Abstract: Accurate and reliable predictions of Terrestrial Water Storage Anomaly (TWSA) changes over the Changjiang River Basin are crucial for achieving efficient and sustainable water resource management. This study utilizes a method combining seasonal adjustment and a nonlinear autoregressive neural network (NARNN-SA), leveraging the autocorrelation of TWSA changes in the Changjiang River Basin for the first prediction. Two tests are designed to evaluate the effectiveness of the NARNN-SA model by comparing it against three models: AutoRegression (AR), Seasonal AutoRegressive Integrated Moving Average (SARIMA), and a nonlinear autoregressive neural network without seasonal adjustment (NARNN). Results demonstrated that the introduction of seasonal adjustment significantly improved the predictive performance of the NARNN-SA model, which achieved high consistency with GRACE observations, with correlation coefficient (CC) of 0.894, Nash-Sutcliffe Efficiency (NSE) of 0.769, and root mean square error (RMSE) of 1.425 cm during the testing phase. Additionally, NARNN-SA successfully predicted TWSA changes in the source, eastern, and western regions of the Changjiang River Basin and bridged the data gap between GRACE and its successor, GRACE-FO missions.