High-resolution global map of closed-canopy coconut

The file ‘GlobalCoconutLayer_2020_v1-1.zip’ contains 886 raster tiles of 100x100 km in geotiff format. The raster files are the result of a convolutional neural network that classified Sentinel-1 and Sentinel-2 annual composites into a coconut layer for the year 2020. The images have a spatial resolution of 20 meters and contain two classes: <br> [0] Other land covers that are not coconut.<br> [1] Coconut. The file ‘GlobalCoconutLayer_2020_densityMap_1km_v1-1.zip’ contains the 20-meter coconut classification aggregated to 1 km. The value of each pixel represents the coconut area (in squared meters) within the 1-km pixel. The file ‘Validation_points_GlobalCoconutLayer_2020_v1-1.shp’ includes the 10,200 points that were used to validate the product. Each point includes the attribute ‘Class’, which is the class assigned by visual interpretation of sub-meter resolution images, and the attribute ‘predClass’, which reflects the predicted class by the convolutional neural network. The ‘predClass’ values are the same as the raster files:<br> [0] Other land covers that are not coconut.<br> [1] Coconut.<br> The attribute ‘Class’ contains the following values: <br> [0] Land cover could not be determined because sub-meter resolution data was not available.<br> [1] Other land covers that are not coconut.<br> [2] Sparse coconut. Low density of coconut trees; between 1 and 4 coconut trees within the 20-meter pixel.<br> [3] Dense open-canopy coconut; more than 4 coconut trees within the 20-meter pixel but coconut trees do not reach the full canopy closure. <br> [4] Closed -canopy coconut; more than 4 coconut trees within the 20-meter pixel and coconut trees fully cover the ground.<br> [5] Palm species that are not coconut.