2.0 -//Pentabarf//Schedule//EN PUBLISH KDCGDG@@pretalx.earthmonitor.org -KDCGDG Ice breaker en en 20230827T170000 20230827T200000 3.00000

Ice breaker

Ice breaker Ice breaker Ice breaker Ice breaker PUBLIC CONFIRMED Social event https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/KDCGDG/ Other locations PUBLISH SAUGBJ@@pretalx.earthmonitor.org -SAUGBJ Plenary introduction, including introduction to the hackathons en en 20230828T090000 20230828T103000 1.03000

Plenary introduction, including introduction to the hackathons

Plenary introduction, including an introduction of the lecturers PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/SAUGBJ/ Room 21 (Sala 21) PUBLISH 7JN3FV@@pretalx.earthmonitor.org -7JN3FV Tidy geographic data with sf, dplyr, ggplot2, geos and friends (part 1) en en 20230828T110000 20230828T123000 1.03000

Tidy geographic data with sf, dplyr, ggplot2, geos and friends (part 1)

This lecture will provide an introduction to working with geographic data using R in a ‘tidy’ way. It will focus on using the sf package to read, write, manipulate, and plot geographic data in combination with the tidyverse metapackage. Why use the sf package with the tidyverse? The lecture will outline some of the ideas underlying the tidyverse and how they can speed-up data analysis pipelines, while making data analysis code easier to read and write. We will see how the following lines library(sf) library(tidyverse) can provide a foundation on which the many geographic data analysis problems can be solved. The lecture will also cover on more recently developed packages that integrate with the tidyverse to a greater and lesser extent. We will look at how the geos package, which provides a simple and high-performance interface to the GEOS library for performing geometric operations on geographic data, integrates with the tidyverse. The tidyverse is not the right tool for every data analysis task and we touch on alternatives for working with raster data, with reference to the terra package, and alternative frameworks such as data.table. Finally, we will also look at how the ‘tidy’ philosophy could be implemented in other programming languages, such as Python. The focus throughout will be on practical skills and using packages effectively within the wider context of project management tools, integrated development environments (we recommend VS Code with appropriate extensions or RStudio), and version control systems. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/7JN3FV/ Room 21 (Sala 21) Robin Lovelace PUBLISH XPBVY3@@pretalx.earthmonitor.org -XPBVY3 Tidy geographic data with sf, dplyr, ggplot2, geos and friends (part 2) en en 20230828T133000 20230828T150000 1.03000

Tidy geographic data with sf, dplyr, ggplot2, geos and friends (part 2)

This lecture will provide an introduction to working with geographic data using R in a ‘tidy’ way. It will focus on using the sf package to read, write, manipulate, and plot geographic data in combination with the tidyverse metapackage. Why use the sf package with the tidyverse? The lecture will outline some of the ideas underlying the tidyverse and how they can speed-up data analysis pipelines, while making data analysis code easier to read and write. We will see how the following lines library(sf) library(tidyverse) can provide a foundation on which the many geographic data analysis problems can be solved. The lecture will also cover on more recently developed packages that integrate with the tidyverse to a greater and lesser extent. We will look at how the geos package, which provides a simple and high-performance interface to the GEOS library for performing geometric operations on geographic data, integrates with the tidyverse. The tidyverse is not the right tool for every data analysis task and we touch on alternatives for working with raster data, with reference to the terra package, and alternative frameworks such as data.table. Finally, we will also look at how the ‘tidy’ philosophy could be implemented in other programming languages, such as Python. The focus throughout will be on practical skills and using packages effectively within the wider context of project management tools, integrated development environments (we recommend VS Code with appropriate extensions or RStudio), and version control systems. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/XPBVY3/ Room 21 (Sala 21) Robin Lovelace PUBLISH DBXBQG@@pretalx.earthmonitor.org -DBXBQG Hackathon workshop en en 20230828T153000 20230828T161500 0.04500

Hackathon workshop

Spatial data processing is an essential part of modern data analysis. In the course of the summer school, you will learn many new tools and techniques to process spatial data. However, you really only know something if you implement it in a concrete situation. For this reason, we are conducting a hackathon during the summer school. You can choose between two topics and apply all the state of the art skills you are learning during the week. To help you better understand the question and relevant domain, we will present the topics in an introductory workshop which will help get you started with the task and the submission process. By participating, you will learn how spatial data analysis can be applied to solve real-world problems. You will gain practical skills in using the tools and techniques to analyse, interpret and model spatial data, and to use this knowledge in your respective field. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/DBXBQG/ Room 21 (Sala 21) Deleted User Nils Ratnaweera PUBLISH RLZK7K@@pretalx.earthmonitor.org -RLZK7K Research Speed Dating en en 20230828T161500 20230828T174500 1.03000

Research Speed Dating

Pre-order the group by their broader interest into subgroups. Split each subgroup equally where one half will be stationary and the other half be moving “clockwise” through the room. Pairs of people sit down for a given amount of time (~7 mins) and present their research topic to each other. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/RLZK7K/ Room 21 (Sala 21) PUBLISH W3998X@@pretalx.earthmonitor.org -W3998X Introduction to working with spatial data in Python (part 1) en en 20230828T110000 20230828T123000 1.03000

Introduction to working with spatial data in Python (part 1)

Python is an extremely popular general-purpose programming language. It is used in a wide range of settings and for various purposes, including for spatial data processing and analysis. The aim of this tutorial is to give an introduction to methods of working with spatial data using Python. The tutorial will be split into two parts, introducing two central Python packages: * `geopandas`---For working with vector layers * `rasterio`---For working with rasters The tutorial will demonstrate typical basic workflows of processing spatial data: data input, processing, geo-computation, and exporting of the results. We will use realistic datasets, such as GTFS public transport data and remote sensing products. By the end of the tutorial, the participants will be able to: * Import spatial data from files * Subset and process the data * Graphically display the data * Perform spatial calculations (such as calculating distances, or applying raster algebra operators) * Export the results To follow along and reproduce the results on your own computer, the prerequisite is to be able to run Python code in a Jupyter Notebook interface, linked to a Python environment with the two above-mentioned packages installed. Instructions will be sent in advance. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/W3998X/ Room 18 (Sala 18) Michael Dorman PUBLISH PMARL3@@pretalx.earthmonitor.org -PMARL3 Introduction to working with spatial data in Python (part 2) en en 20230828T133000 20230828T150000 1.03000

Introduction to working with spatial data in Python (part 2)

Python is an extremely popular general-purpose programming language. It is used in a wide range of settings and for various purposes, including for spatial data processing and analysis. The aim of this tutorial is to give an introduction to methods of working with spatial data using Python. The tutorial will be split into two parts, introducing two central Python packages: * `geopandas`---For working with vector layers * `rasterio`---For working with rasters The tutorial will demonstrate typical basic workflows of processing spatial data: data input, processing, geo-computation, and exporting of the results. We will use realistic datasets, such as GTFS public transport data and remote sensing products. By the end of the tutorial, the participants will be able to: * Import spatial data from files * Subset and process the data * Graphically display the data * Perform spatial calculations (such as calculating distances, or applying raster algebra operators) * Export the results To follow along and reproduce the results on your own computer, the prerequisite is to be able to run Python code in a Jupyter Notebook interface, linked to a Python environment with the two above-mentioned packages installed. Instructions will be sent in advance. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/PMARL3/ Room 18 (Sala 18) Michael Dorman PUBLISH HBWCDX@@pretalx.earthmonitor.org -HBWCDX Raster and vector data cubes in R (part 1) en en 20230829T090000 20230829T103000 1.03000

Raster and vector data cubes in R (part 1)

A common challenge with raster datasets is not only that they come in large files (single Sentinel-2 tiles are around 1 GB), but that many of these files, potentially thousands or millions, are needed to address the area and time period of interest. In 2022, Copernicus, the program that runs all Sentinel satellites, published 160 TB of images per day. This means that a classic pattern in using R consisting of downloading data to local disc, loading the data in memory, and analysing it is not going to work. This lectures describes how large spatial and spatiotemporal datasets can be handled with R, with a focus on packages **sf** and **stars**. For practical use, we classify large datasets as too large: - to fit in working memory, - to fit on the local hard drive, or - to download to locally managed infrastructure (such as network attached storage) These three categories may (today) correspond very roughly to Gigabyte-, Terabyte- and Petabyte-sized datasets. Besides size considerations, access and processing speed also play a role, in particular for larger datasets or interactive applications. Cloud native geospatial formats are formats optimised with processing on cloud infrastructure in mind, where costs of computing and storage need to be considered and optimised. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/HBWCDX/ Room 21 (Sala 21) Edzer Pebesma PUBLISH YZHQQS@@pretalx.earthmonitor.org -YZHQQS Raster and vector data cubes in R (part 2) en en 20230829T110000 20230829T123000 1.03000

Raster and vector data cubes in R (part 2)

A common challenge with raster datasets is not only that they come in large files (single Sentinel-2 tiles are around 1 GB), but that many of these files, potentially thousands or millions, are needed to address the area and time period of interest. In 2022, Copernicus, the program that runs all Sentinel satellites, published 160 TB of images per day. This means that a classic pattern in using R consisting of downloading data to local disc, loading the data in memory, and analysing it is not going to work. This lectures describes how large spatial and spatiotemporal datasets can be handled with R, with a focus on packages **sf** and **stars**. For practical use, we classify large datasets as too large: - to fit in working memory, - to fit on the local hard drive, or - to download to locally managed infrastructure (such as network attached storage) These three categories may (today) correspond very roughly to Gigabyte-, Terabyte- and Petabyte-sized datasets. Besides size considerations, access and processing speed also play a role, in particular for larger datasets or interactive applications. Cloud native geospatial formats are formats optimised with processing on cloud infrastructure in mind, where costs of computing and storage need to be considered and optimised. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/YZHQQS/ Room 21 (Sala 21) Edzer Pebesma PUBLISH DDABRT@@pretalx.earthmonitor.org -DDABRT Unsupervised classification (clustering) of satellite images (part 1) en en 20230829T133000 20230829T150000 1.03000

Unsupervised classification (clustering) of satellite images (part 1)

Unsupervised classification of satellite images is the process of grouping similar pixels on an image into homogeneous clusters based primarily on their spectral characteristics. This approach does not require reference (labeled) data, unlike supervised classification, therefore it can be used as a method of first choice. Satellite image classification is commonly used in a variety of fields, including environmental monitoring, land cover mapping, and disaster management. The generated thematic maps can be used to identify and monitor changes in land use, and assess the impact of natural disasters. During this workshop, participants will gain practical knowledge and skills to perform unsupervised classification of Landsat data using the R language. It will be demonstrated step by step how to use and prepare raster data for analysis, popular grouping methods will be discussed and finally we will prepare a land cover map with interpretation of the results. The workshop will also cover the challenges and limitations of unsupervised classification, such as subjective interpretation of results difficulty of selecting the optimal number of clusters, and validation methods for ensuring the accuracy and reliability of results. The workshop is aimed at beginners, but basic knowledge of GIS and satellite remote sensing is required. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/DDABRT/ Room 21 (Sala 21) Deleted User PUBLISH WN9LGG@@pretalx.earthmonitor.org -WN9LGG Unsupervised classification (clustering) of satellite images (part 2) en en 20230829T153000 20230829T170000 1.03000

Unsupervised classification (clustering) of satellite images (part 2)

Unsupervised classification of satellite images is the process of grouping similar pixels on an image into homogeneous clusters based primarily on their spectral characteristics. This approach does not require reference (labeled) data, unlike supervised classification, therefore it can be used as a method of first choice. Satellite image classification is commonly used in a variety of fields, including environmental monitoring, land cover mapping, and disaster management. The generated thematic maps can be used to identify and monitor changes in land use, and assess the impact of natural disasters. During this workshop, participants will gain practical knowledge and skills to perform unsupervised classification of Landsat data using the R language. It will be demonstrated step by step how to use and prepare raster data for analysis, popular grouping methods will be discussed and finally we will prepare a land cover map with interpretation of the results. The workshop will also cover the challenges and limitations of unsupervised classification, such as subjective interpretation of results difficulty of selecting the optimal number of clusters, and validation methods for ensuring the accuracy and reliability of results. The workshop is aimed at beginners, but basic knowledge of GIS and satellite remote sensing is required. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/WN9LGG/ Room 21 (Sala 21) Deleted User PUBLISH JEV9XU@@pretalx.earthmonitor.org -JEV9XU Hackathons (consultations) en en 20230829T170000 20230829T183000 1.03000

Hackathons (consultations)

Spatial data processing is an essential part of modern data analysis. In the course of the summer school, you will learn many new tools and techniques to process spatial data. However, you really only know something if you implement it in a concrete situation. For this reason, we are conducting a hackathon during the summer school. You can choose between two topics and apply all the state of the art skills you are learning during the week. To help you better understand the question and relevant domain, we will present the topics in an introductory workshop which will help get you started with the task and the submission process. By participating, you will learn how spatial data analysis can be applied to solve real-world problems. You will gain practical skills in using the tools and techniques to analyse, interpret and model spatial data, and to use this knowledge in your respective field. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/JEV9XU/ Room 21 (Sala 21) Deleted User Nils Ratnaweera PUBLISH N338TW@@pretalx.earthmonitor.org -N338TW Processing geospatial data using JuliaGeo framework (Julia tutorial) (part 1) en en 20230829T090000 20230829T103000 1.03000

Processing geospatial data using JuliaGeo framework (Julia tutorial) (part 1)

Julia is a programming language that is simple to write and scriptable like Python and R, but fast like C or C++. At 10 years, it’s a young language, so the ecosystem isn’t as large and mature as you want it to be. Maarten Pronk was an early adopter of the language in his research at Deltares, a Dutch research institute. In this lecture(s) he will introduce Julia, his motivation to use it and his OSS journey. Half of the lecture will be non-spatial, while the latter half will focus on the JuliaGeo ecosystem and showcased some of the possibilities of the Julia language. The JuliaGeo GitHub organization is intended primarily for the collaborative development of packages that are generally applicable across the geospatial and geosciences domains. For dealing with geospatial data, packages from the JuliaGeometry and JuliaImages organizations may also be of interest, and we will aim for good integration with those. Since the JuliaGeo organization aims to provide mostly general tools, more domain specific packages may be better suited for development in domain specific organizations. JuliaClimate is a nice example of such an organization that will be especially interesting to climate, atmosphere and ocean scientists. EcoJulia also provides some tools for generating and downloading spatial data sets, with a focus on ecological applications. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/N338TW/ Room 18 (Sala 18) Maarten Pronk PUBLISH H8PAZC@@pretalx.earthmonitor.org -H8PAZC Processing geospatial data using JuliaGeo framework (Julia tutorial) (part 2) en en 20230829T110000 20230829T123000 1.03000

Processing geospatial data using JuliaGeo framework (Julia tutorial) (part 2)

Julia is a programming language that is simple to write and scriptable like Python and R, but fast like C or C++. At 10 years, it’s a young language, so the ecosystem isn’t as large and mature as you want it to be. Maarten Pronk was an early adopter of the language in his research at Deltares, a Dutch research institute. In this lecture(s) he will introduce Julia, his motivation to use it and his OSS journey. Half of the lecture will be non-spatial, while the latter half will focus on the JuliaGeo ecosystem and showcased some of the possibilities of the Julia language. The JuliaGeo GitHub organization is intended primarily for the collaborative development of packages that are generally applicable across the geospatial and geosciences domains. For dealing with geospatial data, packages from the JuliaGeometry and JuliaImages organizations may also be of interest, and we will aim for good integration with those. Since the JuliaGeo organization aims to provide mostly general tools, more domain specific packages may be better suited for development in domain specific organizations. JuliaClimate is a nice example of such an organization that will be especially interesting to climate, atmosphere and ocean scientists. EcoJulia also provides some tools for generating and downloading spatial data sets, with a focus on ecological applications. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/H8PAZC/ Room 18 (Sala 18) Maarten Pronk PUBLISH FZNK8J@@pretalx.earthmonitor.org -FZNK8J Progress in modernizing and replacing infrastructure packages in R-spatial workflows en en 20230829T133000 20230829T150000 1.03000

Progress in modernizing and replacing infrastructure packages in R-spatial workflows

Until June 2023, maintainers of legacy packages using rgdal, rgeos and/or maptools were encouraged to migrate to sf/stars or terra, as described in https://github.com/r-spatial/evolution and blogs listed there: https://r-spatial.org/r/2022/04/12/evolution.html, https://r-spatial.org/r/2022/12/14/evolution2.html, https://r-spatial.org/r/2023/04/10/evolution3.html. In June 2023, sp switches from using rgdal by default for sp::CRS and sp::spTransform to using sf functionality by default. From October 2023, retiring packages rgdal, rgeos and maptools will be archived on CRAN. This means that residual installations of retiring packages will continue for R 4.2 and R 4.3, but will not be updated after October 2023, nor will they be available for R 4.4. The workshop will present current status, and may assist participants with affected workflows to adapt; the same applies to key affected packages needed in participants' workflows. Participants are invited to contact the presenter with practical ideas to packages to adapt, and time may also be used to prepare non-maintainer update candidates for non-responsive packages. The count of affected packages was over 800, but the severity of the impact of the withdrawal of the retiring packages varies by the dependency category, strong dependence as Depends or Imports, weak dependence as Suggests. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/FZNK8J/ Room 18 (Sala 18) Roger Bivand PUBLISH TATSS7@@pretalx.earthmonitor.org -TATSS7 Progress in modernizing and replacing infrastructure packages in R-spatial workflows en en 20230829T153000 20230829T170000 1.03000

Progress in modernizing and replacing infrastructure packages in R-spatial workflows

Until June 2023, maintainers of legacy packages using rgdal, rgeos and/or maptools were encouraged to migrate to sf/stars or terra, as described in https://github.com/r-spatial/evolution and blogs listed there: https://r-spatial.org/r/2022/04/12/evolution.html, https://r-spatial.org/r/2022/12/14/evolution2.html, https://r-spatial.org/r/2023/04/10/evolution3.html. In June 2023, sp switches from using rgdal by default for sp::CRS and sp::spTransform to using sf functionality by default. From October 2023, retiring packages rgdal, rgeos and maptools will be archived on CRAN. This means that residual installations of retiring packages will continue for R 4.2 and R 4.3, but will not be updated after October 2023, nor will they be available for R 4.4. The workshop will present current status, and may assist participants with affected workflows to adapt; the same applies to key affected packages needed in participants' workflows. Participants are invited to contact the presenter with practical ideas to packages to adapt, and time may also be used to prepare non-maintainer update candidates for non-responsive packages. The count of affected packages was over 800, but the severity of the impact of the withdrawal of the retiring packages varies by the dependency category, strong dependence as Depends or Imports, weak dependence as Suggests. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/TATSS7/ Room 18 (Sala 18) Roger Bivand PUBLISH NEVMZ3@@pretalx.earthmonitor.org -NEVMZ3 Short excursion en en 20230829T171500 20230829T194500 2.03000

Short excursion

The event includes seeing a large excavated meteorite in the in-place museum and then a 2-hour trip to the meteorite craters in the Morasko Preserve. PUBLIC CONFIRMED Short excursion https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/NEVMZ3/ Other locations PUBLISH XCVDSS@@pretalx.earthmonitor.org -XCVDSS Cloud-based analysis of Earth Observation data using openEO Platform, R and Python (part 1) en en 20230830T090000 20230830T103000 1.03000

Cloud-based analysis of Earth Observation data using openEO Platform, R and Python (part 1)

openEO Platform holds a large amount of free and open as well as commercial Earth Observation (EO) data which can be accessed and analysed with openEO, an open API that enables cloud computing and EO data access in a unified and reproducible way. Additionally, client libraries are available in R, Python and Javascript. A JupterLab environment and the Web Editor, a graphical interface, allow a direct and interactive development of processing workflows. The platform is developed with a strong user focus and various use cases have been implemented to illustrate the platform capabilities. Currently, three federated backends support the analysis of EO data from pixel to continental scale. The future evolution of openEO Platform in terms of data availability and processing capabilities closely linked to community requirements, facilitated by feature requests from users who design their workflows for environmental monitoring and reproducible research purposes. This presentation provides an overview of the completed use cases, the newly added functionalities such as user code sharing, and user interface updates based on the new use cases and user requests. openEO Platform exemplifies how the processing and analysing large amounts of EO data to meaningful information products is becoming easier and largely compliant with FAIR data principles supporting the EO community at large. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/XCVDSS/ Room 21 (Sala 21) Edzer Pebesma PUBLISH A8UFQA@@pretalx.earthmonitor.org -A8UFQA Cloud-based analysis of Earth Observation data using openEO Platform, R and Python (part 2) en en 20230830T110000 20230830T123000 1.03000

Cloud-based analysis of Earth Observation data using openEO Platform, R and Python (part 2)

openEO Platform holds a large amount of free and open as well as commercial Earth Observation (EO) data which can be accessed and analysed with openEO, an open API that enables cloud computing and EO data access in a unified and reproducible way. Additionally, client libraries are available in R, Python and Javascript. A JupterLab environment and the Web Editor, a graphical interface, allow a direct and interactive development of processing workflows. The platform is developed with a strong user focus and various use cases have been implemented to illustrate the platform capabilities. Currently, three federated backends support the analysis of EO data from pixel to continental scale. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/A8UFQA/ Room 21 (Sala 21) Edzer Pebesma PUBLISH 7BDZSY@@pretalx.earthmonitor.org -7BDZSY Environmental analysis using satellite image time series (part 1) en en 20230830T133000 20230830T150000 1.03000

Environmental analysis using satellite image time series (part 1)

Satellite imagery time series offer a powerful means to detect and analyze both short- and long-term changes in the environment. In particular, the availability of open-access data from missions like Landsat (since 1972) and Sentinel (since 2015) has significantly enhanced our ability to study these changes. This workshop aims to explore the use of time series of indices derived from satellite imagery for analyzing various types of land cover changes using the programming language R. The workshop will cover essential preprocessing steps, including outlier removal and handling missing observations, to ensure the quality of the data. Participants will learn how to effectively model time series using different methods. Additionally, the workshop will provide insights into detecting trends and breaks within the time series data. The analysis will focus on a range of objects and encompass both abrupt and gradual changes. Examples of the types of changes that will be explored include urban growth or vegetation succession. The repository fot this workshop: https://github.com/egrabska/OGH2023 And the instructions for this workshop are here: https://egrabska.github.io/OGH2023/ However, this repository may be also useful for dealing with other time series, not only satellite imagery! PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/7BDZSY/ Room 21 (Sala 21) Ewa Grabska-Szwagrzyk PUBLISH PES8RJ@@pretalx.earthmonitor.org -PES8RJ Environmental analysis using satellite image time series (part 2) en en 20230830T153000 20230830T170000 1.03000

Environmental analysis using satellite image time series (part 2)

Satellite imagery time series offer a powerful means to detect and analyze both short- and long-term changes in the environment. In particular, the availability of open-access data from missions like Landsat (since 1972) and Sentinel (since 2015) has significantly enhanced our ability to study these changes. This workshop aims to explore the use of time series of indices derived from satellite imagery for analyzing various types of land cover changes using the programming language R. The workshop will cover essential preprocessing steps, including outlier removal and handling missing observations, to ensure the quality of the data. Participants will learn how to effectively model time series using different methods. Additionally, the workshop will provide insights into detecting trends and breaks within the time series data. The analysis will focus on a range of objects and encompass both abrupt and gradual changes. Examples of the types of changes that will be explored include urban growth or vegetation succession. The repository fot this workshop: https://github.com/egrabska/OGH2023 And the instructions for this workshop are here: https://egrabska.github.io/OGH2023/ However, this repository may be also useful for dealing with other time series, not only satellite imagery! PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/PES8RJ/ Room 21 (Sala 21) Ewa Grabska-Szwagrzyk PUBLISH ZQWFQQ@@pretalx.earthmonitor.org -ZQWFQQ Discussion panel: What can R, Python, and Julia development communities do to combat the climate crisis? en en 20230830T171500 20230830T184500 1.03000

Discussion panel: What can R, Python, and Julia development communities do to combat the climate crisis?

What can R, Python, and Julia development communities do to combat the climate crisis. Let’s explore solutions, together with leading experts in each programming language. Join this interactive discussion, ask us your questions, and answer ours online! During this year’s discussion forum, we will have the pleasure to listen to expert presentations by Anita Graser, Spatial data scientist, Austrian Institute of Technology in Vienna Edzer Pebesma, Director of the Institute for Geoinformatics, University of Münster Maarten Pronk, GeoData Scientist, Deltares Lorena Abad, Researcher at Z_GIS – Department of Geoinformatics, University of Salzburg Tomislav Hengl, Data Scientist and Technical Director of OpenGeoHub Foundation PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/ZQWFQQ/ Room 21 (Sala 21) PUBLISH 8QXTGE@@pretalx.earthmonitor.org -8QXTGE Parallelization of geoprocessing workflows in GRASS GIS and Python (part 1) en en 20230830T090000 20230830T103000 1.03000

Parallelization of geoprocessing workflows in GRASS GIS and Python (part 1)

High-resolution, continental-scale modeling enabled by modern, massive datasets, requires development of scalable geoprocessing workflows. To enable participants to effectively use available computational resources (laptop, desktop, institutional HPC), we will introduce basic parallelization concepts such as parallelization efficiency and scaling. We will explain various approaches to parallelization in GRASS GIS, an open source geoprocessing engine, that rely on OpenMP, Python and Bash. In the hands-on part, participants will speed up an urban growth model by parallelizing different parts of this complex geoprocessing workflow using techniques that are easily applicable to a wide range of analyses and computational resources. The workshop will be running in a Jupyter Notebook environment using GRASS GIS Python API to run GRASS tools and visualize results of the analysis in a reproducible way. Participants will be able to either run the workshop on their laptops (see instructions) or in a cloud environment (using WholeTale, no installation required). PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/8QXTGE/ Room 18 (Sala 18) Caitlin Haedrich Anna Petrasova PUBLISH 3RARUC@@pretalx.earthmonitor.org -3RARUC Parallelization of geoprocessing workflows in GRASS GIS and Python (part 2) en en 20230830T110000 20230830T123000 1.03000

Parallelization of geoprocessing workflows in GRASS GIS and Python (part 2)

High-resolution, continental-scale modeling enabled by modern, massive datasets, requires development of scalable geoprocessing workflows. To enable participants to effectively use available computational resources (laptop, desktop, institutional HPC), we will introduce basic parallelization concepts such as parallelization efficiency and scaling. We will explain various approaches to parallelization in GRASS GIS, an open source geoprocessing engine, that rely on OpenMP, Python and Bash. In the hands-on part, participants will speed up an urban growth model by parallelizing different parts of this complex geoprocessing workflow using techniques that are easily applicable to a wide range of analyses and computational resources. The workshop will be running in a Jupyter Notebook environment using GRASS GIS Python API to run GRASS tools and visualize results of the analysis in a reproducible way. Participants will be able to either run the workshop on their laptops (see instructions) or in a cloud environment (using WholeTale, no installation required). PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/3RARUC/ Room 18 (Sala 18) Caitlin Haedrich PUBLISH HFXFCB@@pretalx.earthmonitor.org -HFXFCB xcube for spatiotemporal data analysis and visualization (part 1) en en 20230830T133000 20230830T150000 1.03000

xcube for spatiotemporal data analysis and visualization (part 1)

xcube is an open-source xarray-based Python package and toolkit that has been developed to provide Earth observation (EO) data in an analysis-ready form to users. xcube achieves this by carefully converting EO data sources into self-contained data cubes that can be published in the cloud. In this session you will learn about the ecosystem around xcube, which allows to access different data sources and turning the inputs into data cubes. These data cubes can then be easily used for spatiotemporal data analysis and visualization. After a brief introduction about the software components, we will go step by step though some example Jupyter notebooks and finally we will dive into a hands-on session with a little challenge. For the session you will need a laptop with an internet connection, some basic knowledge about Python and already installed miniconda (https://docs.conda.io/en/latest/miniconda.html) which is used to download the necessary Python packages for the session. Prior experience with Jupyter notebooks will be helpful, but not mandatory. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/HFXFCB/ Room 18 (Sala 18) Alicja Balfanz PUBLISH 37CK9C@@pretalx.earthmonitor.org -37CK9C xcube for spatiotemporal data analysis and visualization (part 2) en en 20230830T153000 20230830T170000 1.03000

xcube for spatiotemporal data analysis and visualization (part 2)

xcube is an open-source xarray-based Python package and toolkit that has been developed to provide Earth observation (EO) data in an analysis-ready form to users. xcube achieves this by carefully converting EO data sources into self-contained data cubes that can be published in the cloud. In this session you will learn about the ecosystem around xcube, which allows to access different data sources and turning the inputs into data cubes. These data cubes can then be easily used for spatiotemporal data analysis and visualization. After a brief introduction about the software components, we will go step by step though some example Jupyter notebooks and finally we will dive into a hands-on session with a little challenge. For the session you will need a laptop with an internet connection, some basic knowledge about Python and already installed miniconda (https://docs.conda.io/en/latest/miniconda.html) which is used to download the necessary Python packages for the session. Prior experience with Jupyter notebooks will be helpful, but not mandatory. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/37CK9C/ Room 18 (Sala 18) Alicja Balfanz PUBLISH RFXDZW@@pretalx.earthmonitor.org -RFXDZW Spatial ML model assessment and interpretation (part 1) en en 20230831T090000 20230831T103000 1.03000

Spatial ML model assessment and interpretation (part 1)

While significant progress has been made towards explaining black-box machine-learning (ML) models, there is still a distinct lack of diagnostic tools that elucidate the spatial behaviour of ML models in terms of predictive skill and variable importance. This contribution proposes spatial prediction error profiles (SPEPs) and spatial variable importance profiles (SVIPs) as novel model-agnostic assessment and interpretation tools for spatial prediction models with a focus on prediction distance. Their suitability is demonstrated in two case studies representing a regionalization task in an environmental-science context, and a classification task from remotely-sensed land cover classification. In these case studies, the SPEPs and SVIPs of geostatistical methods, linear models, random forest, and hybrid algorithms show striking differences but also relevant similarities. Limitations of related cross-validation techniques are outlined, and the case is made that modelers should focus their model assessment and interpretation on the intended spatial prediction horizon. The range of autocorrelation, in contrast, is not a suitable criterion for defining spatial cross-validation test sets. The novel diagnostic tools enrich the toolkit of spatial data science, and may improve ML model interpretation, selection, and design. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/RFXDZW/ Room 21 (Sala 21) Alexander Brenning PUBLISH GNBK8S@@pretalx.earthmonitor.org -GNBK8S Spatial ML model assessment and interpretation (part 2) en en 20230831T110000 20230831T123000 1.03000

Spatial ML model assessment and interpretation (part 2)

While significant progress has been made towards explaining black-box machine-learning (ML) models, there is still a distinct lack of diagnostic tools that elucidate the spatial behaviour of ML models in terms of predictive skill and variable importance. This contribution proposes spatial prediction error profiles (SPEPs) and spatial variable importance profiles (SVIPs) as novel model-agnostic assessment and interpretation tools for spatial prediction models with a focus on prediction distance. Their suitability is demonstrated in two case studies representing a regionalization task in an environmental-science context, and a classification task from remotely-sensed land cover classification. In these case studies, the SPEPs and SVIPs of geostatistical methods, linear models, random forest, and hybrid algorithms show striking differences but also relevant similarities. Limitations of related cross-validation techniques are outlined, and the case is made that modelers should focus their model assessment and interpretation on the intended spatial prediction horizon. The range of autocorrelation, in contrast, is not a suitable criterion for defining spatial cross-validation test sets. The novel diagnostic tools enrich the toolkit of spatial data science, and may improve ML model interpretation, selection, and design. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/GNBK8S/ Room 21 (Sala 21) Alexander Brenning PUBLISH HR3RWF@@pretalx.earthmonitor.org -HR3RWF Tools and packages to query and process Sentinel-1 and Sentinel-2 data with R and Python (part 1) en en 20230831T133000 20230831T150000 1.03000

Tools and packages to query and process Sentinel-1 and Sentinel-2 data with R and Python (part 1)

This session focuses on the products from the ESA Copernicus program Sentinel-1 and Sentinel-2. These products can be freely accessed in several manners and through different portals. We will take a look at packages to query the data you need for your analyses using Python and R, switching between platforms when relevant. An introduction on how to process Sentinel data with both platforms will also be covered focusing on the particularities of the sensors. For Sentinel-1 data access, we will use the [ASF Data Service](https://search.asf.alaska.edu/) to query data. There is no need for credentials for querying the data but if you want to try the downloading steps, you will need [Earthdata Login](https://urs.earthdata.nasa.gov/) credentials. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/HR3RWF/ Room 21 (Sala 21) Lorena Abad PUBLISH RYXWKQ@@pretalx.earthmonitor.org -RYXWKQ Introduction to "City, location-based, game" en en 20230831T151500 20230831T153000 0.01500

Introduction to "City, location-based, game"

Michal will explain the rules and give you all the materials needed to participate. You will be divided into random groups of 5-6 people. The introduction will take 15 min. If you want to join and you haven't declared this - come and join us, we have one spare group just for you. PUBLIC CONFIRMED Social event https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/RYXWKQ/ Room 21 (Sala 21) PUBLISH 9NUVKY@@pretalx.earthmonitor.org -9NUVKY Mapping explanation - Python toolchaing for spatial interpretative machine learning (part 1) en en 20230831T090000 20230831T103000 1.03000

Mapping explanation - Python toolchaing for spatial interpretative machine learning (part 1)

The course will present applications of interpretive machine learning methods to geospatial analysis. Interpretive machine learning is a new branch of machine learning that allows the decomposition of black box models. It allows complex, non-linear models to explain the criteria that lead to a result. In the case of geospatial data, it can be used to search for patterns of spatial explanatory factors. The course covers the entire toolchain from data preparation, model training, and the data transformation process, through data analysis and interpretation of the results, to spatial visualization. The toolchain includes tools such as the shap library, selected components of the scikit-learn, geopandas, and matplotlib packages. The course includes a theoretical introduction to interpretive machine learning and how it can be applied to geospatial data. The practical part is built around analysing the U.S. presidential election results Clinton vs. Trump. In the first step, explanatory variables are collected and transformed into `shapely numbers`. The data transformed in this way will determine the relevance of the explanatory variables and their actual impact on the election outcome in each county. The advantage of shapely numbers is that the variables are automatically weighted, allowing for efficient clustering. The shapely numbers and their clustering results reveal interesting spatial patterns in the electoral process. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/9NUVKY/ Room 18 (Sala 18) Jarek Jasiewicz PUBLISH KEWCDZ@@pretalx.earthmonitor.org -KEWCDZ Mapping explanation - Python toolchaing for spatial interpretative machine learning (part 2) en en 20230831T110000 20230831T123000 1.03000

Mapping explanation - Python toolchaing for spatial interpretative machine learning (part 2)

The course will present applications of interpretive machine learning methods to geospatial analysis. Interpretive machine learning is a new branch of machine learning that allows the decomposition of black box models. It allows complex, non-linear models to explain the criteria that lead to a result. In the case of geospatial data, it can be used to search for patterns of spatial explanatory factors. The course covers the entire toolchain from data preparation, model training, and the data transformation process, through data analysis and interpretation of the results, to spatial visualization. The toolchain includes tools such as the shap library, selected components of the scikit-learn, geopandas, and matplotlib packages. The course includes a theoretical introduction to interpretive machine learning and how it can be applied to geospatial data. The practical part is built around analysing the U.S. presidential election results Clinton vs. Trump. In the first step, explanatory variables are collected and transformed into `shapely numbers`. The data transformed in this way will determine the relevance of the explanatory variables and their actual impact on the election outcome in each county. The advantage of shapely numbers is that the variables are automatically weighted, allowing for efficient clustering. The shapely numbers and their clustering results reveal interesting spatial patterns in the electoral process. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/KEWCDZ/ Room 18 (Sala 18) Jarek Jasiewicz PUBLISH YKZKSA@@pretalx.earthmonitor.org -YKZKSA Data engineering for Mobility Data Science (with Python and DVC) en en 20230831T133000 20230831T150000 1.03000

Data engineering for Mobility Data Science (with Python and DVC)

This session introduces [MovingPandas](https://movingpandas.org) and [DVC](https://dvc.org) for Mobility Data Science. MovingPandas is a Python library for the analysis and visualization of movement data. It is built on top of GeoPandas and provides functions to analyze, manipulate and plot trajectories. To get a better idea of the type of analytics that MovingPandas supports, visit: https://movingpandas.org/examples DVC is a data version control (and machine learning experiment tracking) library. It follows a similar logic to source code version control systems (such as Git) and is typically used together with Git to keep track of data and experiments while Git keeps track of the source code. In this session, we will use DVC to keep track of our movement data analytics workflow. Participants are expected to come prepared with a working MovingPandas & DVC Python environment. Basic previous experience with (Geo)Pandas and version control systems (i.e. how pull, commit, push works in Git) is expected. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/YKZKSA/ Room 18 (Sala 18) Anita Graser PUBLISH 7UQJMV@@pretalx.earthmonitor.org -7UQJMV City, location-based, game en en 20230831T160000 20230831T180000 2.00000

City, location-based, game

A city (location-based) game after the regular summer school workshops on Thursday, August 31st. It will happen in the Poznan city center between 4:00 and 6:00 PM. We cannot share more details, but it will definitely be fun. PUBLIC CONFIRMED Social event https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/7UQJMV/ Other locations PUBLISH KB3U8T@@pretalx.earthmonitor.org -KB3U8T Happy hour en en 20230831T180000 20230831T210000 3.00000

Happy hour

Drinks and light snacks in a pub in the city center PUBLIC CONFIRMED Social event https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/KB3U8T/ Other locations PUBLISH HPDNL9@@pretalx.earthmonitor.org -HPDNL9 Tools and packages to query and process Sentinel-1 and Sentinel-2 data with R and Python (part 2) en en 20230901T090000 20230901T103000 1.03000

Tools and packages to query and process Sentinel-1 and Sentinel-2 data with R and Python (part 2)

This session focuses on the products from the ESA Copernicus program Sentinel-1 and Sentinel-2. These products can be freely accessed in several manners and through different portals. We will take a look at packages to query the data you need for your analyses using Python and R, switching between platforms when relevant. An introduction on how to process Sentinel data with both platforms will also be covered focusing on the particularities of the sensors. For Sentinel-1 data access, we will use the [ASF Data Service](https://search.asf.alaska.edu/) to query data. There is no need for credentials for querying the data but if you want to try the downloading steps, you will need [Earthdata Login](https://urs.earthdata.nasa.gov/) credentials. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/HPDNL9/ Room 21 (Sala 21) Lorena Abad PUBLISH QVQZQC@@pretalx.earthmonitor.org -QVQZQC Sharing your geospatial knowledge in the open en en 20230901T110000 20230901T123000 1.03000

Sharing your geospatial knowledge in the open

It will be (mostly) improvised session showing how to create a new online book with geospatial content. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/QVQZQC/ Room 21 (Sala 21) Jakub Nowosad PUBLISH ANP8DA@@pretalx.earthmonitor.org -ANP8DA OEMC Hackathons Launch en en 20230901T133000 20230901T143000 1.00000

OEMC Hackathons Launch

OEMC Hackathons Launch: Land Cover Mapping EU-LUCAS and Global-FAPAR by Leandro Parente and Julia Hackländer PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/ANP8DA/ Room 21 (Sala 21) PUBLISH 8F9CU3@@pretalx.earthmonitor.org -8F9CU3 Announcement of the hackathons winners en en 20230901T143000 20230901T150000 0.03000

Announcement of the hackathons winners

Announcement of the hackathons winners, prizes and photos PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/8F9CU3/ Room 21 (Sala 21) Deleted User Nils Ratnaweera PUBLISH EY88FF@@pretalx.earthmonitor.org -EY88FF Summer school final session en en 20230901T153000 20230901T170000 1.03000

Summer school final session

Getting feedback, summarizing the summer school, and more PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/EY88FF/ Room 21 (Sala 21) PUBLISH SRMZVJ@@pretalx.earthmonitor.org -SRMZVJ Processing large OpenStreetMap datasets for geocomputational research en en 20230901T090000 20230901T103000 1.03000

Processing large OpenStreetMap datasets for geocomputational research

OpenStreetMap (OSM) is a free and openly editable map of the world. Like Wikipedia and unlike government or corperation maintained datasets, OSM is created and maintained by a community of volunteers, making it the premier decentralized and fastest evolving source of geographic vector data focussed on features relevant to human activity (e.g. roads, buildings, cafes) on planet Earth. Unlike Wikipedia, every data point in OSM has a geographic location and attributes must be structured as key-value pairs. OSM is a rich source of data for geocomputational research, but the decentralized nature of the project and the sheer volume of data. ‘Planet.osm’ now has more nodes than there are people on Earth, with more than 8 billion [nodes](https://wiki.openstreetmap.org/wiki/Node), and the rate of data creation is increasing as the community grows, to [10 million users](https://wiki.openstreetmap.org/wiki/Stats) in early 2023. The size and rapid evolution of OSM are great strengths, democratising geographic knowledge and ensuring resilience. However, these features can make it difficult to work with OSM data. This lecture will provide an introduction to working with OSM and will cover the following: - How and where to download OSM data - How to process small amounts of OSM data using the `osmdata` R package - How to process large OSM ‘extracts’ data with the `osmextract` R package - Other command line tools for working with OSM data, including the mature and widely used `osmium` tool, the `pyrosm` Python package and the [`osm2streets`](https://github.com/a-b-street/osm2streets) web application and Rust codebase Finally, the lecture will outline ideas for using OSM data. It will conclude with a call to action, inspiring the use of this rich resource to support policy objectives such as the fast and fair decarbonisation of the global economy as societies transition away from inefficient, polluting and costly fossil fuels. PUBLIC CONFIRMED Theoretical and training sessions https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/SRMZVJ/ Room 18 (Sala 18) Robin Lovelace PUBLISH ANJVSU@@pretalx.earthmonitor.org -ANJVSU Excursion en en 20230902T100000 20230902T170000 7.00000

Excursion

Long, one-day excursion: it includes a tour of the most fascinating attractions of the Poznań city center. We start at 10AM in front of the Poznań Cathedral (https://goo.gl/maps/ZMrLkSuhAzQPBqVb8) PUBLIC CONFIRMED Excursion https://pretalx.earthmonitor.org/opengeohub-summer-school-2023/talk/ANJVSU/ Other locations