Reconstruction of GRACE Data on Changes in Total Water Storage Over the Global Land Surface and 60 Basins

Sun, Zhangli; Long, Di; Yang, Wenting; Li, Xueying; Pan, Yun

doi:10.1029/2019wr026250

Cited by 170 publications

(109 citation statements)

References 108 publications

Supporting

Mentioning

105

Contrasting

Order By: Relevance

“…To reduce the limitation of remote sensing monitoring data, physics‐based models and data‐driven machine learning models were introduced to predict lake changes (Z. Sun et al., 2020). Cai et al.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

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

Fan

Song

et al. 2021

Water Resources Research

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

“…In recent years, the machine learning approach has been widely applied to hydrological prediction (Humphrey & Gudmundsson, 2019; F. Li et al., 2020; Z. Sun et al., 2020). For example, S Zhu et al.…”

Section: Introductionmentioning

confidence: 99%

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

Fan

Song

et al. 2021

Water Resources Research

View full text Add to dashboard Cite

show abstract

“…Note that even though precipitation and temperature are already part of the inputs to global land surface models, they may represent certain aspects of observed climatology that are not fully captured in the simulated TWS (Sun et al., 2019). In addition, the ERA5‐Land forcing data are not identical to the GLDAS forcing data, thus representing a slightly different source of information (Sun & Tang, 2020; Sun et al., 2020).…”

Section: Datamentioning

confidence: 99%

“…Sun et al. (2020) trained and compared the efficacy of three different machine learning (ML) algorithms on reconstructing the TWSA data. They showed that all three regression models perform reasonably well in humid and low‐intensity irrigated areas, but vary significantly in dry and/or intensively irrigated regions.…”

Section: Introductionmentioning

confidence: 99%

“…While such a single‐algorithm paradigm may suffice for a single study site or a group of similar sites, it becomes insufficient for multisite, large‐scale studies where the predictor importance can exhibit strong spatial variability across sites which, in turn, may affect the performance of ML models. In grid‐based, GRACE data reconstruction problems, existing studies have already shown that no single algorithm consistently outperformed others over all global basins (e.g., Li et al., 2020; Sun et al., 2020). Thus, instead of focusing on training and applying a single algorithm to work for all sites (or grid cells), thus risking model generalization performance, a systematic approach should be used to train and tune separate ML models for different sites, and choose the best performer for each site in a consistent way (including the ad hoc ensemble models built through stacking, see Section 3.1) to achieve optimal performance and reproducibility.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Reconstruction of GRACE Total Water Storage Through Automated Machine Learning

Sun

Scanlon

Save

et al. 2021

Water Resources Research

View full text Add to dashboard Cite

The Gravity Recovery and Climate Experiment (GRACE) satellite mission and its follow‐on, GRACE‐FO, have provided unprecedented opportunities to quantify the impact of climate extremes and human activities on total water storage at large scales. The ∼1‐year data gap between the two GRACE missions needs to be filled to maintain data continuity and maximize mission benefits. In this study, we applied an automated machine learning (AutoML) workflow to perform gridwise GRACE‐like data reconstruction. AutoML represents a new paradigm for optimal algorithm selection, model structure selection, and hyperparameter tuning, addressing some of the most challenging issues in machine learning applications. We demonstrated the workflow over the conterminous U.S. (CONUS) using six types of machine learning models and multiple groups of meteorological and climatic variables as predictors. Results indicate that the AutoML‐assisted gap filling achieved satisfactory performance over the CONUS. On the testing data, the mean gridwise Nash‐Sutcliffe efficiency is around 0.85, the mean correlation coefficient is around 0.95, and the mean normalized root‐mean‐square‐error is about 0.09. Trained models maintain good performance when extrapolating to the mission gap and to GRACE‐FO periods (after June 2017). Results further suggest that no single algorithm provides the best predictive performance over the entire CONUS, stressing the importance of using an end‐to‐end workflow to train, optimize, and combine multiple machine learning models to deliver robust performance, especially when building large‐scale hydrological prediction systems and when predictor importance exhibiting strong spatial variability.

show abstract

Spatial–temporal variation analysis of water storage and its impacts on ecology and environment in high‐intensity coal mining areas

et al. 2022

View full text Add to dashboard Cite

In common with other important coal bases in northwestern China, the hydrology and ecology and environment of Ordos, northern Shaanxi (Shanbei), and Shanxi Provinces have much. Terrestrial water storage anomaly (TWSA), soil moisture anomaly (SMA), and groundwater storage anomaly (GWSA), are important water storage qualities that play a critical role in the distribution and growth of vegetation. In this paper, multi‐source remote sensing data were used to analyze the spatial–temporal changes and relationships of water storage, ecology and environment from 2002 to 2020. The numerical results showed the TWSA and GWSA in the study area had a declining trend and the rates were −7.512 mm yr‐1 and −8.268 mm yr‐1, respectively. On the contrary, the SMS showed an increasing trend, and the rate was 0.840 mm yr‐1. By trend variation and correlation analysis, we found GWSA is the main part in the variation of TWSA. By further analysis, it was found that the climate factors are not the major factors causing the variation of GWSA, but coal mining and artificial irrigation activities, which are especially clear in the Taihang Mountains in eastern Shanxi Province. The ecology and environment have been improving, and water storage and climate factors have played a different role in different regions. The warm climate conditions and the increased 0–40 cm of soil water have promoted the growth of vegetation and the improvement of the ecology and environment. The research results are helpful to understand the impacts of water storage on the ecology and environment in high‐intensity coal mining areas.

show abstract

Reconstruction of GRACE Data on Changes in Total Water Storage Over the Global Land Surface and 60 Basins

Cited by 170 publications

References 108 publications

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

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

Reconstruction of GRACE Total Water Storage Through Automated Machine Learning

Spatial–temporal variation analysis of water storage and its impacts on ecology and environment in high‐intensity coal mining areas

Contact Info

Product

Resources

About