Annual 30 m grassland canopy cover dataset for China from 1990 to 2023

The China annual grassland canopy cover dataset is the first 30 m, wall-to-wall annual dataset of national grassland canopy cover from 1990 to 2023. It is generated by integrating drone and Landsat-series imagery based on random forest (RF)-based regression model. Validation results demonstrate that the RF model achieves high predictive accuracy (R2 = 0.73, RMSE = 18.4%) and robust temporal transferability (R2 = 0.68, RMSE = 20.6%). Comparisons with existing large-scale products demonstrated significantly improved accuracy and reduced residual artifacts, underscoring the robustness of our dataset across diverse grassland types and time periods The dataset is stored as a GeoTIFF file containing one bands, which values range from 0 to 100, representing the percentage of grassland canopy cover within each pixel. The name of the file is “yyyy.tif”, where yyyy represents the year. For example, 1990.tif represents this TIFF file describing the grassland canopy cover of China in 1990.In addition to Zenodo, The China annual grassland canopy cover dataset can be accessed via the Google Earth Engine script at the following link: https://code.earthengine.google.com/?asset=projects/ee-xuanhaojiang646/assets/grassland_collection.