NASA's Making Earth System Data Records for Use in Research Environments (MEaSUREs) Global Land Cover Mapping and Estimation (GLanCE) annual 30 meter (m) Version 1 data product provides global land cover and land cover change data derived from Landsat 5 Thematic Mapper (TM), Landsat 7 Enhanced Thematic Mapper Plus (ETM+), and Landsat 8 Operational Land Imager (OLI). These maps provide the user community with land cover type, land cover change, metrics characterizing the magnitude and seasonality of greenness of each pixel, and the magnitude of change. GLanCE data products will be provided using a set of seven continental grids that use Lambert Azimuthal Equal Area projections parameterized to minimize distortion for each continent. Currently, North America, South America, Europe, and Oceania are available. This dataset is useful for a wide range of applications, including ecosystem, climate, and hydrologic modeling; monitoring the response of terrestrial ecosystems to climate change; carbon accounting; and land management. The GLanCE data product provides seven layers: the land cover class, the estimated day of year of change, integer identifier for class in previous year, median and amplitude of the Enhanced Vegetation Index (EVI2) in the year, rate of change in EVI2, and the change in EVI2 median from previous year to current year. A low-resolution browse image representing EVI2 amplitude is also available for each granule.Known Issues Version 1.0 of the data set does not include Quality Assurance, Leaf Type or Leaf Phenology. These layers are populated with fill values. These layers will be included in future releases of the data product. * Science Data Set (SDS) values may be missing, or of lower quality, at years when land cover change occurs. This issue is a by-product of the fact that Continuous Change Detection and Classification (CCDC) does not fit models or provide synthetic reflectance values during short periods of time between time segments. * The accuracy of mapping results varies by land cover class and geography. Specifically, distinguishing between shrubs and herbaceous cover is challenging at high latitudes and in arid and semi-arid regions. Hence, the accuracy of shrub cover, herbaceous cover, and to some degree bare cover, is lower than for other classes. * Due to the combined effects of large solar zenith angles, short growing seasons, lower availability of high-resolution imagery to support training data, the representation of land cover at land high latitudes in the GLanCE product is lower than in mid latitudes. * Shadows and large variation in local zenith angles decrease the accuracy of the GLanCE product in regions with complex topography, especially at high latitudes. * Mapping results may include artifacts from variation in data density in overlap zones between Landsat scenes relative to mapping results in non-overlap zones. * Regions with low observation density due to cloud cover, especially in the tropics, and/or poor data density (e.g. Alaska, Siberia, West Africa) have lower map quality. * Artifacts from the Landsat 7 Scan Line Corrector failure are occasionally evident in the GLanCE map product. High proportions of missing data in regions with snow and ice at high elevations result in missing data in the GLanCE SDSs.* The GlanCE data product tends to modestly overpredict developed land cover in arid regions.

The dataset is on a global scale with a resolution of 1 km grid and encompasses a timespan from 2020 to 2100. These data are projected in the world-Mercator projection coordinate system and are provided in single-band GeoTIFF format, which can be easily utilized by various mainstream GIS and RS platforms such as ArcGIS, QGIS, ENVI, as well as programming languages such as Python and MATLAB. The simulated data files follow a standardized naming convention “sspx_pp_yyyy.tif”, where x represents the simulated SSP scenario (1 to 5), pp represents the simulated RCP scenario; and yyyy represents the simulated year. For example, the data file named “ssp1_26_2030.tif” corresponds to the LULC simulation data for the year 2030 under the SSP1-2.6 scenario. Each GeoTIFF data file includes integer raster attribute values ranging from 1 to 6, which represent the following land use types: cropland, forest, grassland, urban, barren, and water.

Source of Imagery

Our strategy is to reuse images from existing benchmark datasets as much as possible and manually annotate new land cover labels. We selected xBD, Inria, Open Cities AI, SpaceNet, Landcover.ai, AIRS, GeoNRW, and HTCD datasets. For countries and regions not covered by the existing datasets, aerial images publicly available in such countries or regions were collected to mitigate the regional gap, which is an issue in most of the existing benchmark datasets. The open data were downloaded from OpenAerialMap and geospatial agencies in Peru and Japan. The attribution of source data is summarized here.

Classes and Annotations

We provide annotations with eight classes: bareland, rangeland, developed space, road, tree, water, agriculture land, and building. Their color and proportion of pixels are summarized below. All the labeling was done manually, and it took 2.5 hours per image on average.

License of Labels in OpenEarthMap

Label data of OpenEarthMap are provided under the same license as the original RGB images, which varies with each source dataset. For more details, please see the attribution of source data here. Label data for regions where the original RGB images are in the public domain or where the license is not explicitly stated are licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Reference

@inproceedings{xia_2023_openearthmap,

title = {OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping},

author = {Junshi Xia and Naoto Yokoya and Bruno Adriano and Clifford Broni-Bediako},

booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},

month = {January},

year = {2023},

pages = {6254-6264}

}

HILDA+ version 2.0 is an updated version of the HILDA+ (HIstoric Land Dynamics Assessment+) doi:10.1594/PANGAEA.921846. It is a global dataset on annual land use/cover change between 1960-2020 at 1 km spatial resolution. It is based on a data-driven reconstruction approach and integrates multiple open data streams (from high-resolution remote sensing, long-term land use reconstructions and statistics). Compared to the previous version, this new HILDA+ version 2.0 uses a base map from the year 2020 (based on ESA World Cover), integrates new remote sensing-based land cover datasets (see documentation sheet in the uploaded data), is calibrated on updated national land use statistics from FAO and includes additional cropland-related land use categories: tree crops, agroforestry and annual crops. See the documentation and the paper reference for the method of cropland mapping. Forests are subdivided into different forest types based ESA CCI Land Cover (1992-2020). HILDA+ version 2.0 covers the following land use/cover categories (given with their respective code numbers in the dataset): 11: Urban areas, 22: Annual crops, 23: Tree crops, 24: Agroforestry, 33: Pasture/rangeland, 40: Forest (unknown/other), 41: Forest (evergreen, needle leaf), 42: Forest (evergreen, broad leaf), 43: Forest (deciduous, needle leaf), 44: Forest (deciduous, broad leaf), 45: Forest (mixed), 55: Unmanaged grass/shrubland, 66: Sparse/no vegetation.

This layer displays a global map of land use/land cover (LULC) derived from ESA Sentinel-2 imagery at 10m resolution. Each year is generated with Impact Observatory’s deep learning AI land classification model, trained using billions of human-labeled image pixels from the National Geographic Society. The global maps are produced by applying this model to the Sentinel-2 Level-2A image collection on Microsoft’s Planetary Computer, processing over 400,000 Earth observations per year.The algorithm generates LULC predictions for nine classes, described in detail below. The year 2017 has a land cover class assigned for every pixel, but its class is based upon fewer images than the other years. The years 2018-2024 are based upon a more complete set of imagery. For this reason, the year 2017 may have less accurate land cover class assignments than the years 2018-2024. Key Properties Variable mapped: Land use/land cover in 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024Source Data Coordinate System: Universal Transverse Mercator (UTM) WGS84Service Coordinate System: Web Mercator Auxiliary Sphere WGS84 (EPSG:3857)Extent: GlobalSource imagery: Sentinel-2 L2ACell Size: 10-metersType: ThematicAttribution: Esri, Impact ObservatoryAnalysis: Optimized for analysisClass Definitions: ValueNameDescription1WaterAreas where water was predominantly present throughout the year; may not cover areas with sporadic or ephemeral water; contains little to no sparse vegetation, no rock outcrop nor built up features like docks; examples: rivers, ponds, lakes, oceans, flooded salt plains.2TreesAny significant clustering of tall (~15 feet or higher) dense vegetation, typically with a closed or dense canopy; examples: wooded vegetation, clusters of dense tall vegetation within savannas, plantations, swamp or mangroves (dense/tall vegetation with ephemeral water or canopy too thick to detect water underneath).4Flooded vegetationAreas of any type of vegetation with obvious intermixing of water throughout a majority of the year; seasonally flooded area that is a mix of grass/shrub/trees/bare ground; examples: flooded mangroves, emergent vegetation, rice paddies and other heavily irrigated and inundated agriculture.5CropsHuman planted/plotted cereals, grasses, and crops not at tree height; examples: corn, wheat, soy, fallow plots of structured land.7Built AreaHuman made structures; major road and rail networks; large homogenous impervious surfaces including parking structures, office buildings and residential housing; examples: houses, dense villages / towns / cities, paved roads, asphalt.8Bare groundAreas of rock or soil with very sparse to no vegetation for the entire year; large areas of sand and deserts with no to little vegetation; examples: exposed rock or soil, desert and sand dunes, dry salt flats/pans, dried lake beds, mines.9Snow/IceLarge homogenous areas of permanent snow or ice, typically only in mountain areas or highest latitudes; examples: glaciers, permanent snowpack, snow fields.10CloudsNo land cover information due to persistent cloud cover.11RangelandOpen areas covered in homogenous grasses with little to no taller vegetation; wild cereals and grasses with no obvious human plotting (i.e., not a plotted field); examples: natural meadows and fields with sparse to no tree cover, open savanna with few to no trees, parks/golf courses/lawns, pastures. Mix of small clusters of plants or single plants dispersed on a landscape that shows exposed soil or rock; scrub-filled clearings within dense forests that are clearly not taller than trees; examples: moderate to sparse cover of bushes, shrubs and tufts of grass, savannas with very sparse grasses, trees or other plants.NOTE: Land use focus does not provide the spatial detail of a land cover map. As such, for the built area classification, yards, parks, and groves will appear as built area rather than trees or rangeland classes.Usage Information and Best PracticesProcessing TemplatesThis layer includes a number of preconfigured processing templates (raster function templates) to provide on-the-fly data rendering and class isolation for visualization and analysis. Each processing template includes labels and descriptions to characterize the intended usage. This may include for visualization, for analysis, or for both visualization and analysis. VisualizationThe default rendering on this layer displays all classes.There are a number of on-the-fly renderings/processing templates designed specifically for data visualization.By default, the most recent year is displayed. To discover and isolate specific years for visualization in Map Viewer, try using the Image Collection Explorer. AnalysisIn order to leverage the optimization for analysis, the capability must be enabled by your ArcGIS organization administrator. More information on enabling this feature can be found in the ‘Regional data hosting’ section of this help doc.Optimized for analysis means this layer does not have size constraints for analysis and it is recommended for multisource analysis with other layers optimized for analysis. See this group for a complete list of imagery layers optimized for analysis.Prior to running analysis, users should always provide some form of data selection with either a layer filter (e.g. for a specific date range, cloud cover percent, mission, etc.) or by selecting specific images. To discover and isolate specific images for analysis in Map Viewer, try using the Image Collection Explorer.Zonal Statistics is a common tool used for understanding the composition of a specified area by reporting the total estimates for each of the classes. GeneralIf you are new to Sentinel-2 LULC, the Sentinel-2 Land Cover Explorer provides a good introductory user experience for working with this imagery layer. For more information, see this Quick Start Guide.Global land use/land cover maps provide information on conservation planning, food security, and hydrologic modeling, among other things. This dataset can be used to visualize land use/land cover anywhere on Earth. Classification ProcessThese maps include Version 003 of the global Sentinel-2 land use/land cover data product. It is produced by a deep learning model trained using over five billion hand-labeled Sentinel-2 pixels, sampled from over 20,000 sites distributed across all major biomes of the world.The underlying deep learning model uses 6-bands of Sentinel-2 L2A surface reflectance data: visible blue, green, red, near infrared, and two shortwave infrared bands. To create the final map, the model is run on multiple dates of imagery throughout the year, and the outputs are composited into a final representative map for each year.The input Sentinel-2 L2A data was accessed via Microsoft’s Planetary Computer and scaled using Microsoft Azure Batch. CitationKarra, Kontgis, et al. “Global land use/land cover with Sentinel-2 and deep learning.” IGARSS 2021-2021 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2021.AcknowledgementsTraining data for this project makes use of the National Geographic Society Dynamic World training dataset, produced for the Dynamic World Project by National Geographic Society in partnership with Google and the World Resources Institute.

We (Intelligent Mining and Analysis of Remote Sensing big data, IMARS) create a large-scale annotated dataset (Globe230k) for land use/land cover (LULC) mapping, which is annotated on Google Earth image of 1 m spatial resolution. Globe230k is annotated by numerous experts and students major in survey and mapping after necessary training, through visual interpretation on very high-resolution images, as well as in-situ field survey, under the guidance of the organized annotation pipeline. Globe230k has three superiorities:

1) Large scale: the Globe230k includes 232,819 annotated images with the size of 512x512 and spatial resolution of 1 m, with more than 3x1010 annotated pixels, and it includes 10 first-level categories.

2) Rich diversity: the annotated images are sampled from worldwide regions, with coverage area of over 60,000 km2, indicating a high variability and diversity. Besides, in order to ensure the category balance, we intentionally give more chance to the rare categories to be sampled, such as wetland, ice/snow, etc.

3) Multi-modal: Globe230k not only contains RGB bands, but also include other important features for Earth system research, such as Normalized differential vegetation index (NDVI), digital elevation model (DEM), vertical-vertical polarization (VV) bands, vertical-horizontal polarization (VH) bands, which can facilitate the multi-modal data fusion research. Due to the large size of the multi-modal dataset (DEM 1.91G, NDVI 164G, VVVH 372G), these dataset are stored on Baidu Yunpan, the download link is :https://pan.baidu.com/s/12AKbiqOXSf4fnm7mYkCE0g?pwd=230k, the extraction code is 230k.

The image patches and their corresponding annotated patches are respectively stored in "image_patch.zip" and "label_patch.zip" file. The RGB image is in forms of ".jpg", with size of 512x512, the pixel value is ranged from 0-255. The annotated patches is in forms of ".png", also with size of 512x512, the pixel value is ranged from 1-10, which respectively represent 1#cropland, 2#forest, 3#grass, 4#shrubland, 5#wetland, 6#water, 7#tundra, 8#impervious, 9#bareland, 10#ice/snow. The corresponding DEM, NDVI and VVVH patches are all in form of ".tif", with size of 512x512 (due to the different resolution of DEM, NDVI and VVVH patches, they are all uniformly resized to the same scale as the image patch).

The total 232,819 pairs are officially divided into training set, validation set, and test set, based on ratio of 7:1:2, which can be find in "train_num.txt","val_num.txt","test_num.txt" file. Based on this division, the official baseline accuracy of several state-of-the-art semantic segmentation can be found in the related arcticle (https://spj.science.org/doi/10.34133/remotesensing.0078).

We hope it can be used as a benchmark to promote further development of global land cover mapping and semantic segmentation algorithm development.

The Advanced Very High Resolution Radiometer (AVHRR) 1-km Global Land 10-Day Composites data set project is a component of the National Aeronautics and Space Administration (NASA) AVHRR Pathfinder Program. The project is a collaborative effort between the National Oceanic and Atmospheric Administration (NOAA), NASA, the U.S. Geological Survey (USGS), the European Space Agency (ESA), Australia's Commonwealth Scientific and Industrial Research Organization (CSIRO), and 30 international ground receiving stations. The project represents an international effort to archive and distribute the 1-km AVHRR composites of the entire global land surface to scientific researchers and to the general public.

The data set is comprised of a time series of global 10-day normalized difference vegetation index composites. The composites are generated from radiometrically calibrated, atmospherically corrected, and geometrically corrected daily AVHRR observations. The time series begins in April 1992 and continues for specific time periods.

The USGS’s FORE-SCE model was used to produce a long-term landscape dataset for the Delaware River Basin (DRB). Using historical landscape reconstruction and scenario-based future projections, the data provided land-use and land-cover (LULC) data for the DRB from year 1680 through 2100, with future projections from 2020-2100 modeled for 7 different socioeconomic-based scenarios, and 3 climate realizations for each socioeconomic scenario (21 scenario combinations in total). The projections are characterized by 1) high spatial resolution (30-meter cells), 2) high thematic resolution (20 land use and land cover classes), 3) broad spatial extent (covering the entirety of the Delaware River basin, corresponding to USGS HUC codes 020401 and 020402), 4) use of real land ownership boundaries to ensure realistic representation of landscape patterns, and 5) representation of both anthropogenic land use and natural vegetation change that respond to projected climate change. Data are provided in 10-year time steps from 1680 through 2100 (43 individual dates). Historical landscape data is provided in one downloadable zip file, containing 34 individual land cover datasets for 10-year intervals from 1680 through 2010. “Current” (2020) and “future” (2030 through 2100) data are provided at 10-year time steps in files corresponding to the 21 different scenario combinations. The following provides a brief summary of the 7 major land-use scenarios. 1) Business-as-usual - Based on an extrapolation of recent land-cover trends as derived from remote-sensing data. Overall trends were provided by 2001 to 2016 change in the National Land Cover Database, while change in crop types were extrapolated from 2008 to 2018 change in the Cropland Data Layer. 2) Billion Ton Update (BTU) scenario ($40 farmgate price) - This scenario is based on US Department of Energy biofuel scenarios from the BTU. The $40 scenario represents likely agricultural conditions under an assumed farmgate price of $40 per dry ton of biomass (for the production of biofuel). All three BTU scenarios include the representation of a “perennial grass” class (class #20) that represents grass crops such as miscanthus, switchgrass, or prairie grasses grown for production of cellulosic biofuel. 3) BTU scenario ($60 farmgate price) - This scenario is based on US Department of Energy biofuel scenarios from the BTU. The $60 scenario represents likely agricultural conditions under an assumed farmgate price of $60 per dry ton of biomass (for the production of biofuel). 4) BTU scenario ($80 farmgate price) - This scenario is based on US Department of Energy biofuel scenarios from the BTU. The $80 scenario represents likely agricultural conditions under an assumed farmgate price of $80 per dry ton of biomass (for the production of biofuel). 5) Global Change Analysis Model (GCAM) Reference scenario - Based on global-scale scenarios from the GCAM model, the "reference" scenario provides a likely landscape under a world without specific carbon or climate mitigation efforts. As such, it's another form of a "business-as-usual" scenario. 6) GCAM 2.6 scenario - Based on global-scale scenarios from the GCAM model, the GCAM 2.6 model represents a very aggressive climate mitigation scenario, where carbon payments and other mitigation efforts result in a net radiative forcing of only ~2.6 W/m2 by 2100. 7) GCAM 4.5 scenario - Based on global-scale scenarios from the GCAM model, the GCAM 4.5 model represents a mid-level climate mitigation scenario, where carbon payments and other mitigation efforts result in a net radiative forcing of ~4.5 W/m2 by 2100. For each of the 7 land-use scenarios, three alternative climate / vegetation scenarios were modeled, resulting in 21 unique scenario combinations. The alternative vegetation scenarios represent the potential changes in quantity and distribution of the major vegetation classes that were modeled (grassland, shrubland, deciduous forest, mixed forest, and evergreen forest), as a response to potential future climate conditions. The three alternative vegetation scenarios correspond to climate conditions consistent with 1) The Intergovernmental Panel on Climate Change (IPCC's) Representative Concentration Pathway (RCP) 8.5 scenario (a scenario of high climate change), 2) the RCP 4.5 scenario (a mid-level climate change scenario), and 3) a mid-point climate that averages RCP4.5 and RCP8.5 conditions Data are provided here as compressed ZIP files for 1) the historical landscape reconstruction time frame (1680 through 2010), and 2) for each of the 21 future scenario combinations, including the starting 2020 year and extending through 2100 (thus 22 downloadable ZIP files). The “attributes” section of the metadata provides a key for identifying file names associated with each of the scenario combinations and historical period.

The data set consists of a LBA study area subset of the IGBP DISCover Data Set. The DISCover data set is one data set contained within the Global Land Cover Characteristics Data Base. The U.S. Geological Survey (USGS), the University of Nebraska-Lincoln (UNL), and the European Commission's Joint Research Centre (JRC) have generated a 1-km resolution global land cover characteristics data base for use in a wide range of environmental research and modeling applications. The global land cover characteristics data base was developed on a continent-by-continent basis. All continental data bases share the same map projections (Interrupted Goode Homolosine and Lambert Azimuthal Equal Area), have 1-km nominal spatial resolution, and are based on 1-km Advanced Very High Resolution Radiometer (AVHRR) data spanning April 1992 through March 1993. Each data base contains unique elements based on the geographic aspects of the specific continent. In addition, a core set of derived thematic maps produced through the aggregation of seasonal land cover regions are included in each continental data base. The continental data bases are combined to make six global data sets, each representing a different landscape based on a particular classification legend. The following derived data sets are included in the global land cover data base: * Global Ecosystems (Olson, 1994a, 1994b) * IGBP Land Cover Classification (Belward, 1996) * U.S. Geological Survey Land Use/Land Cover System(Anderson & others, 1976) * Simple Biosphere Model (Sellers and others, 1986) * Simple Biosphere 2 Model (Sellers and others, 1996) * Biosphere-Atmosphere Transfer Scheme (Dickinson and others, 1986) The legends for each of these derived data sets can be found in the documentation accompanying the data. For a description of the methodology for the global data base, see the global readme file found under the EROS Data Center DAAC home page (http://edcwww.cr.usgs.gov/landdaac/glcc/glcc.html).

The objective of the International Satellite Land Surface Climatology Project (ISLSCP II) study that produced this data set, ISLSCP II University of Maryland Global Land Cover Classifications 1992-1993, was to create a land cover map derived from 1 kilometer Advanced Very High Resolution Radiometer (AVHRR) data using all available bands, derived Normalized Difference Vegetation Index (NDVI), and a full year of data (April 1992-March 1993). This thematic map was resampled to 0.25, 0.5 and 1.0 degree grids. During this re-processing, the original University of Maryland (UMD) land cover type and fraction maps were adjusted to match the water/land fraction of the ISLSCP II land/water mask. These maps were generated for use by modelers of global biogeochemical cycles and others in need of an internally consistent, global depiction of land cover. This 1km map was also one of the MODerate resolution Imaging Spectroradiometer (MODIS) at-launch land cover maps. This product describes the geographic distributions of 13 classes of vegetation cover (plus water and unclassified classes) based on a modified International Geosphere-Biosphere Programme (IGBP) legend. The data set also provides the fraction of each of the 15 classes within the coarser resolution cells, at three spatial resolutions of 0.25, 0.5 and 1.0 degrees in latitude and longitude.

Global land cover is an essential climate variable and a key biophysical driver for earth system models. While remote sensing technology, particularly satellites, have played a key role in providing land cover datasets, large discrepancies have been noted among the available products. Global land use is typically more difficult to map and in many cases cannot be remotely sensed. In-situ or ground-based data and high resolution imagery are thus an important requirement for producing accurate land cover and land use datasets and this is precisely what is lacking. Here we describe the global land cover and land use reference data derived from the Geo-Wiki crowdsourcing platform via four campaigns. These global datasets provide information on human impact, land cover disagreement, wilderness and land cover and land use. Hence, they are relevant for the scientific community that requires reference data for global satellite-derived products, as well as those interested in monitoring global terrestrial ecosystems in general.

Full data description can be found in the corresponding article Fritz et al (2017):
https://doi.org/10.1038/sdata.2017.75

Data Coverage:
Median Latitude: 23.136733 * Median Longitude: 21.642639 * South-bound Latitude: -60.537500 * West-bound Longitude: -179.837500 * North-bound Latitude: 83.437500 * East-bound Longitude: 179.962500

The data are 475 thematic land cover raster’s at 2m resolution. Land cover classification was to the land cover classes: Tree (1), Water (2), Barren (3), Other Vegetation (4) and Ice & Snow (8). Cloud cover and Shadow were sometimes coded as Cloud (5) and Shadow (6), however for any land cover application would be considered NoData. Some raster’s may have Cloud and Shadow pixels coded or recoded to NoData already. Commercial high-resolution satellite data was used to create the classifications. Usable image data for the target year (2010) was acquired for 475 of the 500 primary sample locations, with 90% of images acquired within ±2 years of the 2010 target. The remaining 25 of the 500 sample blocks had no usable data so were not able to be mapped. Tabular data is included with the raster classifications indicating the specific high-resolution sensor and date of acquisition for source imagery as well as the stratum to which that sample block belonged. Methods for this classification are described in Pengra et al. (2015). A 1-stage cluster sampling design was used where 500 (475 usable), 5 km x 5 km sample blocks were the primary sampling units (note; the nominal size was 5km x 5km blocks, but some have deviations in dimensions due only partial coverage of the sample block with usable imagery). Sample blocks were selected using stratified random sampling within a sample frame stratified by a modification of the Köppen Climate/Vegetation classification and population density (Olofsson et al., 2012). Secondary sampling units are each of the classified 2m pixels of the raster. This design satisfies the criteria that define a probability sampling design and thus serves as the basis to support rigorous design-based statistical inference (Stehman, 2000).

The GLCC from USGS is a landuse and land cover classification dataset based primarily on the unsupervised classification of the 1-km AVHRR (Advanced Very High-Resolution Radiometer) 10-day NDVI (Normalized Difference Vegetation Index) composites. The AVHRR source imagery dates from April 1992 through March 1993. The GLCC map contains 24 land cover types. Correspondence is made between the GLCC units and SWAT crop database based on the description of the land covers provided by the maps and the SWAT landuse definitions. The databases for the above two global landuse maps are supported by the table crop in the SWAT2012.mdb database and the lookup tables “Lookup_Landuse_Globcover.txt” and Lookup_Landuse_USGS.txt. The SWAT2012.mdb and look up tables could be downloaded in https://www.2w2e.com/

This dataset provides projections of land use and land cover (LULC) change within the Arctic Boreal Vulnerability Experiment (ABoVE) domain, spanning from 2015 to 2100 with a spatial resolution of 0.25 degrees. It includes LULC change under two Shared Socioeconomic Pathways (SSP126 and SSP585) derived from Global Change Analysis Model (GCAM) at an annual scale. The specific land types include: needleleaf evergreen tree-temperate, needleleaf evergreen tree-boreal, needleleaf deciduous tree-boreal, broadleaf evergreen tree-tropical, broadleaf evergreen tree-temperate, broadleaf deciduous tree-tropical, broadleaf deciduous tree-temperate, broadleaf deciduous tree-boreal, broadleaf evergreen shrub-temperate, broadleaf deciduous shrub-temperate, broadleaf deciduous shrub-boreal, C3 arctic grass, C3 grass, C4 grass, and C3 unmanaged rainfed crop. The data were generated by integrating regional LULC projections from GCAM with high-resolution MODIS land cover data and applying two alternative spatial downscaling models: FLUS and Demeter. Data are provided in NetCDF format.

This map features Africa Land Cover at 30m resolution from MDAUS BaseVue 2013, referencing the World Land Cover 30m BaseVue 2013 layer.Land cover data represent a descriptive thematic surface for characteristics of the land's surface such as densities or types of developed areas, agricultural lands, and natural vegetation regimes. Land cover data are the result of a model, so a good way to think of the values in each cell are as the predominating value rather than the only characteristic in that cell.Land use and land cover data are critical and fundamental for environmental monitoring, planning, and assessment.Dataset SummaryBaseVue 2013 is a commercial global, land use / land cover (LULC) product developed by MDA. BaseVue covers the Earth’s entire land area, excluding Antarctica. BaseVue is independently derived from roughly 9,200 Landsat 8 images and is the highest spatial resolution (30m), most current LULC product available. The capture dates for the Landsat 8 imagery range from April 11, 2013 to June 29, 2014. The following 16 classes of land use / land cover are listed by their cell value in this layer: Deciduous Forest: Trees > 3 meters in height, canopy closure >35% (<25% inter-mixture with evergreen species) that seasonally lose their leaves, except Larch.Evergreen Forest: Trees >3 meters in height, canopy closure >35% (<25% inter-mixture with deciduous species), of species that do not lose leaves. (will include coniferous Larch regardless of deciduous nature).Shrub/Scrub: Woody vegetation <3 meters in height, > 10% ground cover. Only collect >30% ground cover.Grassland: Herbaceous grasses, > 10% cover, including pasture lands. Only collect >30% cover.Barren or Minimal Vegetation: Land with minimal vegetation (<10%) including rock, sand, clay, beaches, quarries, strip mines, and gravel pits. Salt flats, playas, and non-tidal mud flats are also included when not inundated with water.Not Used (in other MDA products 6 represents urban areas or built up areas, which have been split here in into values 20 and 21).Agriculture, General: Cultivated crop landsAgriculture, Paddy: Crop lands characterized by inundation for a substantial portion of the growing seasonWetland: Areas where the water table is at or near the surface for a substantial portion of the growing season, including herbaceous and woody species (except mangrove species)Mangrove: Coastal (tropical wetlands) dominated by Mangrove speciesWater: All water bodies greater than 0.08 hectares (1 LS pixel) including oceans, lakes, ponds, rivers, and streamsIce / Snow: Land areas covered permanently or nearly permanent with ice or snowClouds: Areas where no land cover interpretation is possible due to obstruction from clouds, cloud shadows, smoke, haze, or satellite malfunctionWoody Wetlands: Areas where forest or shrubland vegetation accounts for greater than 20% of vegetative cover and the soil or substrate periodically is saturated with, or covered by water. Only used within the continental U.S.Mixed Forest: Areas dominated by trees generally greater than 5 meters tall, and greater than 20% of total vegetation cover. Neither deciduous nor evergreen species are greater than 75% of total tree cover. Only used within the continental U.S.Not UsedNot UsedNot UsedNot UsedHigh Density Urban: Areas with over 70% of constructed materials that are a minimum of 60 meters wide (asphalt, concrete, buildings, etc.). Includes residential areas with a mixture of constructed materials and vegetation where constructed materials account for >60%. Commercial, industrial, and transportation i.e., Train stations, airports, etc.Medium-Low Density Urban: Areas with 30%-70% of constructed materials that are a minimum of 60 meters wide (asphalt, concrete, buildings, etc.). Includes residential areas with a mixture of constructed materials and vegetation, where constructed materials account for greater than 40%. Commercial, industrial, and transportation i.e., Train stations, airports, etc.MDA updated the underlying data in late 2016 and this service was updated in February 2017. An improved selection of cloud-free images was used to produce the update, resulting in improvement of classification quality to 80% of the tiles for this service.What can you do with this layer?This layer can be used to create maps and to visualize the underlying data across the ArcGIS platform. It can also be used as an analytic input in ArcMap and ArcGIS Pro.This layer has query, identify, and export image services available. The layer is restricted to an 16,000 x 16,000 pixel limit, which represents an area of nearly 300 miles on a side. This layer is part of a larger collection of landscape layers that you can use to perform a wide variety of mapping and analysis tasks.

This dataset provides global maps describing the land surface into 22 classes, which have been defined using the United Nations Food and Agriculture Organization’s (UN FAO) Land Cover Classification System (LCCS). In addition to the land cover (LC) maps, four quality flags are produced to document the reliability of the classification and change detection. In order to ensure continuity, these land cover maps are consistent with the series of global annual LC maps from the 1990s to 2015 produced by the European Space Agency (ESA) Climate Change Initiative (CCI), which are also available on the ESA CCI LC viewer. To produce this dataset, the entire Medium Resolution Imaging Spectrometer (MERIS) Full and Reduced Resolution archive from 2003 to 2012 was first classified into a unique 10-year baseline LC map. This is then back- and up-dated using change detected from (i) Advanced Very-High-Resolution Radiometer (AVHRR) time series from 1992 to 1999, (ii) SPOT-Vegetation (SPOT-VGT) time series from 1998 to 2012 and (iii) PROBA-Vegetation (PROBA-V), Sentinel-3 OLCI (S3 OLCI) and Sentinel-3 SLSTR (S3 SLSTR) time series from 2013. Beyond the climate-modelling communities, this dataset’s long-term consistency, yearly updates, and high thematic detail on a global scale have made it attractive for a multitude of applications such as land accounting, forest monitoring and desertification, in addition to scientific research.

Land cover refers to the physical and biological cover over the surface of land, including water, vegetation, bare soil, and/or artificial structures. Land use usually refers to signs of human activities such as agriculture, forestry and building construction that altered the original land surface processes. The Land Use / Land Cover (LULC) maps were developed using remotely sensed data (i.e., satellite imagery) of different resolution and vintage and validated with the aid of some ground truthing, virtual truthing (using high-resolution imagery of more recent vintage and other internet resources), agriculture census, and other ancillary data collected during the course of the project. Preliminary interpretation of the Land Use / Land Cover (LULC) data from the satellite imagery was carried out by using an image classification algorithm and was enhanced by using imagery parameters such as tone, texture, pattern, size, shape and contextual association. This process was further improved using onscreen digitization of the known crops on high resolution satellite imagery. A Normalized Difference Vegetation Index (NDVI) was generated and used for classifying forest areas classification into dense, open, or shrub forests. Given the methodology adopted, it is to be expected that in some instances the information included in the LULC maps may be obsolete and inaccurate. The LULC maps developed are suitable for the scope of assessing wind and flood hazard (roughness factors and precipitation runoff percentages) as well establishing a crop exposure database. Data Sources: Publically available EO-1, LandSat imagery, partial coverage 10m SPOT, others. Compiled by AIR Worldwide.

This data set is a subset of Hansen et al. (1999), "1 km Global Land Cover Data Set Derived from AVHRR," which was developed at the Laboratory for Global Remote Sensing Studies (LGRSS) at the University of Maryland. This subset was created for the study area of the Large Scale Biosphere-Atmosphere Experiment in Amazonia (LBA) in South America (i.e., latitude 10 N to 25 S, longitude 30 to 85 W). The data are in ASCII GRID file format.In recent years, researchers have increasingly turned to remotely sensed data to improve the accuracy of data sets that describe the geographic distribution of land cover at regional and global scales. To develop improved methodologies for global land cover classifications as well as to provide global land cover products for immediate use in global change research, LGRSS researchers have employed the NASA/NOAA Pathfinder AVHRR Land (PAL) data set with a spatial resolution of 1 km. The PAL data set has a record length of 14 years (1981-1994), providing the ability to test the stability of classification algorithms. The PAL data set includes red, infrared, and thermal bands in addition to the Normalized Difference Vegetation Index (NDVI). Inclusion of these additional bands improves discrimination between cover types. The LGRSS researchers' aim was to develop and validate global land cover data sets and to develop advanced methodologies for more realistically describing the vegetative land surface based on satellite data.The 1-km global land cover product was created from 1992-1993 local area coverage (LAC) AVHRR data. The global land cover product is available for download from the University of Maryland's Global Land Cover Facility (GLCF) Web site (http://glcf.umiacs.umd.edu/data/landcover/index.shtml). Forty-one metrics were developed to describe global vegetation phenology, and these data were used to make the 1-km land cover map. The final product contains 13 land cover classes.More information can be found at ftp://daac.ornl.gov/data/lba/land_use_land_cover_change/land_cover_data_1km/comp/glcf1km_readme.pdf.LBA was a cooperative international research initiative led by Brazil. NASA was a lead sponsor for several experiments. LBA was designed to create the new knowledge needed to understand the climatological, ecological, biogeochemical, and hydrological functioning of Amazonia; the impact of land use change on these functions; and the interactions between Amazonia and the Earth system. More information about LBA can be found at http://www.daac.ornl.gov/LBA/misc_amazon.html.

This land cover data set was derived from the Advanced Very High Resolution Radiometer (AVHRR) sensor operating on board the United States National Oceanic and Atmospheric Administration (NOAA) satellites. Information on the NOAA series of satellites can be found at www.noaa.gov/satellites.html The vegetation and land cover information set has been classified into twelve categories. Information on the classification of the vegetation and land cover, raster to vector conversion, generalization for cartographic presentations is included in the paper "The Canada Vegetation and Land Cover: A Raster and Vector Data Set for GIS Applications - Uses in Agriculture" (https://geogratis.cgdi.gc.ca/download/landcover/scale/gis95ppr.pdf). A soil quality evaluation was obtained by cross-referencing the AVHRR information with Census of Agriculture records and biophysical (Soil Landscapes of Canada) data and is also included in the above paper. AVHRR Land Cover Data approximates a 1:2M scale and was done originally for Agriculture Canada. The projection used is Lambert Conformal Conic (LCC) 49/77 with origin at 49N 95W.

With the latest version of GLASS (Global Land Surface Satellite) CDRs (climate data records) from 1982 to 2015, the authors built the first record of 34-year-long annual dynamics of global land-use/land-cover (LULC) (GLASS_GLC) at 5 km resolution using Google Earth Engine platform. Compared to earlier global LULC products, GLASS-GLC is characterized by high consistency, more detail, and longer temporal coverage.