Landcover

This dataset, produced by Impact Observatory, Microsoft, and Esri, displays a global map of land use/land cover (LULC) derived from ESA Sentinel-2 imagery at 10m resolution back to 2017. Each year is generated from Impact Observatory’s deep learning AI land classification model using a massive training dataset of billions of human-labeled image pixels. The global maps were produced by applying this model to every Sentinel-2 scene, processing over 400,000 Earth observations per year. The algorithm generates LULC predictions for 9 classes globally. These classifications include Built, Crops, Trees, Water, Rangeland, Flooded Vegetation, Snow/Ice, Bare Ground, and Clouds.