{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T06:15:02Z","timestamp":1783059302104,"version":"3.54.6"},"reference-count":54,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T00:00:00Z","timestamp":1691712000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Innovation and Entrepreneurship Training Program for College Students of Sun Yat-sen University","award":["2022A1515010676"],"award-info":[{"award-number":["2022A1515010676"]}]},{"name":"Natural Science Foundation of Guangdong Province, China","award":["2022A1515010676"],"award-info":[{"award-number":["2022A1515010676"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Accurate estimation of terrestrial water storage (TWS) and understanding its driving factors are crucial for effective hydrological assessment and water resource management. The launches of the Gravity Recovery and Climate Experiment (GRACE) satellites and their successor, GRACE Follow-On (GRACE-FO), combined with deep learning algorithms, have opened new avenues for such investigations. In this study, we employed a long short-term memory (LSTM) neural network model to simulate TWS anomaly (TWSA) in the Pearl River Basin (PRB) from 2003 to 2020, using precipitation, temperature, runoff, evapotranspiration, and leaf area index (LAI) data. The performance of the LSTM model was rigorously evaluated, achieving a high average correlation coefficient (r) of 0.967 and an average Nash\u2013Sutcliffe efficiency (NSE) coefficient of 0.912 on the testing set. To unravel the relative importance of each driving factor and assess the impact of different lead times, we employed the SHapley Additive exPlanations (SHAP) method. Our results revealed that precipitation exerted the most significant influence on TWSA in the PRB, with a one-month lead time exhibiting the greatest impact. Evapotranspiration, runoff, temperature, and LAI also played important roles, with interactive effects among these factors. Moreover, we observed an accumulation effect of precipitation and evapotranspiration on TWSA, particularly with shorter lead times. Overall, the SHAP method provides an alternative approach for the quantitative analysis of natural driving factors at the basin scale, shedding light on the natural dominant influences on TWSA in the PRB. The combination of satellite observations and deep learning techniques holds promise for advancing our understanding of TWS dynamics and enhancing water resource management strategies.<\/jats:p>","DOI":"10.3390\/rs15163983","type":"journal-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T10:33:23Z","timestamp":1691750003000},"page":"3983","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Simulation and Driving Factor Analysis of Satellite-Observed Terrestrial Water Storage Anomaly in the Pearl River Basin Using Deep Learning"],"prefix":"10.3390","volume":"15","author":[{"given":"Haijun","family":"Huang","sequence":"first","affiliation":[{"name":"School of Civil Engineering, Sun Yat-Sen University, Guangzhou 510275, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanbin","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou 510275, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeer","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Atmospheric Science, Sun Yat-Sen University, Guangzhou 510275, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanning","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Sun Yat-Sen University, Guangzhou 510275, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhikai","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Civil Engineering, Sun Yat-Sen University, Guangzhou 510275, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7042-9756","authenticated-orcid":false,"given":"Peizhi","family":"Tian","sequence":"additional","affiliation":[{"name":"School of Civil Engineering, Sun Yat-Sen University, Guangzhou 510275, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juncheng","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Civil Engineering, Sun Yat-Sen University, Guangzhou 510275, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xitian","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Civil Engineering, Sun Yat-Sen University, Guangzhou 510275, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e2021GL093492","DOI":"10.1029\/2021GL093492","article-title":"Long-Term (1979\u2013Present) Total Water Storage Anomalies Over the Global Land Derived by Reconstructing GRACE Data","volume":"48","author":"Li","year":"2021","journal-title":"Geophys. Res. Lett."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"E7","DOI":"10.1038\/s41586-018-0831-6","article-title":"Emerging trends in global freshwater availability","volume":"565","author":"Rodell","year":"2019","journal-title":"Nature"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"111259","DOI":"10.1016\/j.rse.2019.111259","article-title":"Detecting hotspots of interactions between vegetation greenness and terrestrial water storage using satellite observations","volume":"231","author":"Xie","year":"2019","journal-title":"Remote Sens. Environ."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"8026","DOI":"10.1002\/2016GL069538","article-title":"Mapping probabilities of extreme continental water storage changes from space gravimetry","volume":"43","author":"Kusche","year":"2016","journal-title":"Geophys. Res. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2053","DOI":"10.1175\/JCLI-D-20-0332.1","article-title":"Drought and Flood Characterization and Connection to Climate Variability in the Pearl River Basin in Southern China Using Long-Term GRACE and Reanalysis Data","volume":"34","author":"Huang","year":"2021","journal-title":"J. Clim."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1038\/s41558-020-00972-w","article-title":"Global terrestrial water storage and drought severity under climate change","volume":"11","author":"Pokhrel","year":"2021","journal-title":"Nat. Clim. Change"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.geog.2016.04.008","article-title":"Terrestrial water storage changes over the Pearl River Basin from GRACE and connections with Pacific climate variability","volume":"7","author":"Luo","year":"2016","journal-title":"Geod. Geodyn."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1029\/2004GL019779","article-title":"Time-variable gravity from GRACE: First results","volume":"31","author":"Wahr","year":"2004","journal-title":"Geophys. Res. Lett."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"128225","DOI":"10.1016\/j.jhydrol.2022.128225","article-title":"Driving factors and changes in components of terrestrial water storage in the endorheic Tibetan Plateau","volume":"612","author":"Deng","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2427","DOI":"10.1007\/s12665-012-2070-8","article-title":"Evolution of major environmental geological problems in karst areas of Southwestern China","volume":"69","author":"Guo","year":"2013","journal-title":"Environ. Earth Sci."},{"key":"ref_11","first-page":"334","article-title":"Karstic water storage response to the recent droughts in Southwest China estimated from satellite gravimetry","volume":"9808","author":"Yao","year":"2015","journal-title":"Int. Conf. Intell. Earth Obs. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"073001","DOI":"10.1088\/1748-9326\/ab1b7d","article-title":"How can Big Data and machine learning benefit environment and water management: A survey of methods, applications, and future directions","volume":"14","author":"Sun","year":"2019","journal-title":"Environ. Res. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"4040","DOI":"10.1029\/2017WR022238","article-title":"A New Machine-Learning Approach for Classifying Hysteresis in Suspended-Sediment Discharge Relationships Using High-Frequency Monitoring Data","volume":"54","author":"Hamshaw","year":"2018","journal-title":"Water Resour. Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1038\/s41586-019-0912-1","article-title":"Deep learning and process understanding for data-driven Earth system science","volume":"566","author":"Reichstein","year":"2019","journal-title":"Nature"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"105337","DOI":"10.1016\/j.atmosres.2020.105337","article-title":"CNN-based near-real-time precipitation estimation from Fengyun-2 satellite over Xinjiang, China","volume":"250","author":"Xue","year":"2021","journal-title":"Atmos. Res."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Huang, X., Gao, L., Crosbie, R.S., Zhang, N., Fu, G.B., and Doble, R. (2019). Groundwater Recharge Prediction Using Linear Regression, Multi-Layer Perception Network, and Deep Learning. Water, 11.","DOI":"10.3390\/w11091879"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"6005","DOI":"10.5194\/hess-22-6005-2018","article-title":"Rainfall-runoff modelling using Long Short-Term Memory (LSTM) networks","volume":"22","author":"Kratzert","year":"2018","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.rse.2014.08.006","article-title":"Drought and flood monitoring for a large karst plateau in Southwest China using extended GRACE data","volume":"155","author":"Long","year":"2014","journal-title":"Remote Sens. Environ."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"126016","DOI":"10.1016\/j.jhydrol.2021.126016","article-title":"River water temperature forecasting using a deep learning method","volume":"595","author":"Qiu","year":"2021","journal-title":"J. Hydrol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"127244","DOI":"10.1016\/j.jhydrol.2021.127244","article-title":"Bayesian convolutional neural networks for predicting the terrestrial water storage anomalies during GRACE and GRACE-FO gap","volume":"604","author":"Mo","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2221","DOI":"10.1109\/TGRS.2018.2872131","article-title":"The Value of SMAP for Long-Term Soil Moisture Estimation With the Help of Deep Learning","volume":"57","author":"Fang","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e2021WR031412","DOI":"10.1029\/2021WR031412","article-title":"Improved Understanding of How Catchment Properties Control Hydrological Partitioning Through Machine Learning","volume":"58","author":"Cheng","year":"2022","journal-title":"Water Resour. Res."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Li, L.Y., Zeng, Z.Z., Zhang, G., Duan, K., Liu, B.J., and Cai, X.T. (2022). Exploring the Individualized Effect of Climatic Drivers on MODIS Net Primary Productivity through an Explainable Machine Learning Framework. Remote Sens., 14.","DOI":"10.3390\/rs14174401"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e2021WR030185","DOI":"10.1029\/2021WR030185","article-title":"Uncovering Flooding Mechanisms Across the Contiguous United States Through Interpretive Deep Learning on Representative Catchments","volume":"58","author":"Jiang","year":"2022","journal-title":"Water Resour. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e2022GL099368","DOI":"10.1029\/2022GL099368","article-title":"Wildfire Danger Prediction and Understanding With Deep Learning","volume":"49","author":"Kondylatos","year":"2022","journal-title":"Geophys. Res. Lett."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"847892","DOI":"10.3389\/fsufs.2022.847892","article-title":"Explainable Machine Learning Approach Quantified the Long-Term (1981\u20132015) Impact of Climate and Soil Properties on Yields of Major Agricultural Crops Across CONUS","volume":"6","author":"Sihi","year":"2022","journal-title":"Front. Sustain. Food Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e2021MS002496","DOI":"10.1029\/2021MS002496","article-title":"Revealing the Impact of Global Heating on North Atlantic Circulation Using Transparent Machine Learning","volume":"13","author":"Sonnewald","year":"2021","journal-title":"J. Adv. Model. Earth Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1112970","DOI":"10.3389\/frwa.2023.1112970","article-title":"Investigation of hydrometeorological influences on reservoir releases using explainable machine learning methods","volume":"5","author":"Fan","year":"2023","journal-title":"Front. Water"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"129696","DOI":"10.1016\/j.jhydrol.2023.129696","article-title":"The responses of ecosystem water use efficiency to CO2, nitrogen deposition, and climatic drivers across China","volume":"622","author":"Cai","year":"2023","journal-title":"J. Hydrol."},{"key":"ref_30","unstructured":"Lundberg, S.M., and Lee, S.I. (2017). A Unified Approach to Interpreting Model Predictions. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_31","unstructured":"Lundberg, S.M., Erion, G.G., and Lee, S.-I. (2018). Consistent individualized feature attribution for tree ensembles. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"e2019WR026250","DOI":"10.1029\/2019WR026250","article-title":"Reconstruction of GRACE Data on Changes in Total Water Storage Over the Global Land Surface and 60 Basins","volume":"56","author":"Sun","year":"2020","journal-title":"Water Resour. Res."},{"key":"ref_33","unstructured":"Pearl River Water Resources Committee (PRWRC) (1991). The Zhujiang Archive, Guangdong Science and Technology Press. (In Chinese)."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"84","DOI":"10.3724\/SP.J.1248.2012.00084","article-title":"Responses of hydrological processes to climate change in the Zhujiang River basin in the 21st century","volume":"3","author":"Tong","year":"2012","journal-title":"Adv. Clim. Change Res."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/j.jhydrol.2012.09.054","article-title":"Regionalization and spatial changing properties of droughts across the Pearl River basin, China","volume":"472","author":"Zhang","year":"2012","journal-title":"J. Hydrol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.jhydrol.2012.03.037","article-title":"Spatial-temporal changes of precipitation structure across the Pearl River basin, China","volume":"440","author":"Zhang","year":"2012","journal-title":"J. Hydrol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1381","DOI":"10.1007\/s00190-019-01252-y","article-title":"Regularization and error characterization of GRACE mascons","volume":"93","author":"Loomis","year":"2019","journal-title":"J. Geod."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"9412","DOI":"10.1002\/2016WR019494","article-title":"Global evaluation of new GRACE mascon products for hydrologic applications","volume":"52","author":"Scanlon","year":"2016","journal-title":"Water Resour. Res."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"22071","DOI":"10.1073\/pnas.1900654116","article-title":"Definitions, methods, and applications in interpretable machine learning","volume":"116","author":"Murdoch","year":"2019","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1038\/s41597-020-0453-3","article-title":"Version 4 of the CRU TS monthly high-resolution gridded multivariate climate dataset","volume":"7","author":"Harris","year":"2020","journal-title":"Sci. Data"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1903","DOI":"10.5194\/gmd-10-1903-2017","article-title":"GLEAM v3: Satellite-based land evaporation and root-zone soil moisture","volume":"10","author":"Martens","year":"2017","journal-title":"Geosci. Model Dev."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"453","DOI":"10.5194\/hess-15-453-2011","article-title":"Global land-surface evaporation estimated from satellite-based observations","volume":"15","author":"Miralles","year":"2011","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Lin, W.Y., Yuan, H., Dong, W.Z., Zhang, S.P., Liu, S.F., Wei, N., Lu, X.J., Wei, Z.W., Hu, Y., and Dai, Y.J. (2023). Reprocessed MODIS Version 6.1 Leaf Area Index Dataset and Its Evaluation for Land Surface and Climate Modeling. Remote Sens., 15.","DOI":"10.3390\/rs15071780"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1171","DOI":"10.1016\/j.rse.2011.01.001","article-title":"Reprocessing the MODIS Leaf Area Index products for land surface and climate modelling","volume":"115","author":"Yuan","year":"2011","journal-title":"Remote Sens. Environ."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"e2019EA000959","DOI":"10.1029\/2019EA000959","article-title":"Can Terrestrial Water Storage Dynamics be Estimated From Climate Anomalies?","volume":"7","author":"Jing","year":"2020","journal-title":"Earth Space Sci."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"128562","DOI":"10.1016\/j.jhydrol.2022.128562","article-title":"Comparison of deep learning models and a typical process-based model in glacio-hydrology simulation","volume":"615","author":"Chen","year":"2022","journal-title":"J. Hydrol."},{"key":"ref_48","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_49","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1007\/s10115-013-0679-x","article-title":"Explaining prediction models and individual predictions with feature contributions","volume":"41","author":"Strumbelj","year":"2014","journal-title":"Knowl. Inf. Syst."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Wang, F., Chen, Y.N., Li, Z., Fang, G.H., Li, Y.P., Wang, X.X., Zhang, X.Q., and Kayumba, P.M. (2021). Developing a Long Short-Term Memory (LSTM)-Based Model for Reconstructing Terrestrial Water Storage Variations from 1982 to 2016 in the Tarim River Basin, Northwest China. Remote Sens., 13.","DOI":"10.3390\/rs13050889"},{"key":"ref_52","first-page":"1","article-title":"Spatial and temporal variation of water storage in recent seven years from GRACE in Yunnan Province","volume":"5","author":"Wang","year":"2012","journal-title":"Water Sav. Irrig."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"52138","DOI":"10.1109\/ACCESS.2018.2870052","article-title":"Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)","volume":"6","author":"Adadi","year":"2018","journal-title":"IEEE Access"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1029\/2018WR023333","article-title":"Combining Physically Based Modeling and Deep Learning for Fusing GRACE Satellite Data: Can We Learn From Mismatch?","volume":"55","author":"Sun","year":"2019","journal-title":"Water Resour. Res."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/16\/3983\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:31:11Z","timestamp":1760128271000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/16\/3983"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,11]]},"references-count":54,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["rs15163983"],"URL":"https:\/\/doi.org\/10.3390\/rs15163983","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,11]]}}}