Century‐Scale Reconstruction of Water Storage Changes of the Largest Lake in the Inner Mongolia Plateau Using a Machine Learning Approach

Abstract

Lake Hulun is the fifth‐largest lake in China, playing a substantial role in maintaining the balance of the grassland ecosystem of the Mongolia Plateau, which is a crucial ecological barrier in North China. To better understand the changing characteristics of Lake Hulun and the driving mechanisms, it is necessary to investigate the water storage changes of Lake Hulun on extended timescales. The main objective of this study is to reconstruct the water storage time series of Lake Hulun over the past century. We employed a machine learning approach termed the extreme gradient boosting tree (XGBoost) to reconstruct the water storage changes over a one‐century timescale based on the generated bathymetry and satellite altimetry data and investigated the relationships with hydrological and climatic variables in long term. Results show that the water storage changes from 1961 to 2019 were featured by four fluctuation phases, with the highest water storage observed in 1991 (14.02 Gt) and the lowest point in 2012 (5.18 Gt). The century‐scale reconstruction result reveals that the water storage of Lake Hulun reached the highest point in the 1960s within the period of 1910–2019. The lowest stage occurred in the sub‐period of the 1930s–1940s, which was even lower than the alerted shrinkage stage in 2012. The predictive model results indicate the effective performance of the XGBoost model in reconstructing century‐scale water storage variations, with the mean absolute error of 0.68, normalized root mean square error of 0.11, Nash–Sutcliffe efficiency of 0.97, and correlation coefficient of 0.94. The annual fluctuations of water storage were mostly affected by precipitation, followed by vapor pressure, temperature, potential evapotranspiration, and wet day frequency. The dominating characteristics of different variables vary evidently with different sub‐periods. The atmospheric circulations of the Arctic Oscillation, El Nino Southern Oscillation, Pacific Decadal Oscillation, and North Atlantic Oscillation have tight associations with the water storage variations of Lake Hulun, which change with different study periods.

Median bed-material sediment particle size across rivers in the contiguous U.S.

“…Among various machine learning methods, eXtreme Gradient Boosting (XGBoost) is a version of the gradient tree boosting algorithm known for its high efficiency and superior performance in recent years (Chen and Guestrin, 2016;Zheng et al, 2019;Fan et al, 2021). Therefore, we adopt XGBoost to develop a predictive model with the Optuna optimization framework (Akiba…”

“…One of the most recent offspring of gradient boosting techniques is the XGBoost, a scalable end-to-end tree boosting system (Chen & Guestrin, 2016). It has been successfully utilized across a wide array of applications, such as snowpack estimation (Zheng et al, 2019) and water storage change in a large lake (Fan et al, 2021). XGBoost dataset is represented as = {( , ), = 1, 2, .…”

Seasonal Amplitude of Water Storage Variations of the Yangtze–Huai Plain Lake Group: Implicaion for Floodwater Storage Capacity

“…In this research, the in-situ measured daily water level time series of Poyang Lake and Taihu Lake are obtained from Jiangxi Provincial Hydrology Monitoring Center (http://www.jxssw.gov.cn/) and Taihu Lake Basin Administration bureau of the Ministry of Water Resources (http://www.tba.gov.cn/), respectively. In addition, Hydroweb (Crétaux et al, 2011) and DAHITI (Schwatke et al, 2015) provide multi-mission satellite altimetry of water level time series for lakes, which has been broadly utilized in hydrological research (Liu et al, 2019;Zhan et al, 2020;Fan et al, 2021). The lake water level records are provided by combining several altimetry satellite products, including Ocean Topography Experiment/Poseidon Mission (TOPEX/Poseidon), European Remote-Sensing Satellite (ERS), Jason-1/2/3 Ocean Surface Topography Mission, Cryosphere Satellite (CryoSat), Environmental Satellite (ENVISAT), Satellite for ARgos and ALtika (SARAL), and Sentinel-3 Satellite.…”

Responses to RC1, RC2 and RC3 -- essd-2021-201

“…Among various machine learning methods, eXtreme Gradient Boosting (XGBoost) is a version of the gradient tree boosting algorithm known for its high efficiency and superior performance in recent years (Chen and Guestrin, 2016;Zheng et al, 2019;Fan et al, 2021). Therefore, we adopt XGBoost to develop a predictive model with the Optuna optimization framework (Akiba et al, 2019) for tuning hyperparameters and the SHapley Additive exPlanations (SHAP) (Lundberg and Lee, 2016) for feature importance analysis and thus feature selection.…”

“…One of the most recent offspring of gradient boosting techniques is the XGBoost, a scalable end-to-end tree boosting system (Chen & Guestrin, 2016). It has been successfully utilized across a wide array of applications, such as snowpack estimation (Zheng et al, 2019) and water storage change in a large lake (Fan et al, 2021). XGBoost dataset is represented as 𝐷 = {(𝑋 𝑖 , 𝑌 𝑖 ), 𝑖 = 1, 2, .…”