Simulation and Driving Factor Analysis of Satellite-Observed Terrestrial Water Storage Anomaly in the Pearl River Basin Using Deep Learning

作者：Haijun Huang, Guanbin Feng, Y. Cao, Guanning Feng, Zhi-Kai Dai, Peizhi Tian, Juncheng Wei, Xitian Cai · 发表于：Remote Sensing · 年份：2023 · DOI：10.3390/rs15163983 · 被引用次数：15 · 研究领域：Geophysics and Gravity Measurements、Solar and Space Plasma Dynamics、Computational Physics and Python Applications

Accurate estimation of terrestrial water storage (TWS) and understanding its driving factors are crucial for effective hydrological assessment and water resource management. The launches of the Gravity Recovery and Climate Experiment (GRACE) satellites and their successor, GRACE Follow-On (GRACE-FO), combined with deep learning algorithms, have opened new avenues for such investigations. In this study, we employed a long short-term memory (LSTM) neural network model to simulate TWS anomaly (TWSA) in the Pearl River Basin (PRB) from 2003 to 2020, using precipitation, temperature, runoff, evapotranspiration, and leaf area index (LAI) data. The performance of the LSTM model was rigorously evaluated, achieving a high average correlation coefficient (r) of 0.967 and an average Nash–Sutcliffe efficiency (NSE) coefficient of 0.912 on the testing set. To unravel the relative importance of each driving factor and assess the impact of different lead times, we employed the SHapley Additive exPlanations (SHAP) method. Our results revealed that precipitation exerted the most significant influence on TWSA in the PRB, with a one-month lead time exhibiting the greatest impact. Evapotranspiration, runoff, temperature, and LAI also played important roles, with interactive effects among these factors. Moreover, we observed an accumulation effect of precipitation and evapotranspiration on TWSA, particularly with shorter lead times. Overall, the SHAP method provides an alternative approach for th...