needs and developments into reproducible and reusable software, data and knowledge.

This study presents an integrated data preprocessing framework tailored to monitor peatland degradation across diverse climate zones, leveraging the high-resolution capabilities of hyperspectral imagery, Synthetic Aperture Radar (SAR), and LiDAR data. Peatlands are vital carbon sinks that face threats from environmental changes and human activities, making their effective monitoring critical. However, differences in climate and ecosystem characteristics across peatland zones, from temperate to boreal, pose unique challenges in data integration and preprocessing. We address these by aligning multi-sensor data sources to enable seamless analysis of peatland degradation patterns.

To capture intricate peatland features, we incorporate spectral bands from hyperspectral sensors, SAR data for moisture and structural insights, and LiDAR data to detail elevation and topographic changes. Our data integration strategy harmonizes these data layers, facilitating a multi-dimensional view of peatland health. Furthermore, preprocessing steps are adapted based on climate zone characteristics, accounting for variations in spectral reflectance, moisture content, and vegetation structure typical of each zone. This climate-sensitive approach addresses issues in standardizing data resolution and spectral calibration, enhancing the accuracy of degradation assessments.

To streamline the high-dimensional data and retain critical spectral information, we utilize autoencoders and deep autoencoders. These deep learning models effectively reduce data complexity, extracting essential spectral signatures that characterize peatland degradation indicators without significant information loss. This approach ensures a rich yet manageable dataset that supports fine-grained analysis across different peatland types.

Overall, this framework provides a robust foundation for analyzing peatland degradation, offering climate-specific, high-resolution insights critical for conservation and sustainable land management. By enhancing peatland monitoring across diverse environmental conditions, the proposed methodology facilitates more informed decision-making in peatland preservation efforts.

Authors:
Patrik Heintze (1,2), Amirhossein Hassani (3), Panos Panagos (4), Alberto Orgiazzi (4,5), Julia Köninger (6), Maëva Labouyrie (4,7,8), Nima Shokri (1,2)
1 Institute of Geo‐Hydroinformatics, Hamburg University of Technology, Hamburg, Germany.
2 United Nations University Hub on Engineering to Face Climate Change at the Hamburg University of Technology, United Nations University Institute for Water, Environment and Health (UNU‐INWEH), Hamburg, Germany.
3 The Climate and Environmental Research Institute NILU, Kjeller, Norway.
4 European Commission, Joint Research Centre (JRC), Ispra, VA, Italy.
5 European Dynamics, Brussels, Belgium.
6 Departamento de Ecología y Biología Animal, Universidade de Vigo, Vigo, Spain.
7 Department of Plant and Microbial Biology, University of Zurich, Zurich, Switzerland.
8 Plant-Soil-Interactions, Research Division Agroecology and Environment, Agroscope, Zurich, Switzerland.

Diverse microbial communities are fundamental to healthy and productive soils, accommodating essential ecosystem services including nutrient cycling, organic matter decomposition, land-atmosphere carbon exchange, water and climate regulation, and contaminant control. The immense taxonomic and functional diversity of soil microorganisms makes deciphering the intricate interactions between soil, its inhabitants, and the far-extending effects for life on earth a complex challenge. Advances in the analysis of eDNA, like metabarcoding to determine community composition from soil samples, enable large-scale assessments across manifold habitat conditions. Based on the LUCAS 2018 soil biodiversity datasets, we aim to (i) identify key drivers shaping soil microbial community composition, and (ii) quantify marginal changes in soil microbial abundance, richness, and diversity forced by soil properties, climatic, and anthropogenic pressures. To improve the understanding of interactions between external drivers and soil microbial communities, we employ machine learning algorithms, in particular generalized additive models for increased interpretability (Hassani et al., 2024), to investigate and identify the parameters influencing the observed soil microbial diversity and richness in the LUCAS datasets. Our modeling efforts will enable us to predict changes in soil biodiversity under the influence of anthropogenic pressures and projected climate scenarios. Such an analysis can further support decision-making in land management with potential policy implications on a pan-European scale.

References
Hassani, A., Smith, P., & Shokri, N. (2024). Negative correlation between soil salinity and soil organic carbon variability. Proceedings of the National Academy of Sciences, 121(18), e2317332121. https://doi.org/10.1073/pnas.2317332121

Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.

Soil as an Asset Class
Centering science, stewardship, and the farmer’s voice

As soil emerges on the radar of global markets and sustainability metrics, this keynote reframes it not just as a carbon sink or yield substrate — but as a living, multifunctional asset. It challenges us to go beyond measurement and toward meaning: recognizing that true soil health cannot be divorced from the people who steward it. Blending scientific rigor with the lived wisdom of farmers, this talk explores how epistemic humility, systems thinking, and inclusive research can shape a regenerative future — one where soil is valued, not just valued at.

Soil as an Asset Class
Centering science, stewardship, and the farmer’s voice

As soil emerges on the radar of global markets and sustainability metrics, this keynote reframes it not just as a carbon sink or yield substrate — but as a living, multifunctional asset. It challenges us to go beyond measurement and toward meaning: recognizing that true soil health cannot be divorced from the people who steward it. Blending scientific rigor with the lived wisdom of farmers, this talk explores how epistemic humility, systems thinking, and inclusive research can shape a regenerative future — one where soil is valued, not just valued at.

Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.

Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.

Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.Please include an abstract at your earliest convenience. This text is merely descriptive and should be replaced before the official program is published.

Automated Machine Learning (AutoML) is today of interest to many production teams looking for faster and more robust data production (see e.g. https://youtu.be/aiM_9r5strw). Large-scale soil property mapping is challenging due to the significant computational resources required and the extensive human effort needed to locate, harmonize, and prepare data (including measurements and covariates) that align with the target spatial and temporal modeling scales. To address these challenges, we developed a modular framework EO-soilmapper that automates the workflow as much as possible (read more in: https://doi.org/10.21203/rs.3.rs-5128244/v1). Our framework introduces three main components: (1) ready-to-use EU-scale covariate layers—a comprehensive and consistent set of covariates along with the process for their preparation, (2) a harmonized EU soil property point database that integrates and quality-controls soil point data from multiple sources, and (3) “scikit-map” (https://github.com/openlandmap/scikit-map) a Python package that enables a highly automated execution pipeline, minimizing manual operation. Scikit-map supports spatial-temporal point overlay, spatial machine learning, spatial-temporal mapping, parallelized processing, etc. Together, these components streamline workflows, reduce manual input, and ensure consistency across large datasets. These tools and resources can be readily adapted for other machine learning applications in environmental modeling and mapping, further supporting the open-source soil data communities.

Soil water repellency (SWR) significantly impacts water infiltration and soil health, influencing ecological processes across various habitats. Although many of the mechanisms behind SWR are still unclear, studies have shown that different soil and biological properties influence SWR. Hydrophobic compounds produced by plants and microorganisms can increase SWR, but microorganisms can also reduce SWR by degrading the compounds. While several studies have examined SWR in agricultural soils, fewer studies have focused on natural habitats. This study investigates the relationship between soil properties, prokaryotic communities, and potential SWR in soil samples collected from natural and semi-natural habitats across Denmark. We analysed 1,153 soil samples covering 33 habitat types to examine how well SWR can be explained by the soil’s prokaryotic communities and other selected soil properties. Furthermore, we assessed the degree of SWR in the habitats and identified prokaryotic genera indicating a specific degree of SWR. Our findings highlight the influence of prokaryotic communities on the degree of SWR while confirming the relationship between SWR and carbon content. Using path model analysis, we show that both biotic and abiotic factors contribute significantly to SWR. A model including pH, electrical conductivity (EC), total carbon content (TC), and prokaryotic community composition (β-diversity) could explain ~50% of the variation in SWR, with β-diversity and TC being the most important properties. Furthermore, we reveal distinct variations in SWR across habitat types, which cover a wide range of hydrophobicity, from hydrophilic to strongly hydrophobic. Prokaryotic α-diversity was negatively correlated to the degree of SWR, and we found a clear gradient in β-diversity from the highest to the lowest degree of SWR. The degree of SWR was divided into classes, and we identified 69 genera indicating one or a combination of the SWR classes, which could potentially be used as indicators of the degree of SWR. This research underscores the importance of including the microbial communities in studies examining SWR. In perspective, the observed relations between SWR and soil prokaryotic diversity and community composition also imply SWR could become a key biophysical indicator of soil health.

Increasing soil organic carbon (SOC) confers benefits to soil health, biodiversity, underpins carbon sequestration and ameliorates land degradation. One recommendation is to increase SOC such that the SOC to clay ratio (SOC/clay) exceeds 1/13, yet normalising SOC levels based on clay alone gives misleading indications of soil structure and the potential to store additional carbon. Building on work by Poeplau & Don (2023) to benchmark observed against predicted SOC, we advance an alternative indicator: the ratio between observed and “typical” SOC (O/T SOC) for pan-European application. Here, “typical” SOC is the average concentration in different pedo-climate zones, PCZs (which, unlike existing SOC indicators, incorporate land cover and climate, alongside soil texture) across Europe, determined from mineral (<20 % organic matter) topsoils (0–20 cm) sampled during 2009–2018 in LUCAS, Europe's largest soil monitoring scheme (n = 19,855). Regression tree modelling derived 12 PCZs, with typical SOC values ranging 5.99–39.65 g/kg. New index classes for comparison with SOC/clay grades were established from the quartiles of each PCZ's O/T SOC distribution; these were termed: “Low” (below the 25th percentile), “Intermediate” (between the 25th and 50th percentiles), “High” (between the 50th and 75th percentiles), and “Very high” (above the 75th percentile). Compared with SOC/clay, O/T SOC was less sensitive to clay content, land cover, and climate, less geographically skewed, and better reflected differences in soil porosity and SOC stock, supporting 2 EU Soil Health Mission objectives (consolidating SOC stocks; improving soil structure for crops and biota). These patterns held for 2 independent datasets, and O/T SOC grades were sensitive enough to reflect land management differences across several long-term field experiments. O/T SOC used in conjunction with several other physical, chemical and biological soil health indicators can help support the EU Soil Monitoring Law and achieve several United Nations Sustainable Development Goals.

SOILCRATES is a project funded by HORIZON Research and Innovation to support the implementation of mission A Soil Deal for Europe, running in 2024-2028 and focused on developing innovative solutions to enhance soil quality and promote sustainable soil management practices. Collaborating with leading experts, researchers, and living labs, SOILCRATES aims to address critical challenges related to soil health, biodiversity, and ecosystem services.

Inspired by Socrates’ philosophy of inquiry, dialogue and collective learning, SOILCRATES (Soil-crates) is a collaborative project focused on restoring and preserving soil quality across Europe by developing soil literacy and monitoring soil structure, soil life, and crop-growing conditions of mineral soils. With 21 partners, from academia, agricultural stakeholders, and local authorities, SOILCRATES co-creates, tests and implements sustainable soil practices. This initiative addresses the pressing need to manage soil as a living resource, essential to food security, biodiversity, and climate resilience.

SOILCRATES aims at establishing 4 regional and interconnected user-centred Living Labs (LLs) in

France (Landes), Spain (Granada), Ireland (Southwest Ireland) and the Northern Netherlands (Fryslân, Groningen, Drenthe). The 4 Living Labs aim to function as user-centred, place-based and transdisciplinary research and innovation ecosystems that involve multiple partners (e.g., land managers, scientists, citizens, businesses, and local authorities) to co-design, test, monitor and evaluate solutions in real-life settings for improving soil health. With an integrated approach, the project enables the co-development of solutions in the LL and testing and replication in the Experimental Sites and Lighthouses.

Soil microorganisms are strongly impacted by anthropogenic activities and the ongoing global climate change [1]. Understanding the how microbial information may be used to support soil health assessments is crucial for both scientific and policy perspectives to anticipate the functional consequences of future climatic conditions or land use pressures on soil systems [2].
Measurements of soil biology are similar to soil physical and chemical properties in that the interpretation of what constitutes a "good" level for soil health is highly context-specific [3]. The taxonomic and functional diversity of soil microbiome is closely linked to soil health due to soil’s role in dynamic ecosystem processes and the biota’s sensitivity to land management practices [4]. Therefore, selecting microbial metrics to measure soil health depends on the specific soil, site, and aspects of interest.
Denmark is responding to the growing number of EU initiatives to protect soils and the environment by gathering data on complex soil properties that provide a richer picture of soil health. We collected over 7000 topsoil samples from natural and agricultural areas across Denmark, and analyzed their bacterial composition through a DNA metabarcoding approach. We calculated α-diversity and potential functions to bacterial communities. We used spatial layers of soil properties, climate, vegetation, geomorphology, and parent materials to map the α-diversity, and the relative abundance of denitrifiers, methanotrophs and nitrite-oxidizing bacteria.
We used spatialized soil health indicators namely, SOC concentration, bulk density, pH, EC, soil hydrophobicity, SOC sequestration potential, tillage erosion, water erosion, and nitrogen leaching to map the simultaneous presence of potential threats to soil health in Denmark. We considered potential threats to those soils characterized by below-typical SOC and pH values, and above-typical values of pH, BD, EC clay-to-SOC ratio, soil hydrophobicity, SOC loss, tillage erosion, water erosion, and nitrogen leaching. We did not directly include the soil microbial data as soil health indicator. Instead, we explored the relationship between potential threats and our microbial data to understand how taxonomical and functional diversity respond to different soil degradation conditions.
The α-diversity and the relative abundance of functional groups did not decrease as the potential threats to soil health increased. It is possible that threatening soil conditions, which may physically or chemically inhibit, injure, or eliminate certain microbial communities, create opportunities for other organisms to grow and reproduce, thereby increasing diversity in these areas.

Remediation strategies for metal(loid)-polluted soils can be based on physical, chemical, and biological approaches, as well as on the combination of these. The present work evaluates the effectiveness of a set of soil remediation treatments for restoring soil health in degraded soils consisting of the combined application of inorganic and organic amendments (marble sludge, vermicompost, and dry olive residue [DOR] biotransformed by the saprobic fungi Coriolopsis rigida and Coprinellus radians) and the inoculation of arbuscular mycorrhizal fungi (AMFs) (Rhizophagus irregularis and Rhizoglomus custos). These treatments were applied under greenhouse conditions to soil residually polluted by metal(loid)s including Pb, As, Zn, Cu, Cd, and Sb, and wheat was cultivated in the amended soils to test the effectiveness of the treatments in reducing soil toxicity and improving soil and plant health. In this sense, the influence of the treatments on the main soil properties and microbial activities was evaluated, as well as on PTE availability and bioaccumulation in wheat plants. Overall, all treatments showed a positive influence in terms of soil properties improvement, while those combining marble and biotransformed DOR as organic amendment were the most effective in improving soil biological status, promoting plant growth and survival, and reducing PTE availability and plant uptake. Furthermore, AMF inoculation further enhanced the efficacy of DOR amendments by promoting the immobilization of PTEs in soil and stimulating the phytostabilization mechanisms induced by AMFs, thus playing an important bioprotective role in plants. In conclusion, these findings indicate that biotransformed DOR may represent an efficient product for use as a soil organic amendment for the remediation of metal(loid)-polluted soils, and that its application in combination with AMFs may represent a promising sustainable bioremediation strategy for recovering soil health and functions in polluted areas.

Fertilizers play a significant role in ensuring food security and building soil health, but excess nutrients pose a risk for water quality. Chemical fertilizers provide nutrients in plant-available form to feed the crop, and they are widely used to increase crop yield. Organic fertilizers, on the other hand, provide fewer quickly available nutrients, but they do provide organic matter to build the soil. This organic matter has positive impacts on soil structure, soil biology, and soil water holding capacity, and it delivers nutrients to the crops after mineralization. To investigate the long-term effect of different fertilization strategies we tested the following the following hypotheses: Fertilizers that primarily feed the crop do initially have high yields, but they see decreasing yields over time. On the other hand, fertilizers that primarily build the soil do initially have low yields, because of the low availability of nutrients, while the yields increase over time, with increasing soil health, and mineralization of nutrients from the organic matter.

To test these hypotheses, a twenty year-long field experiment was set up in Flevoland, the Netherlands. The experiment was carried out on a working organic farm, where our study plots were part of the standard crop rotation on the farm. Eight different strategies were tested, including artificial fertilizer, different manures, and composts.

The results show that yield is comparable for fertilizers that primarily build the soil and fertilizers that primarily feed the crop, while the combined treatment has significantly higher yields. We find that building soil health can significantly increase crop yield, both on the short-term and on the long-term. However, yields remained low for fertilizers with a sole focus on building the soil, because even after twenty years of high organic matter application, they do not provide enough plant-available nutrients. We conclude that a (partial) substitution of chemical fertilizers with organic fertilizers can contribute to crop yield and soil health, while it has further environmental benefits such as lowering the sector’s carbon footprint.

The use of traditional tillage as a management tool for agricultural soils is a technique that can negatively influence soil quality due to erosion and the loss of organic carbon (SOC), nutrients, and biodiversity. The use of cover crops (CC) can increase the SOC and produces a cascade of benefits in soil structure, water storage, or biodiversity. In this context, the EJP Soil SANCHOSTHIRST project (Cover crops (CC) ANd soil health and climAte CHaNge adaptatiOn in Semiarid woody crops. THe RemOte SensIng and furTHer scenaRIoS projecTions) aims to delve deeper into the advantages that could be provided by the use of management methods other than traditional tillage in woody crops. One of the aspects taken into account by this project is the study of microbiological activity through the analysis of enzymatic activities related to the main nutrient cycles. This paper presents the preliminary results obtained in the study of the enzymatic activities of b-glucosidase (related to the C cycle), phosphatase (related to the P cycle), urease (related to the N cycle) and arylsulfatase (related to the sulfur cycle) in four vineyard sites in Spain. In each of the sites, sampling was carried out in nearby plots, one with traditional tillage and another with cover crops, taking three sampling points in each of the plots at two depths (0-10 cm and 10-30 cm). The samples taken were kept refrigerated until the analysis was carried out and the indicated enzymatic activities were determined following the ISO 20130 standard in the fraction < 2 mm. In all the cases studied, the enzymatic activities were higher in the samples from the plots with cover crops, especially at the depth of 0-10 cm. The coefficient of variation of the analyzed enzymatic activities was lower in traditional tillage soils, which could indicate that in soils under this type of management the microbial population is affected by reducing its activity and diversity, while on the contrary, in soils under cover crops the higher coefficient of variation would indicate a greater variability in the enzymatic activity and possibly a greater biodiversity.

To address the challenge of soil degradation among different land uses, development of precise indicators that accurately reflect the current state of soil health is crucial. Soil structural attributes, such as the volume of percolating pores and the connectivity of the pore network are inextricably linked to processes such as nutrient dynamics, carbon cycling, root penetration, biological activity, and rainfall partitioning. These attributes are directly reflected in the hydraulic properties of the soil, particularly water infiltration and retention. However, these structural attributes typically have to be quantified using costly and time-consuming imaging methods, while obtaining accurate estimates in lab and field experiments has proven challenging. Our multilevel approach is designed to link directly measured structural attributes (macropore volume and connectivity) to standard field or lab measurements.
More specifically, macropore volume and connectivity were quantified using X-ray imaging across diverse land use types, including arable land, grassland, and forest. Structural characteristics were then correlated with key hydraulic properties, such as water retention and both saturated and unsaturated hydraulic conductivity, measured using Hyprop system. We further compared the imaged and measured hydraulic properties with predictions from the European soil texture-based pedotransfer function EUPTF, to contrast texture- and structure-related soil hydraulic properties. As an additional exploratory angle, we related mid-infrared (MIR) spectral reflectance to our previously obtained hydraulic property data, to evaluate if MIR could serve as a less laborious alternative to traditional lab-based analyses. Finally, to develop applicable user-friendly and sensitive indicators, we correlated our findings with the classifications from in-situ Visual Evaluation of Soil Structure (VESS) and infiltration experiments.
Results of X-ray CT data and Hyprop measurements revealed significant differences in the volumetric fraction and drainage capacity of macropores as well as in the saturated hydraulic conductivity between arable land, grassland, and forest. Forest soil showed the largest drainage capacity of macropores, but also the largest variability between samples. Despite exhibiting similar pore size distributions, arable land samples showed, as a result of tillage, larger pore connectivity than grassland. Larger connectivity did, interestingly, not result in larger hydraulic conductivity of macropores. 
Our novel multilevel approach reveals clear distinction of land use regarding the complex interplay between soil structural continuity, soil texture, and hydraulic behavior. Such knowledge is crucial in formulating sensitive, quantifiable, and scalable soil health indicators.

1. Healthy soils are essential for food production, carbon and water storage and buffering climatic change. As the majority of soils are currently considered unhealthy, evaluation of restoration and management practices requires the regular and systematic monitoring of the physical, chemical, and biological conditions of soil and their overall status. To implement this practice, it is essential to have standardized methods to measure a comprehensive set of physical, chemical and biological indicators, alongside conventional soil descriptions. Here, we present a harmonised protocol for the planning of systematic soil monitoring across continental scales at a single timepoint, from site selection, sampling to data generation. This approach will allow for data integration and produce informative outputs for stakeholders, researchers, landowners and policymakers.
2. Our proposed sampling and processing techniques will minimise methodological and sampling bias by monitoring soils with particular focus on soil faunal and microbial biodiversity. These are evaluated against existing methodologies, data resources, and monitoring efforts.
3. The proposed methodology is based on national and European soil research approaches and has been successfully applied in the HORIZON 2020 Soil Missions funded project “Soil Biodiversity into Ecosystem Services” (SOB4ES) that is developing cost-effective biotic and abiotic indicators of soil conditions across land-use types, intensities and pedoclimatic zones covering 12 European nations.
4. Standardised soil monitoring protocols that combine a comprehensive set of soil parameters with total soil biodiversity across the trophic web are key to gathering datasets comparable across a range of ecosystem types. This will enable robust evaluation of soil condition in respect to management practices, environmental policy, and responses to natural and human-induced environmental change.

High-resolution, reliable soil data is crucial for addressing climate change and sustainable land management. Integrating remote sensing data, such as from Copernicus Sentinel, is essential for improving accuracy and relevance.

This study presents an overview of our Digital Soil Mapping (DSM) approach and its innovations. We combine satellite imagery, environmental covariates (e.g., elevation, weather data), and ground truth observations (e.g., LUCAS and other European and national datasets) to create high-resolution soil property maps using statistical models. These maps encompass primary properties (e.g., organic carbon, pH, texture), derived properties, and soil health indicators.

We used the Soil Composite Mapping Processor (SCMaP) to derive soil reflectance composites from Sentinel-2 time series. These composites aid in identifying bare soil areas and estimating their frequency, serving as a proxy for land management. They represent spectral reflectance and dynamics. Random Forest models, iin particular Quantile Random Forests for uncertainty assessment, are employed to predict soil properties.

This study delves into the advantages and challenges of using high-resolution remote sensing data with limited ground truth data. We also provide insights into product uncertainty assessment at a continental scale, including accuracy, spatial patterns, and user evaluation. We focus in particular on the relevance of finer resolution and accuracy for continental products.

The main objective of the Soil-X-Change project is to collect, harmonize, combine and integrate the results related to sustainable soil and farm management, developed by EIP-AGRI Operational Groups and project partners and to drive the process for scaling up these technologies, practices and knowledge between 9 countries with similar negative aspects of climate change and targets further acceleration to countries with the same problems.

The project will help to connect farmers, interested actors, policy makers, projects, and initiatives to speed up innovation and promote faster, wider co-creation and transposition of innovative solutions for sustainable soil management into practice. The Soil-X-Change project will create an EU-wide network, so EIP Operational Groups (OGs) and key stakeholders can work together on sustainable soil and farm management solutions and to share knowledge and ready-to-use practices that will enable farmers to make the right decisions related to agricultural production practices.

The project will contribute to effective AKIS by intensifying thematic cooperation between researchers, farmers, and other stakeholders in the EU. Soil-X-Change will also contribute to the green transition, smart agriculture, climate-neutrality, and sustainability areas, as well as enhancing and exchanging the knowledge of the main actors.

Soil-X-Change is initiated by EIP-AGRI Operational Group practitioners and reflects the needs of more than 100 direct partners. Furthermore, Soil-X-Change will disseminate and share innovative practices and at the end of the project the extended knowledge and innovative ideas of member and non-member OGs will be showcased to other stakeholders and farmers in an international environment.

The project is implemented by a consortium with 13 participants from 9 countries.

Global decarbonization requires radical changes in the way humanity manages the world's soil organic carbon (SOC) stocks. Yet many soil C solutions face significant credibility challenges and MRV uncertainty.

As a new generation of improved solutions transition from science demonstration scale to commercial deployment in the millions of acres, high-rigor SOC MRV will be the crux of the value creation question. The need for precise, scalable, and cost-effective soil organic carbon (SOC) stock measurement has become increasingly critical.

Voluntary carbon markets, compliance obligations such as CBAM and CRCF, and national inventories all require high-quality soil C MRV at massive scale to ensure SOC stocks are managed well, yet proximal MRV technologies which are high-rigor and low cost are sorely lacking.

Yard Stick addresses this need with an innovative in situ VisNIR probe technology designed to increase SOC stock quantification accessibility while preserving scientific integrity.

Our presentation will outline the experimental design and modeling strategies that have enabled us to approach parity between in situ VisNIR-based stock predictions and traditional laboratory-derived stock assessments. We’ll highlight results from three projects at commercial scale in the US, showcasing how a strategically sparse calibration set enabled robust carbon stock predictions. Through these case studies, we will share new insights into the unique challenges of VisNIR spectroscopy to characterize high SOC soils across different study conditions, and welcome a conversation on the soil C MRV needs of different emerging market incentives to preserve and restore SOC stocks at scale.

Unless high-rigor MRV can build a new foundation of trust in innovative new SOC solutions, business value and climate impact will be elusive. Done right, we can achieve highly credible climate benefits, improved soil and ecosystem health, and rock-solid economic value to land managers and companies along the value chain. In collaboration with its research partners, Yard Stick believes its technology offers a promising path forward for SOC MRV at scale.

Soil Health Data Cube (SHDC) (https://shdc.ai4soilhealth.eu/) is a platform for pan-European soil indicators, including Landsat-based Spectral Indices Data Cube, 30-m resolution maps of SOCD and prediction uncertainty for Europe (2000–2022) in 3D+T, 30-m resolution maps of soil types (WRB), etc. The platform serves the data and empowers zonal statistics, trend and built-up machine learning for Digital Soil Mapping. In the workshop, the participant will walk into the platform, using Jupyter Notebook to connect the cloud data catalogue, working within the small area, and derives different statistics and trend etc.

The introduction will cover the soil health data cube, its vision and its novelty. After that the workshop will be hand-on. The first part of the workshop is to link and access data from the cloud. At the second part, we will load data in time series inside a given area to the local, downloading or saving in cache. The third part is to analyse the data, derive trend, zonal statistics and generate figures and insight.

The goal in the workshop is to connect end users of the Soil health indicators with the free open source pan-European dataset. The user can keep the data and script and apply in their aftermath work to improve soil health in Europe.

Diffuse reflectance infrared spectroscopy has become an indispensable tool for rapid estimation of numerous soil health indicators and soil properties as an noninvasive alternative to the wet chemistry. With a hands-on approach, the workshop addresses topics of near infra-red fundamentals, chemometrics, sample preparation, instrumentation techniques and calibrating models predicting the basic soil health indicators. The target group of the workshop are non experts in the topic, i. e. soil managers, advisors or soil scientists. Therefore the workshop will be focused on the rapid in-situ measurement with handheld near-infrared spectrometer (example with NeoSpectra instrument) explaining what soil indicators are detectable with acceptable accuracy, good practice in spectral measurement of the soil samples in situ or in lab, i. e. user-friendly protocols developed in the AI4SoilHealth project. The core of the workshop will be practical training on how to build predictive models in R (and/or Python) using available machine learning tools and open soil spectral libraries (Open Soil Spectra Library, LUCAS etc). The lecturers will assist during the workshop to guide the participants through premade online computational notebooks. Aimed at advancing soil property estimation through fast, accurate, and cost-effective methods, this session underscores spectroscopy as a transformative tool for soil health monitoring, and environmental sustainability in general, positioning participants to integrate these methods into diverse soil-related research areas.

Reliable and affordable soil information is crucial for well-informed sustainable land management decisions related to food production, land use planning, climate change adaptation and mitigation as well soil health monitoring in Africa and abroad. The EU-H2020-funded Soils4Africa aims to provide an open-access, online soil information system (SIS) with a set of key soil health indicators and underpinning data, accompanied by a methodology for up-to-date and repeated soil monitoring across the African continent. The soil information system will become part of the knowledge and information system of FNSSA and will be hosted by an African institute.
At least 16,000 carefully selected safe agricultural locations across Africa were sampled using well-documented field campaign protocols available in different languages. All the samples are currently being analyzed for selected soil properties based on user needs including soil nutrients mostly P which does not predict very well, heavy metals, exchangeable bases, particle size distribution and pesticide residues (Wageningen University) in the ARC-Soil Climate and Water analytical laboratory in Pretoria, South Africa. All the samples are analysed with a fast, affordable, environmentally friendly, non-destructive, reproducible, and repeatable mid-infrared spectroscopy analysis. At least 20% of these samples are analyzed using wet chemistry methods for a rich, new soil spectral library and soil database. Both the spectroscopy and wet chemistry analyses follow well-documented methods as well as Standard Operating Procedures. A subset of the samples will be submitted to the Global Soil Spectral Calibration Library and Estimation Service (GSCLES) initiative to promote linkage of spectral libraries globally, to evaluate quality, to provide African coverage to the GSCLES and to provide a standardized and rich soil spectral library resource for labs in Africa that may want to start using MIR spectroscopy in future.
Preliminary results show good agreement (R2>0.70) between measured and predicted soil properties namely; organic carbon, total nitrogen, soil pH, particle size distribution, CEC and exchangeable bases among others. These are promising findings for the project and will contribute significantly to the SIS. The African-based SIS will enable policymakers, agri-businesses, scientists and other stakeholders to make well-informed decisions concerning sustainable intensification of agriculture and boosting food security.

Over the past two decades, machine learning (ML) methods have been widely applied in soil science to estimate various soil properties. Despite its successes, traditional ML methods encounter several limitations, such as high data requirements, poor generalization to new scenarios, and challenges in ensuring physically consistent predictions beyond the range of their training data. To overcome these limitations, we propose the use of physics-informed machine learning (PIML) methods, which integrate physical laws directly into the learning process to enhance model robustness and generalizability, particularly in data-limited scenarios. We demonstrate the capabilities of PIML by developing two PIML models for the estimation of two fundamental soil properties related to soil health, soil particle size distribution (PSD) and soil water retention curves (SWRC), using measured spectral reflectance data (400–2500 nm). Unlike conventional approaches, these PIML models are designed to learn non-specific continuous forms of SWRC and PSD by effectively incorporating both observational data and physical laws during training. This novel approach offers capabilities beyond those achievable with traditional methods. Specifically, the PIML model for PSD can seamlessly integrate both complete and incomplete measurements from diverse soil classification systems without requiring harmonization through interpolation of inputs, and is able to make predictions in any soil classification system. This makes the proposed approach particularly suitable for modeling PSD across datasets collected from various countries with different soil classification systems, such as at a pan-European scale. Additionally, The PIML model for SWRC can effectively handle samples with sparse or incomplete measurements, making it well-suited for SWRC datasets that often contain missing sections of the curve or limited data points. The proposed PIML approach provides a fast and cost-efficient method for monitoring fundamental soil properties to evaluate key soil health indicators. It can also be adapted for proximal sensing and digital mapping of other soil health-related properties.

The biodiversity and resilience of ecosystems are increasingly threatened by land degradation, which affects food security and climate stability drastically by reducing the overall productivity in ecosystems. It is important to identify the difference between anthropogenic degradation such as deforestation, intensive agriculture, and urbanization, and natural climate variability. In this context, Earth Observation (EO) datasets offer significant capability for the detection of land degradation patterns on a global scale and their biophysical underpinnings, and climate interactions. The purpose of this study is to utilize EO datasets to monitor land degradation, by combining a satellite-based datacube of spectral indices together with primary productivity, biophysical indicators, and climate factors. Gross Primary Productivity (GPP) is one of the fundamental indicators of how well the ecosystem is functioning and is directly related to vegetation indices, such as NDVI and EVI, and the fraction of absorbed photosynthetically active radiation (fAPAR), which together provide insight into vegetation health and biomass dynamics. The integration of climate data, particularly soil moisture, precipitation, and temperature, with productivity maps aids in differentiating the changes caused by natural climate cycles and human-induced degradation. By identifying areas where productivity declines, we can detect possible human influences in situations where climate conditions alone cannot explain the observed variations. The goal of this integrated framework is to highlight the value of EO-derived GPP and related metrics for detecting, monitoring, and managing land degradation, ultimately supporting sustainable land use policies and climate resilience efforts globally.

Maarten van Dam's story will all be around one core message: the mother of all solutions is the soil. Both from conventional farmers and regenerative farmers—but especially from investment cooperative Pymwymic —it’s about this and the urgency related with this.
The mother of all solutions is the soil. Maarten van Dam addresses this not from a biological or community perspective, but solely from a business angle.
• For Pymwymic, this means a business and impact-investing focus,
• For regenratiev farm Schevichoven it si about demonstrating financial feasibility,
• and from the more conventional agriculture side, it is a reality check grounded in existing farming practices.
Hands-on, field-based experiences, data-driven insights, and above all, the courage to balance pioneering with established practices are the key aspects that Maarten van Dam will highlight. Pymwymic operating from a €100+ million fund, Schevichven is expanding to 26 hectares of regenerative permaculture, and the Wilheminapolder is rooted in its 2000-hectare conventional arable farming operation in the Netherlands. Ultimately, this keynote will show that every step, and the support we provide, and the way we pratice, leads to a healthy and productive soil, which is essential for sustaining business in the long run.
Maarten van Dam will deliver his story straight from the heart, without the use of PowerPoint or other prepared materials. His approach will be improvised, shaped by the feedback and reactions he receives from the audience.

The forthcoming EU Soil Monitoring and resilience Law aims to ensure good soil
health across Member States by 2050. The EJP SOIL research programme has provided
critical insights to support a directive is both scientifically robust and practically feasible.
Among EU countries, 19 already have a national monitoring system, so the Soil
Monitoring should build on the existing for these countries, which emphasizes the
importance of harmonization. Critical aspects in a soil health monitoring system are the
sampling design, the choice of indicators and how targets and thresholds are set.
Sampling design across a country was shown to influence the representation of
different land-uses and soil types and in-fine, the values of indicators. Regarding
indicators, a tiered approach is proposed, which balances minimum harmonized
indicators with context-specific complementary set. A set of tier 1 indicators is
proposed, for soil biology indicators, that encompasses both functional and structural
soil biology indicators. Setting meaningful targets and thresholds is another critical
dimension. EJP SOIL proposes a decision framework that includes our approaches, based
on fixed values, reference sites, population distributions, and relative change,
depending on available data and policy goals. Such a framework provides flexibility for
national implementation while supporting EU-level reporting. Finally, harmonization
with existing systems like LUCAS Soil is essential. Rather than replacing national
protocols, EJP SOIL advocates developing transfer functions and adding new co-located
sites to align datasets, preserving long-term continuity while improving interoperability.
These lessons form a strong scientific and policy foundation to guide the Soil
Monitoring Law's development and when accepted, implementation, enabling soil
health monitoring that is scalable, policy-relevant, and which is also essential and is
being developed in several EU projects, rooted in stakeholder engagement.

In the face of a rapidly changing climate and increasing pressures on agriculture, the European food system stands at a critical juncture. Farmers are at the forefront of this challenge, and their voices are crucial to driving systemic change. This keynote will highlight the work of BENCHMARKS and especially of Climate Farmers, a pioneering initiative focused on transitioning Europe’s agri-food system toward regenerative agriculture to restore soil health, enhance biodiversity, and secure farmers’ livelihoods.

Building on real-world projects and collaborations, including our partnership with the European Alliance for Regenerative Agriculture (EARA), this talk will explore the critical role of policy, research, and innovation in driving the transformation of the agri-food system. We will emphasize the urgency of amplifying farmer-led approaches to soil regeneration and the importance of multi-stakeholder collaboration in developing durable tools, indicators, and standards for soil health across Europe. These efforts are essential not only for immediate impact but for fostering long-term resilience in our agricultural systems.

Moreover, we will delve into how stakeholders can work together to create solutions that not only address the ecological crisis but also provide tangible economic benefits to farmers. This transformation is not just about soils—it’s about the livelihoods of those who care for them. By empowering farmers as central actors in this movement, we can build a resilient, regenerative food system that benefits all.

Traditional soil science, rooted in chemical analysis, has long been the go-to method, but these techniques are often slow, require special pre-treatments, and target parameters that may offer little practical value to those managing the land. As a result, samples go to the lab, data is produced, but by the time it returns, conditions may have changed. This delay leaves managers struggling to make real-time decisions about soil health in the field—decisions that can’t wait for lengthy analysis.
Soil management is an active, time-sensitive process. Whether it’s waiting for rain to come or deciding when to irrigate, soil must be tested quickly, and the results need to be actionable immediately. Instead of complex reports that require expert interpretation, land managers need fast, reliable data that provides clear advice for their specific needs.
There are new methods for measuring soil health—many in fact—but they often output passive data that lacks meaningful interpretation or provide the wrong type of information entirely. What’s needed is a holistic, dynamic approach that spans from fast, practical soil testing to integrated, tailored solutions that account for local conditions and regulations. This approach must center around the real-world needs of land managers and farmers, providing them with the tools and insights they need to make decisions on the spot.
In this keynote, we will explore innovative, multi-level approaches to soil measurement that put the user at the centre. From rapid testing solutions to customized data interpretation, we will discuss how technology and science can meet the immediate demands of land management, ensuring that soil health decisions are both timely and impactful. Join us as we delve into the future of soil measurement and management, paving the way for more effective, real-time decision-making.