10m Annual Land Use Land Cover (9-class) V2

__Note__: _A new version of this item is available for your use. This mature version of the map remains available for use in existing applications. This item will be retired in December 2024. There is 2023 data available in the newer 9-class v2 dataset._ Time series of annual global maps of land use and land cover (LULC). It currently has data from 2017-2022. The maps are derived from ESA Sentinel-2 imagery at 10m resolution. Each map is a composite of LULC predictions for 9 classes throughout the year in order to generate a representative snapshot of each year. This dataset was generated by Impact Observatory, who used billions of human-labeled pixels (curated by the National Geographic Society) to train a deep learning model for land classification. The global map was produced by applying this model to the Sentinel-2 annual scene collections on the Planetary Computer. Each of the maps has an assessed average accuracy of over 75%. This map uses an updated model from the 10-class model and combines Grass(formerly class 3) and Scrub (formerly class 6) into a single Rangeland class (class 11). The original Esri 2020 Land Cover collection uses 10 classes (Grass and Scrub separate) and an older version of the underlying deep learning model. The Esri 2020 Land Cover map was also produced by Impact Observatory. The map remains available for use in existing applications. New applications should use the updated version of 2020 once it is available in this collection, especially when using data from multiple years of this time series, to ensure consistent classification. All years are available under a Creative Commons BY-4.0.

__Note__: _A new version of this item is available for your use. This mature version of the map remains available for use in existing applications. This item will be retired in December 2024. There is 2020 data available in the newer 9-class dataset._ Global estimates of 10-class land use/land cover (LULC) for 2020, derived from ESA Sentinel-2 imagery at 10m resolution. This dataset was generated by Impact Observatory, who used billions of human-labeled pixels (curated by the National Geographic Society) to train a deep learning model for land classification. The global map was produced by applying this model to the relevant yearly Sentinel-2 scenes on the Planetary Computer. This dataset is also available on the ArcGIS Living Atlas of the World.

The European Space Agency (ESA) WorldCover 10 m 2021 product provides a global land cover map for 2021 at 10 m resolution based on Sentinel-1 and Sentinel-2 data. It has 11 land cover classes, aligned with UN-FAO's Land Cover Classification System, and was produced and independently validated with an overall accuracy of about 77%.

The European Space Agency (ESA) WorldCover 10 m 2020 product provides a global land cover map for 2020 at 10 m resolution based on Sentinel-1 and Sentinel-2 data, with 11 land cover classes.

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, Oceania, and Africa are available. This dataset includes global land cover and land cover change data for the period 2001 to 2019. Africa is extended through 2021. GLanCE 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. * All GLnanCE granules should contain 7 products except the year 2001, which contain 4, as there are no change products (chgDate, EVI2chg, prevClass) for the initial year of data. * 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.

Annual Earth-embedding layers from Google DeepMind's AlphaEarth Foundations model: for every 10 m square of land, 64 numbers that summarise what the satellite record (optical, radar, elevation, climate and more) shows there over the year. Places that look and behave alike have similar embeddings, so they power similarity search (“find places like this”), land-cover mapping and change detection without hand-labelled training data. Coverage: global land and coastal waters, one layer per year from 2017 to 2025, in UTM tiles of 8192 × 8192 pixels.