Reconstructing Total Water Storage Anomalies Over the Lake Victoria Basin (1971–2022) Using an Enhanced RecNet Model

Abstract Relatively short records of Total Water Storage Anomalies (TWSA) from the Gravity Recovery and Climate Experiment (GRACE) and its Follow‐On (GRACE‐FO) missions have impeded our understanding of their full range and long‐term variability over the Lake Victoria Basin (LVB). This study introduces an Enhanced RecNet (ERecNet) to reconstruct the LVB's TWSA from 1971 to 2022 using precipitation and Lake Victoria's level data. ERecNet integrates a multi‐layer perceptron and a combination of gridded and basin‐averaged loss functions for improving reconstruction performance. Our results reveal that ERecNet can successfully reconstruct the LVB's TWSA variations, outperforming hydrological models and reanalysis products in capturing the TWSA trends and amplitudes. The reconstruction aligns closely with the lake level and precipitation patterns while effectively closing the LVB's water balance budget. This study provides the first reconstruction of both human‐ and climate‐driven TWSA data over the LVB, offering valuable insights into its long‐term hydrological variability.