GRACE-SeDA: A global total water storage anomaly product with a spatial resolution of 0.5 degrees from self-supervised data assimilation

The monthly total water storage anomaly products with a spatial resolution of 0.5 degrees cover global land areas except for Greenland and Antarctica. The products are generated by applying a self-supervised deep learning model, which assimilates the GRACE(-FO) products and hydrological models. For more details about methodology and evaluations, please refer to the associated paper "Global high-resolution total water storage anomalies from self-supervised data assimilation using deep learning algorithms" published in Nature Water (doi.org/10.1038/s44221-024-00194-w).