Extending GRACE terrestrial water storage anomalies by combining the random forest regression and a spatially moving window structure

doi:10.1016/j.jhydrol.2020.125239

	Extending GRACE terrestrial water storage anomalies by combining the random forest regression and a spatially moving window structure
	Jing, Wenlong 1,5; Zhang, Pengyan 3; Zhao, Xiaodan 1,5; Yang, Yaping 2,4; Jiang, Hao 1,5; Xu, Jianhui 1,5; Yang, Ji 1,5; Li, Yong 1,5
刊名	JOURNAL OF HYDROLOGY
	2020-11-01
卷号	590 页码:17
关键词	Terrestrial water storage anomalies GRACE Land surface model Random forest Moving window
ISSN号	0022-1694
DOI	10.1016/j.jhydrol.2020.125239
通讯作者	Yang, Yaping(yangyp@igsnrr.ac.cn)
英文摘要	The changes of terrestrial water storage (TWS) is critical for drought monitoring, water and food security, global water cycle and climate change studies. Currently, the Gravity Recovery and Climate Experiment (GRACE) twin satellites are unique means of observing large-scale water storage variations, but the short time series (2002-present) limits their applications in long term climatic and hydrologic studies. Although the TWS can be calculated from global land surface models, large uncertainties arise due to uncertainties of inputs and the limitations of the models. This study developed a reconstruction model for GRACE TWS anomalies (TWSA) based on the Global Land Data Assimilation System (GLDAS) model outputs by using a Random Forest (RF) regression approach. A Spatially Moving Window (SMW) structure was introduced when training the RF model to address the spatial variations of TWSA, and a linear regression approach (LR) was also used for comparison purpose. Long-term TWSA over China land area were generated based on the proposed approaches and results were validated through cross-validation and comparisons with reference datasets. As a result, the RF-based model outperforms the LR-based model, and the reconstructed TWSA by using the two models both well reproduce GRACE dataset and outperform the TWSA that are derived directly from GLDAS models. Moreover, the TWSA produced by using the presented models have good agreements with another global GRACE-based reconstructed TWSA dataset and in-situ soil moisture measurements. Importance value for each variable in the RF model was quantified as well as the spatial coefficients for each variable in the LR model. The importance values and regression coefficients present varying spatial patterns. Rather than modifying the land surface model structure and inputs, this study provides alternative ways of improving the TWS estimations of GLDAS and extending time range of GRACE datasets. The experiments are expected to promote and enrich the methodologies and theories of combining physical and statistical models for optimal simulations in geoscientific research.
资助项目	National Natural Science Foundation of China, China[41801362] ; National Natural Science Foundation of China, China[41771380] ; National Natural Science Foundation of China, China[41976190] ; National Natural Science Foundation of China, China[41601175] ; National Earth System Science Data Sharing Infrastructure, China[2005DKA32300] ; Guangdong Provincial Science and Technology Program, China[2018B030324001] ; GDAS's Project of Science and Technology Development, China[2020GDASYL-20200104003] ; GDAS's Project of Science and Technology Development, China[2016GDASRC-0211] ; GDAS's Project of Science and Technology Development, China[2017GDASCX-0601] ; GDAS's Project of Science and Technology Development, China[2018GDASCX-0101] ; GDAS's Project of Science and Technology Development, China[2018GDASCX-0403] ; GDAS's Project of Science and Technology Development, China[2019GDASYL-0502001] ; GDAS's Project of Science and Technology Development, China[2019GDASYL-0301001] ; GDAS's Project of Science and Technology Development, China[2019GDASYL-0302001] ; GDAS's Project of Science and Technology Development, China[2019GDASYL-0501001] ; GDAS's Project of Science and Technology Development, China[2019GDASYL-0401001] ; Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), China[GML2019ZD0301] ; Multidisciplinary Joint Expedition for China-Mongolia-Russia Economic Corridor[2017FY101300] ; 2018 Young Backbone Teachers Foundation from Henan Province, China[2018GGJS019] ; Program for Innovative Research Talent in the University of Henan Province, China[20HASTIT017] ; Key R&D and extension projects in Henan Province in 2019 (agriculture and social development field)[192102310002] ; tackling of key scientific and technical project of Henan Province, China[202102310339] ; Innovation Team Cultivation Project of The First-Class Discipline in Henan University, China[2018YLTD16] ; Guangdong Innovative and Entrepreneurial Research Team Program, China[2016ZT06D336]
WOS关键词	SOIL-MOISTURE ; GROUNDWATER RECHARGE ; AMAZON BASIN ; IRRIGATED CROPLAND ; CLIMATE-CHANGE ; SNOW COVER ; CHINA ; SIMULATION ; MODEL ; HETEROGENEITY
WOS研究方向	Engineering ; Geology ; Water Resources
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000599754500040
资助机构	National Natural Science Foundation of China, China ; National Earth System Science Data Sharing Infrastructure, China ; Guangdong Provincial Science and Technology Program, China ; GDAS's Project of Science and Technology Development, China ; Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), China ; Multidisciplinary Joint Expedition for China-Mongolia-Russia Economic Corridor ; 2018 Young Backbone Teachers Foundation from Henan Province, China ; Program for Innovative Research Talent in the University of Henan Province, China ; Key R&D and extension projects in Henan Province in 2019 (agriculture and social development field) ; tackling of key scientific and technical project of Henan Province, China ; Innovation Team Cultivation Project of The First-Class Discipline in Henan University, China ; Guangdong Innovative and Entrepreneurial Research Team Program, China
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/137599]
专题	中国科学院地理科学与资源研究所
通讯作者	Yang, Yaping
作者单位	1.Guangzhou Inst Geog, Key Lab Guangdong Utilizat Remote Sensing & Geog, Guangdong Open Lab Geospatial Informat Technol &, Guangzhou 510070, Peoples R China 2.Nanjing Normal Univ, Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing 210023, Peoples R China 3.Henan Univ, Coll Environm & Planning, Kaifeng 475004, Peoples R China 4.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 5.Southern Marine Sci & Engn Guangdong Lab, Guangzhou 511458, Peoples R China
推荐引用方式 GB/T 7714	Jing, Wenlong,Zhang, Pengyan,Zhao, Xiaodan,et al. Extending GRACE terrestrial water storage anomalies by combining the random forest regression and a spatially moving window structure[J]. JOURNAL OF HYDROLOGY,2020,590:17.
APA	Jing, Wenlong.,Zhang, Pengyan.,Zhao, Xiaodan.,Yang, Yaping.,Jiang, Hao.,...&Li, Yong.(2020).Extending GRACE terrestrial water storage anomalies by combining the random forest regression and a spatially moving window structure.JOURNAL OF HYDROLOGY,590,17.
MLA	Jing, Wenlong,et al."Extending GRACE terrestrial water storage anomalies by combining the random forest regression and a spatially moving window structure".JOURNAL OF HYDROLOGY 590(2020):17.