Global GIS data

The International Best Track Archive for Climate Stewardship (IBTrACS) project is the most complete global collection of tropical cyclones available. It merges recent and historical tropical cyclone data from multiple agencies to create a unified, publicly available, best-track dataset that improves inter-agency comparisons. Fields available: SID: A unique storm identifier (SID) assigned by IBTrACS algorithm. ISO_TIME: Time of the observation in ISO format (YYYY-MM-DD hh:mm:ss) BASIN: Basin of the current storm position SUBBASIN: Sub-basin of the current storm position NATURE: Type of storm (a combination of the various types from the available sources) NUMBER: Number of the storm for the year (restarts at 1 for each year LAT: Mean position - latitude (a combination of the available positions) LON: Mean position - longitude (a combination of the available positions) WMO_WIND: Maximum sustained wind speed assigned by the responsible WMO agency WMO_PRES: Minimum central pressure assigned by the responsible WMO agency.

This dataset contains the following administrative boundaries: ADM0. Produced and maintained since 2017, the geoBoundaries Global Database of Political Administrative Boundaries Database www.geoboundaries.org is an open license, standardized resource of boundaries (i.e., state, county) for every country in the world.

The Global Drought Hazard project is a collection of spatial raster datasets that provide access to statistical extreme value analyses of the Standardised Precipitation Evapotranspiration Index (6-month SPEI) to identify high risk areas on a global scale. The source data are monthly spatial raster datasets from the Climatology and Climate Services Laboratory's Global SPEI Database for the period from January 1902 to December 2018. Each raster dataset has a spatial resolution of about 0.5 degrees, the values of which we converted into time series for each grid cell. These time series are used to model the number of months above selected SPEI thresholds (e.g. SPEI -1.5 or lower) for a range of return periods (e.g. 100 years) via Poisson-Generalized Pareto Point Process models.

Open and free data for assessing the human presence on the planet. The Global Human Settlement Layer (GHSL) project produces global spatial information, evidence-based analytics, and knowledge describing the human presence on the planet. The GHSL relies on the design and implementation of spatial data processing technologies that allow automatic data analytics and information extraction from large amounts of heterogeneous geospatial data including global, fine-scale satellite image data streams, census data, and crowd sourced or volunteered geographic information sources. The JRC, together with the Directorate-General for Regional and Urban Policy (DG REGIO) and Directorate-General for Defence Industry and Space (DG DEFIS) are working towards a regular and operational monitoring of global built-up and population based on the processing of Sentinel Earth Observation data produced by European Copernicus space program. In addition, the EU Agency for the Space Programme (EUSPA) undertakes activities related to user uptake of data, information and services.

Open and free data for assessing the human presence on the planet. The Global Human Settlement Layer (GHSL) project produces global spatial information, evidence-based analytics, and knowledge describing the human presence on the planet. The GHSL relies on the design and implementation of spatial data processing technologies that allow automatic data analytics and information extraction from large amounts of heterogeneous geospatial data including global, fine-scale satellite image data streams, census data, and crowd sourced or volunteered geographic information sources. The JRC, together with the Directorate-General for Regional and Urban Policy (DG REGIO) and Directorate-General for Defence Industry and Space (DG DEFIS) are working towards a regular and operational monitoring of global built-up and population based on the processing of Sentinel Earth Observation data produced by European Copernicus space program. In addition, the EU Agency for the Space Programme (EUSPA) undertakes activities related to user uptake of data, information and services.

Open and free data for assessing the human presence on the planet. The Global Human Settlement Layer (GHSL) project produces global spatial information, evidence-based analytics, and knowledge describing the human presence on the planet. The GHSL relies on the design and implementation of spatial data processing technologies that allow automatic data analytics and information extraction from large amounts of heterogeneous geospatial data including global, fine-scale satellite image data streams, census data, and crowd sourced or volunteered geographic information sources. The JRC, together with the Directorate-General for Regional and Urban Policy (DG REGIO) and Directorate-General for Defence Industry and Space (DG DEFIS) are working towards a regular and operational monitoring of global built-up and population based on the processing of Sentinel Earth Observation data produced by European Copernicus space program. In addition, the EU Agency for the Space Programme (EUSPA) undertakes activities related to user uptake of data, information and services.

Open and free data for assessing the human presence on the planet. The Global Human Settlement Layer (GHSL) project produces global spatial information, evidence-based analytics, and knowledge describing the human presence on the planet. The GHSL relies on the design and implementation of spatial data processing technologies that allow automatic data analytics and information extraction from large amounts of heterogeneous geospatial data including global, fine-scale satellite image data streams, census data, and crowd sourced or volunteered geographic information sources. The JRC, together with the Directorate-General for Regional and Urban Policy (DG REGIO) and Directorate-General for Defence Industry and Space (DG DEFIS) are working towards a regular and operational monitoring of global built-up and population based on the processing of Sentinel Earth Observation data produced by European Copernicus space program. In addition, the EU Agency for the Space Programme (EUSPA) undertakes activities related to user uptake of data, information and services.

Open and free data for assessing the human presence on the planet. The Global Human Settlement Layer (GHSL) project produces global spatial information, evidence-based analytics, and knowledge describing the human presence on the planet. The GHSL relies on the design and implementation of spatial data processing technologies that allow automatic data analytics and information extraction from large amounts of heterogeneous geospatial data including global, fine-scale satellite image data streams, census data, and crowd sourced or volunteered geographic information sources. The JRC, together with the Directorate-General for Regional and Urban Policy (DG REGIO) and Directorate-General for Defence Industry and Space (DG DEFIS) are working towards a regular and operational monitoring of global built-up and population based on the processing of Sentinel Earth Observation data produced by European Copernicus space program. In addition, the EU Agency for the Space Programme (EUSPA) undertakes activities related to user uptake of data, information and services.

Open and free data for assessing the human presence on the planet. The Global Human Settlement Layer (GHSL) project produces global spatial information, evidence-based analytics, and knowledge describing the human presence on the planet. The GHSL relies on the design and implementation of spatial data processing technologies that allow automatic data analytics and information extraction from large amounts of heterogeneous geospatial data including global, fine-scale satellite image data streams, census data, and crowd sourced or volunteered geographic information sources. The JRC, together with the Directorate-General for Regional and Urban Policy (DG REGIO) and Directorate-General for Defence Industry and Space (DG DEFIS) are working towards a regular and operational monitoring of global built-up and population based on the processing of Sentinel Earth Observation data produced by European Copernicus space program. In addition, the EU Agency for the Space Programme (EUSPA) undertakes activities related to user uptake of data, information and services.

Open and free data for assessing the human presence on the planet. The Global Human Settlement Layer (GHSL) project produces global spatial information, evidence-based analytics, and knowledge describing the human presence on the planet. The GHSL relies on the design and implementation of spatial data processing technologies that allow automatic data analytics and information extraction from large amounts of heterogeneous geospatial data including global, fine-scale satellite image data streams, census data, and crowd sourced or volunteered geographic information sources. The JRC, together with the Directorate-General for Regional and Urban Policy (DG REGIO) and Directorate-General for Defence Industry and Space (DG DEFIS) are working towards a regular and operational monitoring of global built-up and population based on the processing of Sentinel Earth Observation data produced by European Copernicus space program. In addition, the EU Agency for the Space Programme (EUSPA) undertakes activities related to user uptake of data, information and services.

Open and free data for assessing the human presence on the planet. The Global Human Settlement Layer (GHSL) project produces global spatial information, evidence-based analytics, and knowledge describing the human presence on the planet. The GHSL relies on the design and implementation of spatial data processing technologies that allow automatic data analytics and information extraction from large amounts of heterogeneous geospatial data including global, fine-scale satellite image data streams, census data, and crowd sourced or volunteered geographic information sources. The JRC, together with the Directorate-General for Regional and Urban Policy (DG REGIO) and Directorate-General for Defence Industry and Space (DG DEFIS) are working towards a regular and operational monitoring of global built-up and population based on the processing of Sentinel Earth Observation data produced by European Copernicus space program. In addition, the EU Agency for the Space Programme (EUSPA) undertakes activities related to user uptake of data, information and services.

Open and free data for assessing the human presence on the planet. The Global Human Settlement Layer (GHSL) project produces global spatial information, evidence-based analytics, and knowledge describing the human presence on the planet. The GHSL relies on the design and implementation of spatial data processing technologies that allow automatic data analytics and information extraction from large amounts of heterogeneous geospatial data including global, fine-scale satellite image data streams, census data, and crowd sourced or volunteered geographic information sources. The JRC, together with the Directorate-General for Regional and Urban Policy (DG REGIO) and Directorate-General for Defence Industry and Space (DG DEFIS) are working towards a regular and operational monitoring of global built-up and population based on the processing of Sentinel Earth Observation data produced by European Copernicus space program. In addition, the EU Agency for the Space Programme (EUSPA) undertakes activities related to user uptake of data, information and services.

Open and free data for assessing the human presence on the planet. The Global Human Settlement Layer (GHSL) project produces global spatial information, evidence-based analytics, and knowledge describing the human presence on the planet. The GHSL relies on the design and implementation of spatial data processing technologies that allow automatic data analytics and information extraction from large amounts of heterogeneous geospatial data including global, fine-scale satellite image data streams, census data, and crowd sourced or volunteered geographic information sources. The JRC, together with the Directorate-General for Regional and Urban Policy (DG REGIO) and Directorate-General for Defence Industry and Space (DG DEFIS) are working towards a regular and operational monitoring of global built-up and population based on the processing of Sentinel Earth Observation data produced by European Copernicus space program. In addition, the EU Agency for the Space Programme (EUSPA) undertakes activities related to user uptake of data, information and services.

High resolution maps of estimated numbers of births and pregnancies in the Americas in 2015

The International Best Track Archive for Climate Stewardship (IBTrACS) project is the most complete global collection of tropical cyclones available. It merges recent and historical tropical cyclone data from multiple agencies to create a unified, publicly available, best-track dataset that improves inter-agency comparisons. Fields available: SID: A unique storm identifier (SID) assigned by IBTrACS algorithm. ISO_TIME: Time of the observation in ISO format (YYYY-MM-DD hh:mm:ss) BASIN: Basin of the current storm position SUBBASIN: Sub-basin of the current storm position NATURE: Type of storm (a combination of the various types from the available sources) NUMBER: Number of the storm for the year (restarts at 1 for each year LAT: Mean position - latitude (a combination of the available positions) LON: Mean position - longitude (a combination of the available positions) WMO_WIND: Maximum sustained wind speed assigned by the responsible WMO agency WMO_PRES: Minimum central pressure assigned by the responsible WMO agency.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between **paved** and **unpaved** roads across the region. Surface classification is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name British Indian Ocean Territory **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.0001 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0 million km (0.3477%) - Unpaved roads: 0.0 million km (28.0622%) About 0.0001 million km (71.5901%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0 million km (0.0%) of the missing surface information. Intended Use This dataset supports transportation planning, infrastructure analysis, climate emissions assessment, and GIS applications. AI Features - **pred_class**: Model-predicted surface class ("paved" or "unpaved") - **pred_label**: Binary label (0 = paved, 1 = unpaved) - **osm_surface_class**: Surface classification derived from OSM tags - **combined_surface_osm_priority**: Combined classification prioritizing OSM - **combined_surface_DL_priority**: Combined classification prioritizing DL prediction - **n_of_predictions_used**: Number of predictions used for estimation - **predicted_length**: Predicted length based on DL estimation (meters) - **DL_mean_timestamp**: Mean timestamp of predictions used OSM Attributes - **name** - **name:en** - **name:* (local language)** - **highway** - **surface** - **smoothness** - **width** - **lanes** - **oneway** - **bridge** - **layer** - **source** Urban Classification Attributes - **continent** - **country_iso_a2** - **urban** (0 = rural, 1 = urban) - **urban_area** - **osm_id** - **osm_type** Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between **paved** and **unpaved** roads across the region. Surface classification is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name South Georgia and the South Sandwich Islands **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.0 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0 million km (1.1463%) - Unpaved roads: 0.0 million km (30.4902%) About 0.0 million km (68.3634%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0 million km (0.0%) of the missing surface information. Intended Use This dataset supports transportation planning, infrastructure analysis, climate emissions assessment, and GIS applications. AI Features - **pred_class**: Model-predicted surface class ("paved" or "unpaved") - **pred_label**: Binary label (0 = paved, 1 = unpaved) - **osm_surface_class**: Surface classification derived from OSM tags - **combined_surface_osm_priority**: Combined classification prioritizing OSM - **combined_surface_DL_priority**: Combined classification prioritizing DL prediction - **n_of_predictions_used**: Number of predictions used for estimation - **predicted_length**: Predicted length based on DL estimation (meters) - **DL_mean_timestamp**: Mean timestamp of predictions used OSM Attributes - **name** - **name:en** - **name:* (local language)** - **highway** - **surface** - **smoothness** - **width** - **lanes** - **oneway** - **bridge** - **layer** - **source** Urban Classification Attributes - **continent** - **country_iso_a2** - **urban** (0 = rural, 1 = urban) - **urban_area** - **osm_id** - **osm_type** Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between **paved** and **unpaved** roads across the region. Surface classification is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name Antarctica **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.0 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0 million km (nan%) - Unpaved roads: 0.0 million km (nan%) About 0.0 million km (nan%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0 million km (nan%) of the missing surface information. Intended Use This dataset supports transportation planning, infrastructure analysis, climate emissions assessment, and GIS applications. AI Features - **pred_class**: Model-predicted surface class ("paved" or "unpaved") - **pred_label**: Binary label (0 = paved, 1 = unpaved) - **osm_surface_class**: Surface classification derived from OSM tags - **combined_surface_osm_priority**: Combined classification prioritizing OSM - **combined_surface_DL_priority**: Combined classification prioritizing DL prediction - **n_of_predictions_used**: Number of predictions used for estimation - **predicted_length**: Predicted length based on DL estimation (meters) - **DL_mean_timestamp**: Mean timestamp of predictions used OSM Attributes - **name** - **name:en** - **name:* (local language)** - **highway** - **surface** - **smoothness** - **width** - **lanes** - **oneway** - **bridge** - **layer** - **source** Urban Classification Attributes - **continent** - **country_iso_a2** - **urban** (0 = rural, 1 = urban) - **urban_area** - **osm_id** - **osm_type** Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between **paved** and **unpaved** roads across the region. Surface classification is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name French Southern Territories **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.0 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0 million km (nan%) - Unpaved roads: 0.0 million km (nan%) About 0.0 million km (nan%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0 million km (nan%) of the missing surface information. Intended Use This dataset supports transportation planning, infrastructure analysis, climate emissions assessment, and GIS applications. AI Features - **pred_class**: Model-predicted surface class ("paved" or "unpaved") - **pred_label**: Binary label (0 = paved, 1 = unpaved) - **osm_surface_class**: Surface classification derived from OSM tags - **combined_surface_osm_priority**: Combined classification prioritizing OSM - **combined_surface_DL_priority**: Combined classification prioritizing DL prediction - **n_of_predictions_used**: Number of predictions used for estimation - **predicted_length**: Predicted length based on DL estimation (meters) - **DL_mean_timestamp**: Mean timestamp of predictions used OSM Attributes - **name** - **name:en** - **name:* (local language)** - **highway** - **surface** - **smoothness** - **width** - **lanes** - **oneway** - **bridge** - **layer** - **source** Urban Classification Attributes - **continent** - **country_iso_a2** - **urban** (0 = rural, 1 = urban) - **urban_area** - **osm_id** - **osm_type** Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

This zip file contains 28 cloud optimized tiff files that cover the continent of Africa. Each of the 28 files represents a region or area - these are not divided by country. Notes: * The country-by-country files that were previously hosted here have been moved into separate datasets. You can find all of them here. * South Sudan, Sudan, Somalia and Ethiopia are intentionally omitted from this dataset. However, a country-level dataset for Ethiopia can be found here. * These 28 tiff files represent 2015 population estimates. However, please note that many of the country-level files include 2020 population estimates including: Angola, Benin, Botswana, Burundi, Cameroon, Cabo Verde, Cote d'Ivoire, Djibouti, Eritrea, Eswatini, The Gambia, Ghana, Lesotho, Liberia, Mozambique, Namibia, Sao Tome & Principe, Sierra Leone, South Africa, Togo, Zambia, and Zimbabwe.

A 100 m spatial resolution geotiff of walking travel time in seconds to nearest health facility in Namibia. The data was generated using the Child Poverty and Access to Services (CPAS) software (10.5281/zenodo.4638563) and was created as part of the CPAS project within the Data for Children Collaborative. The travel time is calculated assuming walking speeds on all roads, tracks, paths and land cover types. A full description is available here a video description of the data is also available here Projection system is: GCS_WGS_1984 EPSG 4326 for all

A 100 m spatial resolution geotiff of motorised travel time in seconds to nearest health facility in Namibia. The data was generated using the Child Poverty and Access to Services (CPAS) software (10.5281/zenodo.4638563) and was created as part of the CPAS project within the Data for Children Collaborative. The travel time is calculated assuming driving speeds of local public transport options on all-weather roads/asphalt roads and walking speeds on all other roads, tracks, paths and land cover types. A full description is available here a video description of the data is also available here Projection system is: GCS_WGS_1984 EPSG 4326 for all

The International Best Track Archive for Climate Stewardship (IBTrACS) project is the most complete global collection of tropical cyclones available. It merges recent and historical tropical cyclone data from multiple agencies to create a unified, publicly available, best-track dataset that improves inter-agency comparisons. Fields available: SID: A unique storm identifier (SID) assigned by IBTrACS algorithm. ISO_TIME: Time of the observation in ISO format (YYYY-MM-DD hh:mm:ss) BASIN: Basin of the current storm position SUBBASIN: Sub-basin of the current storm position NATURE: Type of storm (a combination of the various types from the available sources) NUMBER: Number of the storm for the year (restarts at 1 for each year LAT: Mean position - latitude (a combination of the available positions) LON: Mean position - longitude (a combination of the available positions) WMO_WIND: Maximum sustained wind speed assigned by the responsible WMO agency WMO_PRES: Minimum central pressure assigned by the responsible WMO agency.

The International Best Track Archive for Climate Stewardship (IBTrACS) project is the most complete global collection of tropical cyclones available. It merges recent and historical tropical cyclone data from multiple agencies to create a unified, publicly available, best-track dataset that improves inter-agency comparisons. Fields available: SID: A unique storm identifier (SID) assigned by IBTrACS algorithm. ISO_TIME: Time of the observation in ISO format (YYYY-MM-DD hh:mm:ss) BASIN: Basin of the current storm position SUBBASIN: Sub-basin of the current storm position NATURE: Type of storm (a combination of the various types from the available sources) NUMBER: Number of the storm for the year (restarts at 1 for each year LAT: Mean position - latitude (a combination of the available positions) LON: Mean position - longitude (a combination of the available positions) WMO_WIND: Maximum sustained wind speed assigned by the responsible WMO agency WMO_PRES: Minimum central pressure assigned by the responsible WMO agency.

The International Best Track Archive for Climate Stewardship (IBTrACS) project is the most complete global collection of tropical cyclones available. It merges recent and historical tropical cyclone data from multiple agencies to create a unified, publicly available, best-track dataset that improves inter-agency comparisons. Fields available: SID: A unique storm identifier (SID) assigned by IBTrACS algorithm. ISO_TIME: Time of the observation in ISO format (YYYY-MM-DD hh:mm:ss) BASIN: Basin of the current storm position SUBBASIN: Sub-basin of the current storm position NATURE: Type of storm (a combination of the various types from the available sources) NUMBER: Number of the storm for the year (restarts at 1 for each year LAT: Mean position - latitude (a combination of the available positions) LON: Mean position - longitude (a combination of the available positions) WMO_WIND: Maximum sustained wind speed assigned by the responsible WMO agency WMO_PRES: Minimum central pressure assigned by the responsible WMO agency.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between **paved** and **unpaved** roads across the region. Surface classification is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name Namibia **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.2016 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0197 million km (9.7506%) - Unpaved roads: 0.1094 million km (54.2725%) About 0.0725 million km (35.9769%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0001 million km (0.0915%) of the missing surface information. Intended Use This dataset supports transportation planning, infrastructure analysis, climate emissions assessment, and GIS applications. AI Features - **pred_class**: Model-predicted surface class ("paved" or "unpaved") - **pred_label**: Binary label (0 = paved, 1 = unpaved) - **osm_surface_class**: Surface classification derived from OSM tags - **combined_surface_osm_priority**: Combined classification prioritizing OSM - **combined_surface_DL_priority**: Combined classification prioritizing DL prediction - **n_of_predictions_used**: Number of predictions used for estimation - **predicted_length**: Predicted length based on DL estimation (meters) - **DL_mean_timestamp**: Mean timestamp of predictions used OSM Attributes - **name** - **name:en** - **name:* (local language)** - **highway** - **surface** - **smoothness** - **width** - **lanes** - **oneway** - **bridge** - **layer** - **source** Urban Classification Attributes - **continent** - **country_iso_a2** - **urban** (0 = rural, 1 = urban) - **urban_area** - **osm_id** - **osm_type** Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between **paved** and **unpaved** roads across the region. Surface classification is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name Curaçao **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.0 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0 million km (nan%) - Unpaved roads: 0.0 million km (nan%) About 0.0 million km (nan%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0 million km (nan%) of the missing surface information. Intended Use This dataset supports transportation planning, infrastructure analysis, climate emissions assessment, and GIS applications. AI Features - **pred_class**: Model-predicted surface class ("paved" or "unpaved") - **pred_label**: Binary label (0 = paved, 1 = unpaved) - **osm_surface_class**: Surface classification derived from OSM tags - **combined_surface_osm_priority**: Combined classification prioritizing OSM - **combined_surface_DL_priority**: Combined classification prioritizing DL prediction - **n_of_predictions_used**: Number of predictions used for estimation - **predicted_length**: Predicted length based on DL estimation (meters) - **DL_mean_timestamp**: Mean timestamp of predictions used OSM Attributes - **name** - **name:en** - **name:* (local language)** - **highway** - **surface** - **smoothness** - **width** - **lanes** - **oneway** - **bridge** - **layer** - **source** Urban Classification Attributes - **continent** - **country_iso_a2** - **urban** (0 = rural, 1 = urban) - **urban_area** - **osm_id** - **osm_type** Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

geoBoundaries ADM0 boundaries for Curaçao: 1 units, representing 2021. Source: raster2polygon from Sentinel-2 10m Land Cover where Image Year = 2021 / exclude gridcode = 1 (water) / dissolve / processed by IMB.

geoBoundaries ADM0 boundaries for Antartica: 1 units, representing 2020. Source: Natural Earth.

This dataset provides detailed information on road surfaces from OpenStreetMap (OSM), distinguishing between **paved** and **unpaved** roads across the region. Surface classification is derived using a hybrid deep learning approach. For methodological details, see: http://arxiv.org/abs/2410.19874 Recently, we also published a new country-level dataset based on PlanetScope satellite imagery with near-complete coverage of all arterial roads. It is available on HDX under the name kosovo **Planet** Road Surface. The corresponding paper is available at: https://arxiv.org/abs/2512.04092 Road Surface Statistics Approximately 0.1691 million km of roads are mapped in OSM in this region. Based on AI-derived estimates: - Paved roads: 0.0696 million km (41.182%) - Unpaved roads: 0.0099 million km (5.8528%) About 0.0896 million km (52.9652%) of road surface information is missing in OSM. To reduce this gap, the Mapillary-derived road surface dataset provides an additional 0.0013 million km (1.451%) of the missing surface information. Intended Use This dataset supports transportation planning, infrastructure analysis, climate emissions assessment, and GIS applications. AI Features - **pred_class**: Model-predicted surface class ("paved" or "unpaved") - **pred_label**: Binary label (0 = paved, 1 = unpaved) - **osm_surface_class**: Surface classification derived from OSM tags - **combined_surface_osm_priority**: Combined classification prioritizing OSM - **combined_surface_DL_priority**: Combined classification prioritizing DL prediction - **n_of_predictions_used**: Number of predictions used for estimation - **predicted_length**: Predicted length based on DL estimation (meters) - **DL_mean_timestamp**: Mean timestamp of predictions used OSM Attributes - **name** - **name:en** - **name:* (local language)** - **highway** - **surface** - **smoothness** - **width** - **lanes** - **oneway** - **bridge** - **layer** - **source** Urban Classification Attributes - **continent** - **country_iso_a2** - **urban** (0 = rural, 1 = urban) - **urban_area** - **osm_id** - **osm_type** Data Sources The dataset originates from OpenStreetMap (OSM) and is augmented with deep learning predictions based on Mapillary street-level imagery, combined with the GHSU Global Human Settlement Urban Layer 2019 and AFRICAPOLIS 2020 urban layer. More HeiGIT datasets: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology More information: https://heigit.org/ Contact: communications@heigit.org

Sint Maarten (Dutch part) administrative level 0-1 boundaries (COD-AB) dataset version 01. This dataset is structured into 1 level: - Admin 1: 8 Dates associated with this dataset: - 07 November 2024: dataset reviewed for accuracy and completeness - 22 January 2024: valid for use by the humanitarian community - 14 September 2018: last edit to the dataset before publishing - 14 September 2018: boundaries created by the source Quality assured, configured, and published by OCHA Field Information Services (FIS) and HDX. Part of the dataset: Global Subnational Administrative Boundaries

The International Best Track Archive for Climate Stewardship (IBTrACS) project is the most complete global collection of tropical cyclones available. It merges recent and historical tropical cyclone data from multiple agencies to create a unified, publicly available, best-track dataset that improves inter-agency comparisons. Fields available: SID: A unique storm identifier (SID) assigned by IBTrACS algorithm. ISO_TIME: Time of the observation in ISO format (YYYY-MM-DD hh:mm:ss) BASIN: Basin of the current storm position SUBBASIN: Sub-basin of the current storm position NATURE: Type of storm (a combination of the various types from the available sources) NUMBER: Number of the storm for the year (restarts at 1 for each year LAT: Mean position - latitude (a combination of the available positions) LON: Mean position - longitude (a combination of the available positions) WMO_WIND: Maximum sustained wind speed assigned by the responsible WMO agency WMO_PRES: Minimum central pressure assigned by the responsible WMO agency.

The NASA Making Earth System Data Records for Use in Research Environments (MEaSUREs) Combined Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) and Moderate Resolution Imaging Spectroradiometer (MODIS) Emissivity for Land (CAMEL) dataset provides monthly emissivity at 0.05 degree (~5 kilometer) resolution (CAM5K30EM). The CAM5K30EM data product was created by combining the University of Wisconsin-Madison MODIS Baseline Fit (UWBF) emissivity database and the Jet Propulsion Laboratory ASTER Global Emissivity Dataset Version 4 (GED V4). The two datasets have been integrated to capitalize on the unique strengths of each product's characteristics. The integration steps include adjustment of ASTER GED Version 3 emissivities for vegetation and snow cover variations to produce ASTER GED Version 4, aggregation of ASTER GED Version 4 emissivities from 100 meter resolution to the UWBF 5 kilometer resolution, merging of the five ASTER spectral emissivities with the UWBF emissivity to create CAMEL at 13 hinge points, and extension of the 13 hinge points to high spectral resolution (HSR) utilizing the Principal Component (PC) regression method. Additional details regarding the methodology are available in the User Guide and Algorithm Theoretical Basis Document (ATBD). Provided in the CAM5K30EM product are layers for the CAMEL emissivity, ASTER Normalized Difference Vegetation Index (NDVI), snow fraction derived from MODIS (MOD10), latitude, longitude, CAMEL quality, ASTER quality, and the UWBF emissivity quality information. Known Issues * The following granules are missing from the product: January, February, and August of 2000; June and July of 2001; March of 2002; December of 2003; July of 2010; and February of 2016.

Mangroves are a group of tree and bush species that thrive in coastal intertidal zones, or the area between high and low tide. Because they prefer warm-water ecosystems, they are most commonly found at tropical and subtropical latitudes around the world. They are halophytes, or salt tolerant, and adapted to live in low-oxygen saline or brackish water. They are easily recognizable due to their tangle of prop roots, which keep their leafy branches above the water as the cycle of tides changes the water level.   Though more than 50—and possibly up to 110—species are considered mangroves, not all are from the genus Rhizophora. Some mangrove species are the result of convergent evolution, when unrelated species adapt to a harsh environment (such as a high-salt, low-oxygen intertidal zone) by taking on similar characteristics (such as a tangled prop root system). For this reason, extensive mangrove forests may contain only a handful of unique mangrove species—and even within a single forest, different types of mangroves each occupy distinct niches.   Mangroves are crucial to the health of coastal ecosystems. Their root systems protect the shoreline against erosion by reducing wave intensity and trapping sediments against the land. Mangrove forests are also effective at carbon sequestration, the process of removing carbon dioxide (a harmful greenhouse gas) from the atmosphere. Their labyrinth of roots is a popular hiding spot for fish and other marine life evading predators. They also shield coastal communities from tsunamis and storm surge.   Today, the largest mangrove forest in the world is the Sundarbans forest along the coast of Bangladesh and India, spanning 10,000 square kilometers (almost 4,000 square miles). In the past 50 years, though, it is estimated that up to 35 percent of the world's mangrove forests have been lost. This is largely due to shrimp farming, in which mangrove forests are cleared and replaced with artificial ponds for aquaculture practices, as well as other growing threats: unsustainable tourism activities; agricultural practices that cause mangrove removal or harmful runoff and pollution; and mangrove deforestation for coastal development or to gather charcoal and timber. These risks are exacerbated by climate change causing sea levels to rise, effectively drowning mangrove forests, and alterations to water chemistry, temperature, and other conditions, which put stress on the mangroves’ preferred growing conditions.   As threats to mangroves become better understood, organizations around the world have been created and joined together to protect these important ecosystems. The data in this map layer is from the Global Mangrove Alliance, a collaboration between Conservation International, The International Union for the Conservation of Nature, The Nature Conservancy, Wetlands International, and the World Wildlife Fund. Supported by grants from the National Geographic Society, Explorers Ben Somerville and Margaret Owuor use research, education, and storytelling to protect mangrove forests near their homes in the Caribbean and southeastern Kenya. The map layer shows mangrove forest extent around the world in 2020. About 40 percent of people live near the coast, and 90 percent of tropical storms form within 20 degrees of the Equator—the parts of the globe where mangrove forests flourish. You can use the Population Density and Longitudes and Latitudes layers to see how many people and mangroves live in these regions, and the Protected Areas layer to find the areas where special conservation plans exist to defend mangrove ecosystems. Data Citation: Bunting, P.; Rosenqvist, A.; Hilarides, L.; Lucas, R.M.; Thomas, T.; Tadono, T.; Worthington, T.A.; Spalding, M.; Murray, N.J.; Rebelo, L-M. Global Mangrove Extent Change 1996 – 2020: Global Mangrove Watch Version 3.0. Remote Sensing. 2022 doi: 10.5281/zenodo.6894272

This dataset shows the list of operating health facilities. Attributes included: Name,Nature of Facility, Activities, Lat, Long

# EOS-RS Damage Proxy Map: Hualien County, Taiwan, Landslide, 24 June 2026, v1.2 The Earth Observatory of Singapore - Remote Sensing Lab (EOS-RS) created this preliminary Damage Proxy Map (DPM) depicting areas that are likely damaged in Hualien County, Taiwan, due to the landslide that created a barrier lake on 22 June 2026. This map was derived from synthetic aperture radar (SAR) images acquired by the Copernicus Sentinel-1 satellite using a pre-event time series of (23 Feb 2026 to 11 June 2026) and a post-event acquisition (23 June 2026). The map covers the area indicated by the white polygon. Damage is shown by colored pixels of approximately 30m in size, where yellow to red indicates increasingly significant ground surface change before and after the event. Preliminary validation was conducted using news reports and pictures in selected areas. This map should be used as guidance to identify damaged areas and may be less reliable over vegetated or mountainous areas. Scattered pixels over such areas may be false positives, and a lack of colored pixels does not necessarily indicate an absence of damage. This product contains modified Copernicus Sentinel data (2026), processed by ESA and analyzed by the Earth Observatory of Singapore - Remote Sensing Lab (EOS-RS). **More map details and files:** **Legal Disclaimer:** **Credits:** Earth Observatory of Singapore - Remote Sensing Lab (EOS-RS), Contains modified Copernicus Sentinel data (2026)