Abstract: Since the beginning of the 21st century, Poyang Lake has been confronted with a series of challenges resulting from the combined effects of climate change and human activities.These challenges include early water withdrawal time, dry season duration extension, and falling water levels.The observed phenomena exhibit a normalization and trending characteristics, posing significant challenges to the production and life in the Poyang Lake area.To analyze the trends in annual average water level at five hydrological stations in Poyang Lake area from 1989 to 2020,namely Xingzi, Tangyin, Kangshan, Duchang, and Hukou Station, we employed trend and mutation tests.Additionally, we quantified the impacts of climate change and human activities on Poyang Lake by utilizing the PCR-GLOBWB(PCRaster Global Water Balance) model, which captures the refined impact of human activities, and the LSTM(long short-term memory) neural network model which is suitable for time series prediction.These models were integrated with the IHA/RVA method.The results indicated that the water level of Poyang Lake showed a downward trend due to human activities.Notably, a significant change occurred in 2003.At the same time, the overall change degree of Poyang Lake water level increased from low change to moderate change.Taking Xingzi Station as an example, human activities were the main driving factors for the change in the hydrological regime of Poyang Lake, with a contribution rate of 110.62%.In contrast, the contribution rate of climate change was only-10.62%.The research results can provide a basis for the scientific management and regulation of water resources in Poyang Lake.