The Three Georges Dam (TGD) has brought many benefits to the society by periodically changing the water level of its reservoir (TGR). Water discharging regularly takes places in the falling season when the downstream of the Yangtze River is drying. The TGD, the world’s largest hydroelectric project, can greatly mitigate the risk of flood caused by extreme precipitation with the prior discharging policy applied in the preflood season. At the end of flood season, water impounding in the storage season can help resist a drought the next year. However, owing to the difficulty in mining causality, the considerable debate about its environmental and climatic impacts have emerged in much of the empirical and modeling studies. We used causal generative neural networks (CGNN) to construct the linkage of water level–climate–vegetation across the TGD areas with a ten-year daily remotely sensed normalized difference vegetation index (NDVI), gauge-based precipitation, temperature observations, water level and streamflow. By quantifying the causality linkages with a non-linear Granger-causality framework, we find that the 30-days accumulated change of water level of the TGR significantly affects the vegetation growth with a median factor of 31.5% in the 100 km buffer region. The result showed that the vegetation dynamics linked to the water level regulation policy were at the regional scale rather than the local scale. Further, the water level regulation in the flood stage can greatly improve the vegetation growth in the buffer regions of the TGR area. Specifically, the explainable Granger causalities of the 25 km, 50 km, 75 km and 100 km buffer regions were 21.72%, 19.24%, 17.31% and 16.03%, respectively. In the falling and impounding stages, the functionality of the TGR that boosts the vegetation growth were not obvious (ranging from 6.1% to 8.3%). Overall, the results demonstrated that the regional vegetation dynamics were driven not only by the factor of climate variations but also by the TGR operation.