Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
528
datasets available to search
ShareScore release 0.7.1
Dataset results
528 results for “Land cover”
Paired Vegetation and Soil Burn Severity Metrics and Associated Climate, Weather, Topographical, and Land Cover Attributes
<p>This dataset pairs differenced Normalized Burn Ratio (dNBR) and soil burn severity (SBS) for 254 large (>400 ha in size) fires across the western US. Dataset also includes climate, weather, topography, physical and chemical soil characteristics, and land cover attributes of each burned pixel at the time of fire. This effort provided a table of 16.3 million burned pixels and their associated characteristics including dNBR, SBS, and 94 biological and physical covariates. After removing correlated features, the final data includes 18 fire covariates namely: dNBR, elevation, slope, aspect, land cover type, wind speed, energy release component, vapor pressure deficit, annual precipitation, and annual average daily max temperature, as well as the clay, sand and silt content of the soil and volumetric fraction of coarse fragments and soil organic carbon content. We also included spatial coherence metrices for dNBR, including DVAR, SHADE and SAVG. This data is provided as CSV files in Xtrain, Xvalidation, Xtest, as well as Ytrain, Yvalidation, and Ytest; in which X files (model input) provide all features except for SBS and Y files (model output) include SBS.</p><p>We also provided this data for an additional 16 large fires across the western US ("Extra Test" folder, including Dataset – X file – and Label – Y file).</p><p>Finally, the trained XGBoost model to translate dNBR to SBS using the associated features is also provided in this folder.</p>
Dakar very-high resolution land cover map
<p>This land cover map of Dakar (Senegal) was created from a Pléiades very-high resolution imagery with a spatial resolution of 0.5 meter. The methodology followed a open-source semi-automated framework [1] that rely on <a href="https://grass.osgeo.org/">GRASS GIS</a> using a local unsupervised optimization approach for the segmentation part [2-3].</p> <p>Description of the files:</p> <ul> <li>"Landcover.zip" : The direct output from the supervised classification using the Random Forest classifier.</li> <li>"Landcover_Postclassif_Level8_Splitbuildings.zip" : Post-processed version of the previous map ("Landcover"), with reduced misclassifications from the original classification (rule-based used to reclassify the errors, with a focus on built-up classes).</li> <li>"Landcover_Postclassif_Level8_modalfilter3.zip" : Smoothed version of the previous product (modal filter with window 3x3 applied on the "Landcover_Postclassif_Level8_Splitbuildings"). </li> <li>"Landcover_Postclassif_Level9_Shadowsback.zip" : Corresponds to the "level8_Splitbuildings" with shadows coming from the original classification.</li> <li>"Dakar_legend_colors.txt" : Text file providing the correspondance between the value of the pixels and the legend labels and a proposition of color to be used.</li> </ul> <p> </p> <p>References:</p> <p>[1] Grippa, Taïs, Moritz Lennert, Benjamin Beaumont, Sabine Vanhuysse, Nathalie Stephenne, and Eléonore Wolff. 2017. “An Open-Source Semi-Automated Processing Chain for Urban Object-Based Classification.” <em>Remote Sensing</em> 9 (4): 358. <a href="https://doi.org/10.3390/rs9040358">https://doi.org/10.3390/rs9040358</a>.</p> <p>[2] Grippa, Tais, Stefanos Georganos, Sabine G. Vanhuysse, Moritz Lennert, and Eléonore Wolff. 2017. “A Local Segmentation Parameter Optimization Approach for Mapping Heterogeneous Urban Environments Using VHR Imagery.” In <em>Proceedings Volume 10431, Remote Sensing Technologies and Applications in Urban Environments II.</em>, edited by Wieke Heldens, Nektarios Chrysoulakis, Thilo Erbertseder, and Ying Zhang, 20. SPIE. <a href="https://doi.org/10.1117/12.2278422">https://doi.org/10.1117/12.2278422</a>.</p> <p>[3] Georganos, Stefanos, Taïs Grippa, Moritz Lennert, Sabine Vanhuysse, and Eleonore Wolff. 2017. “SPUSPO: Spatially Partitioned Unsupervised Segmentation Parameter Optimization for Efficiently Segmenting Large Heterogeneous Areas.” In <em>Proceedings of the 2017 Conference on Big Data from Space (BiDS’17)</em>.</p> <p> </p> <p>Founding: </p> <p>This dataset was produced in the frame of two research project : MAUPP (<a href="http://maupp.ulb.ac.be">http://maupp.ulb.ac.be</a>) and REACT (<a href="http://react.ulb.be">http://react.ulb.be</a>), funded by the Belgian Federal Science Policy Office (<a href="http://eo.belspo.be/About/Stereo3.aspx">BELSPO</a>).</p>
Ouagadougou very-high resolution land cover map
<p>This land cover map of Ouagadougou (Burkina Faso) was created from a WorldView3 very-high resolution imagery with a spatial resolution of 0.5 meter. The methodology followed a open-source semi-automated framework [1] that rely on <a href="https://grass.osgeo.org/">GRASS GIS</a> using a local unsupervised optimization approach for the segmentation part [2-3].</p> <p>Description of the files:</p> <ul> <li>"Landcover.zip" : The direct output from the supervised classification using the Random Forest classifier.</li> <li>"Landcover_Postclassif_Level5_Splitbuildings.zip" : Post-processed version of the previous map ("Landcover"), with reduced misclassifications from the original classification (rule-based used to reclassify the errors, with a focus on built-up classes).</li> <li>"Landcover_Postclassif_Level5_modalfilter3.zip" : Smoothed version of the previous product (modal filter with window 3x3 applied on the "Landcover_Postclassif_Level5_Splitbuildings"). </li> <li>"Landcover_Postclassif_Level6_Shadowsback.zip" : Corresponds to the "level5_Splitbuildings" with shadows coming from the original classification.</li> <li>"Ouaga_legend_colors.txt" : Text file providing the correspondance between the value of the pixels and the legend labels and a proposition of color to be used.</li> </ul> <p> </p> <p>References:</p> <p>[1] Grippa, Taïs, Moritz Lennert, Benjamin Beaumont, Sabine Vanhuysse, Nathalie Stephenne, and Eléonore Wolff. 2017. “An Open-Source Semi-Automated Processing Chain for Urban Object-Based Classification.” <em>Remote Sensing</em> 9 (4): 358. <a href="https://doi.org/10.3390/rs9040358">https://doi.org/10.3390/rs9040358</a>.</p> <p>[2] Grippa, Tais, Stefanos Georganos, Sabine G. Vanhuysse, Moritz Lennert, and Eléonore Wolff. 2017. “A Local Segmentation Parameter Optimization Approach for Mapping Heterogeneous Urban Environments Using VHR Imagery.” In <em>Proceedings Volume 10431, Remote Sensing Technologies and Applications in Urban Environments II.</em>, edited by Wieke Heldens, Nektarios Chrysoulakis, Thilo Erbertseder, and Ying Zhang, 20. SPIE. <a href="https://doi.org/10.1117/12.2278422">https://doi.org/10.1117/12.2278422</a>.</p> <p>[3] Georganos, Stefanos, Taïs Grippa, Moritz Lennert, Sabine Vanhuysse, and Eleonore Wolff. 2017. “SPUSPO: Spatially Partitioned Unsupervised Segmentation Parameter Optimization for Efficiently Segmenting Large Heterogeneous Areas.” In <em>Proceedings of the 2017 Conference on Big Data from Space (BiDS’17)</em>.</p> <p> </p> <p>Founding: </p> <p>This dataset was produced in the frame of two research project : MAUPP (<a href="http://maupp.ulb.ac.be">http://maupp.ulb.ac.be</a>) and REACT (<a href="http://react.ulb.be">http://react.ulb.be</a>), funded by the Belgian Federal Science Policy Office (<a href="http://eo.belspo.be/About/Stereo3.aspx">BELSPO</a>).</p>
INEGI Uso del Suelo y Vegetacion Land Cover Classifications for Mexico (1985, 1993, 2002, 2007, 2011), Harmonized with NLCD 2011 Legend
<p>We have taken the Uso del Suelo y Vegetacion land cover classification products for Mexico (courtesy of Mexico's Instituto Nacional de Estadistica y Geografia, or INEGI) for years 1985, 1993, 2002, 2007, and 2011 (INEGI, 2015); and harmonized their classes with the classes of the Multi-Resolution Land Characteristics Consortium (MRLC) National Land Cover Database (NLCD) (Homer et al., 2015). Details of processing, along with the processing scripts, are archived in GitHub in the <a href="https://github.com/tbohn/NLCD_INEGI/tree/v1.5">NLCD_INEGI</a> project (Bohn, 2019).</p> <p>This project contains the following g-zipped tar files:</p> <ul> <li>SERIE_I.tgz - land cover from 1985</li> <li>SERIE_II.tgz - land cover from 1993</li> <li>SERIE_III.tgz - land cover from 2002</li> <li>SERIE_IV.tgz - land cover from 2007</li> <li>SERIE_V.tgz - land cover from 2011</li> </ul> <p>On LINUX, the contents of these files can be extracted via "tar":</p> <p>tar -xvzf SERIE_I.tgz >& log.tar.txt</p> <p>On Windows, applications such as "7-zip" can extract the contents.</p> <p>Each of these .tgz files contain a folder with the same name but without the ".tgz". Within each of these folders are the following sub-folders:</p> <ul> <li>For SERIE_I to SERIE_IV: <ul> <li>metatiles/ - original land cover shapefiles, with Mexico divided into "metatiles" along UTM zones, as documented in <a href="https://github.com/tbohn/NLCD_INEGI/tree/v1.0/docs/Processing_of_INEGI_USOSV_dataset.docx">Processing_of_INEGI_USOSV_dataset.docx</a></li> <li>geo/ - shapefiles from "metatiles", reprojected into geographic</li> <li>entire/ - shapefiles from "geo" merged into a single file for the entire country</li> </ul> </li> <li>For SERIE_V: <ul> <li>entire/ - original land cover shapefile in Lambert Conical projection, covering all of Mexico</li> <li>geo/ - shapefile from "entire" reprojected into geographic</li> </ul> </li> <li>SERIE_I to SERIE_V: <ul> <li>cve_union/ - shapefiles covering all of Mexico, in geographic projection, with land cover reclassified to NLCD 2011 legend</li> <li>rasters/ - files from "cve_union", rasterized at 0.000350884 degree resolution</li> <li>ascii/ - raster files from "rasters", exported to ascii ESRI grid file format</li> </ul> </li> </ul> <p>Output files (in the "ascii" folders) are ESRI ascii raster grid files, in geographic projection, with cellsize = 0.000350884 degrees.</p>
Homisland-IO: a homogeneous land cover over the small islands of the southwest Indian Ocean
<p>This dataset is a landcover product, called Homisland-IO<strong>,</strong> based on the analysis of high spatial resolution images acquired by the SPOT 5 satellite between December 2012 and July 2014 and produced at the SEAS-OI Station. We used an object-based image analysis method to identify the 11 major classes of land cover / land use of these tropical islands. This methodology together with a good knowledge of the field has enabled us to achieve an overall accuracy of 86%, making it an operational product. Homisland-IO is<strong> </strong>freely accessible through a web portal and thus available for future uses.</p>
Murgia Alta: land cover map (2018)
<p>A land cover map in "Murgia Alta" PA, for 2018, obtained by considering 4 multi-seasonal Sentinel-2 images. A Support Vector machine (SVM) classifier was used for a 13 classes problem. The images were atmospherically corrected.</p> <p>The map was produced at 10 meters spatial resolution and projected in WGS84/UTM33N.</p> <p>The Overall Accuracy (OA) of the map was: OA=97.37%±0.09%.</p> <p>The map has 14 values related as follows in LCCS-FAO taxonomy:</p> <p>Value 0 = Unclassified</p> <p>Value 1 = A11/A7.A9 (olive grooves)</p> <p>Value 2 = A11/A1.A7.A10 (orchards)</p> <p>Value 3 = A11/A2.A7.A10 (vineyards)</p> <p>Value 4 = A11/A3 (cultivated herbaceous)</p> <p>Value 5 = A12/A1.D1.E1 (natural broadleaved evergreen)</p> <p>Value 6 = A12/A1.D1.E2 (natural broadleaved deciduous)</p> <p>Value 7 = A12/A1.D2.E1 (natural needleleaved evergreen)</p> <p>Value 8 = A12/A2.A6 (natural grasslands)</p> <p>Value 9 = B15/A1 (artificial structures, buildings/roads)</p> <p>Value 10 = B15/A2.A6 (extraction sites)</p> <p>Value 11 = B27-B28/A1.A5 (artificial-natural water)</p> <p>Value 12 =BURNED AREAS </p> <p>Value 13 =Out of PA</p>
A Dataset of Global Land Cover Validation Samples
<p>A dataset of global land cover validation samples in 2015. In order to guarantee the confidence and objective of the validation samples, several existing reference datasets such as GLCNMO2008 training dataset, VIIRS reference dataset, STEP reference dataset, Global cropland reference data and so on, high resolution imagery in the Google earth and time-series NDVI,NDSI values of each related point are integrated to derive the global validation datasets. The dataset is provided in .shp format.</p>
GLM2_modified and Results as used in Ma et al: Global rules for translating land-use change (LUH2) to land-cover change for CMIP6 using GLM2, Geosci. Model Dev., 2020
<p>Code modified GLM2, scripts and result as used in Ma et al 2019, Ma et al 2019, Geosci. Model Dev. Discuss., https://doi.org/10.5194/gmd-2019-146</p>
Land-Cover Classification of Mesoamerica's Cimate Hubs
<p>This project presents land use classification maps obtained through satellite image analyses for 10 study areas in Mesoamerica. A classification algorithm was adapted specifically for the tropics and developed using the latest satellite images available. We applied Object Based Image Analysis method & Random Forest algorithm on 10m Sentinel 1 (S1) & Sentinel 2 (S2) image collections of years 2022/2023. The study area encompassed 10 landscapes spanning 8 countries across Mesoamerica. These areas cover a total of 256 971 km² and were previously defined by Osa Conservation as potential climate adaptation hubs.</p>
The 30 m land cover dataset for capturing land cover changes induced by ecological restoration from 1990 to 2022 on the Chinese Loess Plateau
<p>Continuous time-series of land cover is critical for attributing runoff, sediment and carbon changes on the Chinese Loess Plateau (CLP). However, current land cover products with annal temporal resolution lack spatial identification accuracy, particularly in capturing authentic changes of cropland, forest and grassland. To address these issues, a 30 m annual land cover dataset was proposed by the Yellow River Conservancy Commission (YRCC_LPLC) for the CLP from 1990 to 2022. Different levels of land cover were classified using different combinations of spectral, monthly and annual temporal and topographic features and Random Forest classifier. Compared to other land cover products (45.64%–73.38%), the accuracy of YRCC_LPLC has a better performance with an overall accuracy of 85.16%. The YRCC_LPLC is capable of capturing not only the explicit spatial variation but also the change direction and change time of land cover, especially for the most critical conversion of cropland into forest and grassland induced by implementation of Grain to Green Program on the CLP.</p>
Multi-decade land use and land cover samples for Brazil based in a stratified sampling design and visual interpretation of Landsat data (1985 — 2018)
<p>This dataset is composed by 85,152 random points throughout the Brazilian territory selected according to a stratified sampling design, based in 127 regular regions and six slope classes (<a href="https://www.usgs.gov/centers/eros/science/usgs-eros-archive-digital-elevation-shuttle-radar-topography-mission-srtm-1-arc?qt-science_center_objects=0#qt-science_center_objects">SRTM</a>). Each sample was visually inspected by three independent interpreters, which associated all the land use and land cover (LULC) changes between 1985 and 2018, on a <strong>yearly basis</strong>, using as reference two <strong>Landsat</strong> images per year, a <strong>MODIS</strong> NDVI time series and high resolution images from <strong>Google Earth</strong>. </p> <p>This process was guided by a <a href="https://www.lapig.iesa.ufg.br/chave/">reference labeling protocol</a> which established the follow LULC classes:</p> <ul> <li><strong>Annual crop:</strong> Areas occupied with short to medium-term crops, usually with a vegetative cycle of less than one year, which after harvest needs to be re-planted. </li> <li><strong>Aquaculture:</strong> Artificial lakes, where aquaculture and/or salt production activities predominate</li> <li><strong>Beach and dune (Other):</strong> Sandy areas, with bright white color, where there is no vegetation predominance of any kind.</li> <li><strong>Forest formation:</strong> Vegetation types with predominance of tree species, with continuous canopy formation</li> <li><strong>Grassland formation:</strong> Grassland formations with predominance of herbaceous stratum</li> <li><strong>Mangrove (Other):</strong> Dense and Evergreen Forest formations, often flooded by tide and associated with the mangrove coastal ecosystem.</li> <li><strong>Mining (Other):</strong> Areas where clear signs of extensive mineral extractions are present, shows clear exposure of the soil by the action of heavy machinery. Only regions surrounding the AhkBrasilien (AHK) and the CPRM digital reference data were considered.</li> <li><strong>Not observed:</strong> Areas blocked by clouds or atmospheric noise, or with absence of ground observation masked out from analysis.</li> <li><strong>Other non-forest natural formations:</strong> Marshes (with fluvio-marine influence).</li> <li><strong>Other non-vegetated area (Other):</strong> Non-permeable surface areas (infrastructure, urban expansion or mining) not mapped into their classes</li> <li><strong>Pasture:</strong> Pasture areas, natural or planted, related with farming activity. In particular in the Pampa and Pantanal biomes part of the area classified as Grassland Formation also includes pasture areas.</li> <li><strong>Perennial crop:</strong> Areas occupied with crops with a long cycle (more than one year), which allow successive harvests without the need for new crop. </li> <li><strong>Rocky outcrop (Other)</strong>: Naturally exposed rocks without soil cover, often with the partial presence of rupicolous vegetation and high slope. </li> <li><strong>Salt flat (Other):</strong> "Apicuns" or Salt flats are formations often without tree vegetation, associated to a higher, hypersaline and less flooded area in the mangrove, generally in the transition between this area and the continent.</li> <li><strong>Savanna formation:</strong> Savanna formations with defined tree and shrub-herbaceous stratum</li> <li><strong>Semi-perennial crop:</strong> Cultivated areas with sugar cane</li> <li><strong>Tree plantation:</strong> Planted tree species for commercial use (e.g. Eucalyptus, Pinus and Araucaria)</li> <li><strong>Urban infrastructure:</strong> Urban areas with predominance of non-vegetated surfaces, including roads, highways and constructions.</li> <li><strong>Water:</strong> Rivers, lakes, dams, reservoir and other water bodies</li> <li><strong>Wetland:</strong> Wetlands with fluvial influence or swampy areas</li> </ul> <p>To enable a proper area estimation and accuracy assessment (<a href="https://www.tandfonline.com/doi/abs/10.1080/01431161.2014.930207">Stehman, 2014</a>) the dataset is provided with the <strong>sampling probability</strong> for each sample (<em>brazil_lulc_samples_1985_2018</em> and <em>brazil_lulc_samples_1985_2018_row_wise</em>) and the <strong>sampling weight</strong> (<em>brazil_lulc_samples_1985_2018_row_wise</em>), which was adjusted to disregard the "<strong>Not observed" </strong>class. The number of votes for the associated LULC class (visual interpretation agreement) and an indication if the sample is between two different LULC<strong> </strong>classes (<strong>border flag</strong>) are also provided.</p> <p>The samples were used to produce several <strong><a href="https://github.com/lapig-ufg/tvi-analysis">area estimation analyses</a></strong>, including land use and land cover dynamics, historical deforestation and agricultural expansion of Brazil. A publication describing in detail the methodology and the analysis is under preparation.</p>
High resolution land cover 2016 Velika Gorica
<p>30cm Object based image analysis land cover dataset based on WorldView 3 and nDSM, stored as a .shp file.</p> <table> <tbody> <tr> <td> <p><strong>Class</strong></p> </td> <td> <p><strong>Vector </strong></p> <p><strong>NumCodec</strong></p> <p><strong>(16bit)</strong></p> </td> <td> <p><strong>Raster</strong></p> <p><strong>NumCodec</strong></p> <p><strong>(8bit)</strong></p> </td> </tr> <tr> <td> <p> </p> </td> <td> <p> </p> </td> <td> <p> </p> </td> </tr> <tr> <td> <p>Building</p> </td> <td> <p>100</p> </td> <td> <p>10</p> </td> </tr> <tr> <td> <p>0 Lowest rise building</p> </td> <td> <p>110</p> </td> <td> <p>11</p> </td> </tr> <tr> <td> <p>1 Low rise building</p> </td> <td> <p>120</p> </td> <td> <p>12</p> </td> </tr> <tr> <td> <p>2 Mid rise building</p> </td> <td> <p>130</p> </td> <td> <p>13</p> </td> </tr> <tr> <td> <p>3 High rise building</p> </td> <td> <p>140</p> </td> <td> <p>14</p> </td> </tr> <tr> <td> <p>4 Highest rise building</p> </td> <td> <p>150</p> </td> <td> <p>15</p> </td> </tr> <tr> <td> <p>Mineral surface</p> </td> <td> <p>210</p> </td> <td> <p>21</p> </td> </tr> <tr> <td> <p>Bare soil</p> </td> <td> <p>220</p> </td> <td> <p>22</p> </td> </tr> <tr> <td> <p>Artificial grass</p> </td> <td> <p>230</p> </td> <td> <p>23</p> </td> </tr> <tr> <td> <p>Grass</p> </td> <td> <p>310</p> </td> <td> <p>31</p> </td> </tr> <tr> <td> <p>Shrub round</p> </td> <td> <p>410</p> </td> <td> <p>41</p> </td> </tr> <tr> <td> <p>Shrub linear</p> </td> <td> <p>420</p> </td> <td> <p>42</p> </td> </tr> <tr> <td> <p>Evergreen</p> </td> <td> <p>510</p> </td> <td> <p>51</p> </td> </tr> <tr> <td> <p>Deciduous</p> </td> <td> <p>520</p> </td> <td> <p>52</p> </td> </tr> <tr> <td> <p>Lake</p> </td> <td> <p>610</p> </td> <td> <p>61</p> </td> </tr> <tr> <td> <p>River</p> </td> <td> <p>620</p> </td> <td> <p>62</p> </td> </tr> <tr> <td> <p>Sea</p> </td> <td> <p>630</p> </td> <td> <p>63</p> </td> </tr> <tr> <td> <p>Undergrowth</p> </td> <td> <p>710</p> </td> <td> <p>71</p> </td> </tr> <tr> <td> <p>Agriculture, intensive temporary crops</p> </td> <td> <p>810</p> </td> <td> <p>81</p> </td> </tr> <tr> <td> <p>Agriculture, intensive permanent crops</p> </td> <td> <p>820</p> </td> <td> <p>82</p> </td> </tr> <tr> <td> <p>Agriculture, extensive</p> </td> <td> <p>830</p> </td> <td> <p>83</p> </td> </tr> <tr> <td> <p>unclassified</p> </td> <td> <p>999</p> </td> <td> <p>99</p> </td> </tr> <tr> <td> <p>NonAOI</p> </td> <td> <p>999</p> </td> <td> <p>99</p> </td> </tr> </tbody> </table>
Annual land cover maps of Germany based on Sentinel-2 MSI Level 3A (WASP) data
<p>Overview:<br> This annual land cover product is available for the years 2016, 2019, 2020, 2021 for the whole of Germany. It was generated based on Sentinel-2 MSI L3A WASP Data provided by DLR (https://geoservice.dlr.de/data-assets/4hcq6dgkj648.html). For a complete description of the classification procedure please refer to<br> Riembauer, G.; Weinmann, A.; Xu, S.; Eichfuss, S.; Eberz, C.; Neteler, M.: Germany-wide Sentinel-2 based land cover classification and change detection for settlement and infrastructure monitoring. In: Proceedings of the 2021 conference on Big Data from Space (doi:10.2760/125905), 2021.</p> <p>Source data:</p> <ul> <li>Satellite data <ul> <li>German Aerospace Center (DLR): Sentinel-2 MSI - Level 3A (MAJA/WASP Tiles) - Germany, DOI: 10.15489/4hcq6dgkj648</li> </ul> </li> <li>Auxiliary data <ul> <li>European Union, Copernicus Land Monitoring Service, European Environment Agency (EEA), <strong>Copernicus High Resolution Layer: Imperviousness Status Map, 2018 </strong>(https://land.copernicus.eu/pan-european/high-resolution-layers/imperviousness/status-maps/imperviousness-density-2018)</li> <li><strong>OpenStreetMap</strong> Planet dump retrieved from https://planet.osm.org, https://www.openstreetmap.org</li> <li><strong>S2GLC Map of Europe</strong> (R. Malinowski, S. Lewiński, M. Rybicki, E. Gromny, M. Jenerowicz, M. Krupiński, A. Nowakowski, C. Wojtkowski, M. Krupiński, E. Krätzschmar, and P. Schauer, "Automated Production of a Land Cover/Use Map of Europe Based on Sentinel-2 Imagery," Remote Sensing, vol. 12, no. 21, p. 3523, 2020.)</li> </ul> </li> </ul> <p>File naming:<br> classification_map_germany_[year].tif example: classification_map_germany_2020.tif</p> <p>Projection + EPSG code:<br> WGS 84 / UTM zone 32N (EPSG: 32632)</p> <p>Spatial extent:<br> north: 55:03:38.646483N<br> south: 47:08:24.738401N<br> west: 5:33:47.816647E<br> east: 15:34:24.108516E</p> <p>Spatial resolution:<br> 10 m</p> <p>Format: COG (Cloud-Optimized GeoTIFF)</p> <p>Pixel values:<br> 10: forest<br> 20: low vegetation<br> 30: water<br> 40: built-up<br> 50: bare soil<br> 60: agriculture</p> <p>Temporal coverage:<br> Years 2016, 2019, 2020, 2021</p> <p>Software used:<br> GRASS 7.8, actinia</p> <p>Original dataset license:<br> The Sentinel-2 level 3A data produced and distributed by DLR are based on Copernicus Sentinel-2 level 1C data, which are subject to the following license: https://theia.cnes.fr/atdistrib/documents/TC_Sentinel_Data_31072014.pdf One of the following citations is mandatory for using the provided MAJA/WASP L3A product: German Aerospace Center (DLR): Sentinel-2 MSI - Level 3A (MAJA/WASP Tiles) - Germany, DOI: 10.15489/4hcq6dgkj648 or Contains modified Copernicus Sentinel data, processed by DLR, licensed under CC-BY 4.0</p> <p>Processed by:<br> mundialis GmbH & Co. KG, Germany (<a href="https://www.mundialis.de/">https://www.mundialis.de/</a>)</p>
Land Cover Fraction Mapping with FORCE - Supplemental Data
<p> </p> <p>This upload contains data required to replicate a <a href="https://github.com/franzschug/force/blob/develop/docs/source/howto/lcf.rst">tutorial </a>that applies regression-based unmixing of spectral-temporal metrics for sub-pixel land cover mapping with synthetically created training data. The tutorial uses the <a href="https://github.com/davidfrantz/force">Framework for Operational Radiometric Correction for Environmental monitoring</a>.</p> <p>This dataset contains intermediate and final results of the workflow described in that tutorial as well as auxiliary data such as parameter files.</p> <p>Please refer to the above mentioned tutorial for more information.</p> <p> </p>
Mapping ecosystem types and land cover types in the Seychelles granitic islands, using Earth Engine and Sentinel-2
<p>We share here maps produced using Earth Engine: https://code.earthengine.google.com/?accept_repo=users/bsenterre/gis</p> <p>The maps include a land cover classification based on Sentinel-2, at 10m resolution, using an Object-Based Image Analysis approach, for the Seychelles granitic islands. Based on the land cover, landform (modeled using TauDEM), altitude and expert knowledge, we then derived a model of ecosystem types, with 3 maps: current distribution, potential distribution and prehuman distribution.</p> <p>A report exists (18th May 2022) that describes in detail the methodology, and it is being used for the preparation of a publication. The maps uploaded here are in raster format (geotif), crs=4326, and are accompanied by QGIS legend files (.qml), so they should load in QGIS with their legend automatically.</p>
A hybrid 100-m global land cover dataset with Local Climate Zones for WRF
<p>This hybrid 100-m CGLC-MODIS-LCZ global land cover dataset is produced for the Weather Research and Forecasting (WRF) model starting from version 4.5. It is based on 1) the Copernicus Global Land Service Land Cover (CGLC, Buchhorn et al., 2021) product resampled to MODIS IGBP classes (CGLC-MODIS), and 2) the global map of Local Climate Zones (LCZ, Demuzere et al., 2022a, b) that describes the urban and built-up land surface. Both the CGLC and LCZ products are available at a 100-m spatial resolution, are representative for the year 2018, and cover -180°W to 180°E and -60°S to 78°N. Remaining areas are filled with the MODIS land cover classes. This dataset has been implemented into the WRF Preprocessing System (WPS) as <a href="https://www2.mmm.ucar.edu/wrf/users/download/get_sources_wps_geog.html">tiled binary data files</a> with <a href="https://github.com/wrf-model/WPS/blob/develop/geogrid/GEOGRID.TBL.ARW_LCZ">a new GEOGRID table entry</a> to allow WRF/WPS users to flexibly use this dataset in their studies particularly for urban modeling applications.</p> <p>To display the dataset in QGIS, <em>cmap_Qgis_CGLC_MOD_LCZ.txt </em>can be used as a color scheme.</p> <p>For more details, please read the technical documentation: <a href="https://doi.org/10.5281/zenodo.7670792">https://doi.org/10.5281/zenodo.7670792</a>.<br> <br> References:</p> <p><em>Buchhorn, M., Smets, B., Bertels, L., De Roo, B., Lesiv, M., Tsendbazar, N.-E., Li, L., Tarko, A. Copernicus Global Land Service: Land Cover 100m: version 3 Globe 2015-2019: Product User Manual (Dataset v3.0, doc issue 3.4). Product User Manual; Zenodo, Geneve, Switzerland, September 2020; doi: 10.5281/zenodo.3938963<br> <br> Demuzere M, Kittner J, Martilli A, et al. A global map of local climate zones to support earth system modelling and urban-scale environmental science. Earth Syst Sci Data. 2022a;14(8):3835-3873. doi:10.5194/essd-14-3835-2022</em></p> <p><em>Demuzere M, Kittner J, Martilli A, et al. (2022). Global map of Local Climate Zones (2.0.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.6364593</em></p>
Validation data set on land cover changes for RapidAI4EO project
<p>This is a reference data set collected for validation of the monthly land cover maps at a 3m and at a 10m resolution produced in the WP5. The reference data set has been collected by using Geo-Wiki toolbox for visual interpretation of very high-resolution images, including Planet data and Google maps. The data set has been collected over 3 AOIs. Each reference sample site corresponds to a 30m-by-30m box and includes information about monthly land cover type over the period 2018-2020. Land cover legend is the same as in ESA WorldCover map at a 10m resolution (https://worldcover2021.esa.int/).</p> <p>Fields:</p> <p>"rowid" – unique row identifier;</p> <p>"sampleid" – unique sample site identifier in the Geo-Wiki database;</p> <p>"samplegroupid" – group id with values 257(Portugal), 258 (Belgium), 259(Sicily);</p> <p>"x_min","x_max","y_min","y_max" – bounding box coordinates of each sample site (30m x 30m), in WGS84</p> <p>"X2018_1","X2018_2",…, "X2020_12" – dominant land cover class in each sample site in each month from January 2018 to December 2020;</p> <p>Land cover codes:</p> <p>10 – Tree cover</p> <p>20 - Shrubland</p> <p>30 - Grassland</p> <p>40 - Cropland</p> <p>50 – Urban/built-up</p> <p>60 - Bare/Sparse vegetation</p> <p>80 - Water</p> <p>90 - Wetland</p> <p>110 - Burnt</p> <p>120 – Not sure</p>
Extracellular polymeric substances are closely related to land cover, microbial communities, and enzyme activity in tropical soils
<p>These are datasets and R codes linked to the paper: Extracellular polymeric substances are closely related to land cover, microbial communities, and enzyme activity in tropical soils. </p>
High resolution and high cadence time series of land surface categories, land use land cover, and land use land cover changes
<p>A prototype of monthly, 10 m resolution land surface categories, land use land cover (LULC) cover, and LULC change maps derived from Sentinel-2 data over three areas within Belgium, Portugal, and Sicily for the period 2018-2020. The LULC and LULC change maps were independently validated by IIASA. All products were generated within the framework of the RapidAI4EO project, funded from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 101004356.</p> <p>The data description can be found below. The validation report of the LULC and LULC change maps can be found in validation_LULC.pdf and validation_change.pdf, respectively, and the validation dataset can be found in Lesiv <em>et al.</em> (2023).</p> <p><strong>Data description</strong></p> <p>Increasing the cadence of the land cover updates from the typical (multi-)annual to monthly cadence poses several challenges. First, several land cover types are difficult to discriminate without any knowledge of temporal dynamics. For instance, croplands are characterized by a dynamic of vegetation growth and a harvest period (i.e. cycles of bare soil, sparsely vegetated and vegetated periods). This contrasts with grasslands that often lack the harvest period resulting in a bare soil cover. Without this temporal information, it is difficult to distinguish a vegetated cropland field from grassland. Second, phenological changes may introduce a large intra-class variability and thus also confusion between classes. For example, the shedding of leaves during autumn or wilting of herbaceous vegetation in dry summer periods introduces spectral variability within land cover classes.</p> <p>To overcome these challenges, we developed a workflow with two main phases. The first phase aims to map land surface categories (LSC) at a monthly resolution. The next phase uses the resulting monthly LSC probability time series to classify land cover.</p> <p><strong><em>Land surface category (LSC)</em></strong></p> <p>These LSC represent basic, observable bio-geophysical properties (categories) of the Earth surface that can be predicted directly from individual monthly composites. LSC classes contain a set of vegetated and non-vegetated surface categories.</p> <p>Discrete LSC classification legend:</p> <table> <tbody> <tr> <td> <p>Map code</p> </td> <td> <p>Land cover class</p> </td> </tr> <tr> <td> <p>11</p> </td> <td> <p>Tree (leaf-on)</p> </td> </tr> <tr> <td> <p>12</p> </td> <td> <p>Shrubland (leaf-on)</p> </td> </tr> <tr> <td> <p>13</p> </td> <td> <p>Grassland</p> </td> </tr> <tr> <td> <p>14</p> </td> <td> <p>Woody vegetation (leaf-off)</p> </td> </tr> <tr> <td> <p>15</p> </td> <td> <p>Wilted herbaceous vegetation</p> </td> </tr> <tr> <td> <p>21</p> </td> <td> <p>Bare/sparse vegetation</p> </td> </tr> <tr> <td> <p>22</p> </td> <td> <p>Water</p> </td> </tr> <tr> <td> <p>24</p> </td> <td> <p>Built-up</p> </td> </tr> </tbody> </table> <p>In order to predict the LSC, we trained a CatBoost model (Dorogush et al., 2018) using a DEM, spectral bands and vegetation indices, country, the timing (month) of the spectral data, and the pseudo-probability of a U-Net model trained to segment built-up surfaces as input. Labels were derived by post-processing the land cover labels of the ESA WorldCover product (Zanaga et al., 2021). Please note that the collection of these labels was suboptimal, likely having an impact on the LULC and change maps generated in the prototype.</p> <p><strong><em>Land use land cover</em></strong></p> <p>After predicting LSC over the three AOI’s, we trained a CatBoost model using the LSC probabilities over a window of one year, country, and the timing (month) as independent variable. The use of LSC probabilities over multiple months allows to incorporate information about dynamics, which is necessary to discriminate some classes (e.g. cropland and grassland or cropland and bare). Similar to the LSC labels, the LULC labels were derived from the ESA WorldCover product v100 (year 2020), resulting in a similar legend system.</p> <p>The use of a moving window approach to predict LULC allows to (i) incorporate temporal information that is necessary to discriminate land cover classes and (ii) is expected to lead to more consistent land cover maps. It however has the disadvantage that (i) no land cover predictions are available at the beginning and the end of the time series and (ii) the timing of the predicted land cover change is not always accurate. To resolve these issues, we applied a post-processing step that compares and integrates the LULC predictions and cleaned LSC predictions.</p> <p>Discrete LC classification legend:</p> <table> <tbody> <tr> <td> <p><strong>Map code</strong></p> </td> <td> <p><strong>Land cover class</strong></p> </td> </tr> <tr> <td> <p>10</p> </td> <td> <p>Tree cover</p> </td> </tr> <tr> <td> <p>20</p> </td> <td> <p>Shrubland</p> </td> </tr> <tr> <td> <p>30</p> </td> <td> <p>Grassland</p> </td> </tr> <tr> <td> <p>40</p> </td> <td> <p>Cropland</p> </td> </tr> <tr> <td> <p>50</p> </td> <td> <p>Built-up</p> </td> </tr> <tr> <td> <p>60</p> </td> <td> <p>Bare/sparse vegetation</p> </td> </tr> <tr> <td> <p>80</p> </td> <td> <p>Permanent water bodies</p> </td> </tr> <tr> <td> <p>90</p> </td> <td> <p>Herbaceous wetland</p> </td> </tr> </tbody> </table> <p><strong><em>Land use land cover change </em></strong></p> <p>Monthly change maps were finally derived from the land cover maps. The pixel values within the change maps represent the percentage of pixels that changed with respect to the previous month over an area of 90x90m. The maps contain values between 0-100, with larger values assigned to larger change patches. A value of 100 indicates that all pixels within an area of 90x90m around the pixel were flagged as change.</p> <p><strong><em>Files</em></strong></p> <p>The zip files contain the following data:</p> <ul> <li>lsc.zip: land surface category maps over the three AOI’s</li> <li>lc.zip: LULC maps over the three AOI’s</li> <li>change.zip: change maps over the three AOI’s</li> </ul> <p>These maps are generated for each month over the period 2018-2020 for each of the tiles (see tiles.gpkg for an overview of all tiles). The files names use the following naming convention: “<em>tile</em>-<em>year</em>-<em>month</em>.tif”.</p> <p><strong><em>References</em></strong></p> <p>Myroslava Lesiv, Halyna Bun, & Martina Duerauer. (2023). Validation data set on land cover changes for RapidAI4EO project [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7825963 </p> <p>Dorogush, A. V., Ershov, V., & Gulin, A. (2018). CatBoost: gradient boosting with categorical features support. arXiv preprint arXiv:1810.11363.</p> <p><em>Zanaga, D., </em><em>et al.</em><em>., 2021. ESA WorldCover 10 m 2020 v100. </em><a href="https://doi.org/10.5281/zenodo.5571936 "><em>https://doi.org/10.5281/zenodo.5571936 </em></a></p>
Map Of Land Cover Agreement - MOLCA
<p>Map Of Land Cover Agreement (MOLCA) is generated by reusing existing datasets for High-Resolution Land Cover (HRLC), but only select portions with unanimous agreement among multiple datasets. We combined multiple HRLCs using intersection methods, retaining only the areas where all datasets agree on the land cover classes and disregarding areas of disagreement. The following HRLCs were used:</p> <ul> <li>FROM-GLC 2017 (<a href="http://data.ess.tsinghua.edu.cn/">[1]</a><a href="https://doi.org/10.1080/01431161.2012.748992">[2]</a><a href="https://doi.org/10.1016/j.scib.2017.03.011">[3]</a><a href="https://doi.org/10.1016/j.scib.2019.03.002">[4]</a>),</li> <li>GL30 2020 (<a href="http://www.globallandcover.com/">[5]</a><a href="https://doi.org/10.1016/j.isprsjprs.2014.09.002">[6]</a>),</li> <li>GHS BU S1NODSM 2016 (<a href="https://doi.org/10.1080/20964471.2017.1397899">[7]</a><a href="https://doi.org/10.3390/rs8040299">[8]</a>),</li> <li>WSF 2019 (<a href="https://geoservice.dlr.de/web/maps/eoc:wsf2019">[9]</a><a href="https://doi.org/10.6084/M9.FIGSHARE.C.4712852.V1">[10]</a><a href="https://doi.org/10.1553/giscience2021_01_s33">[11]</a>),</li> <li>GSW 2019 (<a href="https://global-surface-water.appspot.com/">[12]</a><a href="https://doi.org/10.1038/nature20584">[13]</a>),</li> <li>FNF 2018 (<a href="https://earth.jaxa.jp/en/data/2555/index.html">[14]</a><a href="https://doi.org/10.1016/j.rse.2014.04.014">[15]</a>),</li> <li>MapBiomas 2019 (<a href="https://doi.org/10.3390/rs12172735">[16]</a><a href="https://mapbiomas.org/en/accuracy-statistics?cama_set_language=en">[17]</a>),</li> <li>CCI Africa Prototype 2016 (<a href="https://2016africalandcover20m.esrin.esa.int/">[18]</a><a href="https://iiasa.dev.local/">[19]</a>),</li> <li>ESA DUE GlobPermafrost 2016 (<a href="https://doi.org/10.13140/RG.2.2.30661.76007">[20]</a><a href="https://doi.org/10.1594/PANGAEA.897916">[21]</a></li> </ul> <p> MOLCA contains around 117 billion 10-meter pixels (covering about 11.7 million square kilometers) distributed across a total area of 19 million square kilometers. It is available for 3 macro-regions in Siberia, Africa, and Amazon. The land cover classes represented in MOLCA are Bareland, Built-up, Cropland, Forest, Grassland, Shrubland, Water, Wetland, and Permanent ice and snow, covering the period between 2016 and 2020 The accuracy estimate for MOLCA indicates an Overall Accuracy (OA) of 96%. </p> <p>The repository contains:</p> <ul> <li><strong>MOLCA_<em>nnxxx</em>_v1.tif </strong>x 2075: 2075 MOLCA tiles (893 in Africa, 658 in Amazon, 524 in Siberia). Tiles of MOLCA follow the Sentinel-2 Level-1C product tiling grid, and consequently, the identifier of MOLCA tiles (<em>nnxxx</em>) is the same as the corresponding Sentinel-2 Level-1C tile identifier. </li> <li><strong>MOLCA_tiles_with_statistics.gpkg</strong>: Vector of MOLCA tile extents with statistics (number of pixels per class, total number of pixels, proportion of valid values) of each tile in the attribute table.</li> <li><strong>MOLCA_legend.csv</strong>: Class code and labels of MOLCA</li> </ul> <p> </p> <p>The creation of the MOLCA dataset was done in the project Climate Change Initiative Extension (CCI+) Phase 1 New Essential Climate Variables (NEW ECVS) High Resolution Land Cover ECV (HR_LandCover_cci) funded by the European Space Agency (ESA) known under the abbreviation CCI HRLC or CCI+ HRLC <a href="https://climate esa int/en/projects/high-resolution-land-cover/">[22]</a>.</p>
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.