Effect of Three Gorges Dam on Poyang Lake water level at daily scale based on machine learning

Lake water level is an essential indicator of environmental changes caused by natural and human factors. The Poyang Lake, the largest freshwater lake in China, has exhibited a dramatic variation for past few years, especially after completion Three Gorges Dam (TGD). However, there lack more accurate assessment effect TGD on (PLWL) at finer temporal scales (e.g., daily scale). Here, we used three machine learning models, namely, Artificial Neural Network (ANN), Nonlinear Autoregressive model with eXogenous input (NARX), Gated Recurrent Unit (GRU), to simulate during 2003–2016. We found that models historical memory (i.e., GRU model) are suitable simulating PLWL under influence TGD. GRU-based results show significantly affected regulation different operation stages periods. Although had slight but not very significant impact yearly decline PLWL, blocking or releasing certain moments large level. This machine-learning-based study sheds light interactions between Yangtze River regulated