Random Forest-Based Reconstruction and Application of the GRACE Terrestrial Water Storage Estimates for the Lancang-Mekong River Basin

Abstract

Terrestrial water storage (TWS) is a critical variable in the global hydrological cycle. The TWS estimates derived from the Gravity Recovery and Climate Experiment (GRACE) allow us to better understand water exchanges between the atmosphere, land surface, sea, and glaciers. However, missing historical (pre-2002) GRACE data limit their further application. In this study, we developed a random forest (RF) model to reconstruct the monthly terrestrial water storage anomaly (TWSA) time series using Global Land Data Assimilation System (GLDAS) and Climatic Research Unit (CRU) data for the Lancang-Mekong River basin. The results show that the RF-built TWSA time series agrees well with the GRACE TWSA time series for 2003–2014, showing that correlation coefficients (R) of 0.97 and 0.90 at the basin and grid scales, respectively, which demonstrates the reliability of the RF model. Furthermore, this method is used to reconstruct the historical TWSA time series for 1980–2002. Moreover, the discharge can be obtained by subtracting the evapotranspiration (ET) and RF-built terrestrial water storage change (TWSC) from the precipitation. The comparison between the discharge calculated from the water balance method and the observed discharge showed significant consistency, with a correlation coefficient of 0.89 for 2003–2014 but a slightly lower correlation coefficient (0.86) for 1980–2002. The methods and findings in this study can provide an effective means of reconstructing the TWSA and discharge time series in basins with sparse hydrological data.

Moisture Sources and Pathways of Annual Maximum Precipitation in the Lancang‐Mekong River Basin

“…Moreover, the unique topography of the Tibetan Plateau also influences moisture transport patterns, especially under the impact of significant warming. The strong local upward convection, along with the surface radiative heating, would facilitate the water vapor confluence and suction dynamic effects (Cheng et al., 2022; X. Li et al., 2022; Y. Wang et al., 2023; Xu et al., 2019; K. Yang et al., 2010).…”

“…The population exposed to hazards caused by extreme precipitation is projected to increase with continuous global warming (Gudmundsson et al., 2021; X. Li et al., 2022; Smith et al., 2019; Swain et al., 2020). As one of the most important transboundary river basins, the Lancang‐Mekong River Basin (LMRB) comprises a complex geographical distribution of land, ocean, and terrains, a high agriculture and industry‐based economy, and a high human density, rendering it highly vulnerable to impacts of hazards resulted from worsening extreme precipitation under the effects of global warming, often with disastrous consequences (Ge et al., 2019, 2021; Irannezhad et al., 2021; Shaw et al., 2022; Y. Wang et al., 2023).…”

Leveraging ICESat, ICESat‐2, and Landsat for Global‐Scale, Multi‐Decadal Reconstruction of Lake Water Levels

“…Recent advances in laser altimeters have enabled more extensive monitoring of lake levels because of their smaller footprints (e.g., ≤70 m) (Cooley et al., 2021; Ma et al., 2024; Madson & Sheng, 2021; Y. Wang et al., 2023; Yuan et al., 2020; Zhang et al., 2011). The Ice, Cloud, and land Elevation Satellite (ICESat) provides water level measurements for thousands of inland water bodies with an accuracy of a few centimeters from 2003 to 2009 at a 91‐day interval (Schutz et al., 2005).…”

Inter‐Basin Water Transfer Effectively Compensates for Regional Unsustainable Water Use

“…In addition to statistical analyses and large‐scale models, TWSA reconstruction methods have been proposed for analyzing factors controlling TWSA changes (Humphrey et al., 2017; X. Li et al., 2022; Tang et al., 2021; Xiao et al., 2022; P. Yang et al., 2018; Zhong et al., 2019). This approach typically uses a scale parameter or machine learning algorithms to empirically estimate TWS anomalies (TWSA, i.e., the TWS change relative to its long‐term mean).…”

“…In addition to statistical analyses and large-scale models, TWSA reconstruction methods have been proposed for analyzing factors controlling TWSA changes (Humphrey et al, 2017;Tang et al, 2021;Xiao et al, 2022;P. Yang et al, 2018;Zhong et al, 2019).…”