AUTHOR=Li Bing , Yang Guishan , Wan Rongrong , Wang Yanan , Xu Chen , Wang Dianchang , Mi Chuang 

TITLE=Unraveling the Importance of the Yangtze River and Local Catchment on Water Level Variations of Poyang Lake (China) After the Three Gorges Dam Operation: Insights From Random Forest Modeling

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2022.927462

DOI=10.3389/feart.2022.927462

ISSN=2296-6463

ABSTRACT=Investigating the contributions of the influencing factors on lake water level fluctuations (WLF) and their related changes regarding to hydraulic facilities is vital for understanding the driving mechanism of WLF under multiple pressure from anthropogenic activities and climate change. In this study, random forest (RF) model was used to investigate the changes of the relationship between WLF and discharge of the Yangtze River and local tributaries in Poyang Lake, China, based on daily hydrological data from 1980 to 2018. Results indicated that RF exhibited robust capability for WLF prediction in Poyang Lake, with average R2 of 0.95, 0.88, 0.92, and 0.94 for the dry, rising, wet, and recession seasons, respectively. Predictor importance analysis showed that the discharge of Yangtze River exerted larger influences on the WLF than the discharge of local tributaries except for the dry season in Poyang Lake, the influence of which on the WLF was evident with discharge less than 5000 m3/s. The influence of the Yangtze River also showed a clear attenuation pattern with the distance increased from the outlet of the lake, of which the WLF was constantly regulated by the Yangtze River. In addition, the partial dependence plots also indicated that the Yangtze River discharge changes after the TGD operation have resulted in remarkable water level decreases in the wet and recession seasons, especially for the recession period. Meanwhile, a slight increase water level was predicted in the dry season, which was only concentrated in the outlet of the lake. This study indicated RF model as a robust technique for WLF predictions and attribution analysis under multiple temporal and spatial scales. Moreover, this study confirmed the uneven influences of the Yangtze River and local tributaries on WLF across different seasons, gauging stations, and phases, and could provide some insights into the WLF responses to the TGD operation in Poyang Lake.