A Machine Learning-Based Geostatistical Downscaling Method for Coarse-Resolution Soil Moisture Products

doi:10.1109/JSTARS.2020.3035386

	A Machine Learning-Based Geostatistical Downscaling Method for Coarse-Resolution Soil Moisture Products
	Jin, Yan 3; Ge, Yong 4; Liu, Yaojie 1; Chen, Yuehong 5; Zhang, Haitao 3; Heuvelink, Gerard B. M.2
刊名	IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
	2021
卷号	14 页码:1025-1037
关键词	Spatial resolution Interpolation Support vector machines Mathematical model Market research Soil moisture Monitoring Area-to-area kriging downscaling soil moisture support vector regression
ISSN号	1939-1404
DOI	10.1109/JSTARS.2020.3035386
通讯作者	Ge, Yong(gey@lreis.ac.cn)
英文摘要	The surface soil moisture (SSM) products derived from microwave remote sensing have a coarse spatial resolution; therefore, downscaling is required to obtain accurate SSM at high spatial resolution. An effective way to handle the stratified heterogeneity is to model for various stratifications; however, the number of samples is often limited under each stratification, influencing the downscaling accuracy. In this study, a machine learning-based geostatistical model, which combines various kinds of ancillary information at fine spatial scale, is developed for spatial downscaling. The proposed support vector area-to-area regression kriging (SVATARK) model incorporates support vector regression and area-to-area kriging by considering the nonlinear relationships among variables for various stratifications. SVATARK also considers the change of support problem in the downscaling interpolation process as well as for solving the small sample size in trend prediction. The SVATARK method is evaluated in the Naqu region on the Tibetan Plateau, China, to downscale the European Space Agency's (ESA) 25-km-resolution SSM product. The 1-km-resolution SSM predictions have been produced every eight days over a six-year period (2010-2015). Compared with five other downscaling methods, the downscaled predictions from the SVATARK method performs the best with in situ observations, resulting in a 24.4% reduction in root-mean-square error with 0.08 m(3)center dot m(-3) and a 8.2% increase in correlation coefficient with 0.72, on average. Additionally, anomalously low SSM values, an indicator of drought, had a record low anomaly in mid-July for 2015, as noted by previous studies, indicating that SVATARK could be utilized for drought monitoring.
资助项目	National Natural Science Foundation for Distinguished Young Scholars of China[41725006] ; National Natural Science Foundation of China[42001332] ; National Natural Science Foundation of China[42001375] ; National Natural Science Foundation of China[41531174] ; National Natural Science Foundation of China[41531179] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDA20030302] ; Scientific Research Fund of Nanjing University of Posts and Telecommunications under NUPTSF[NY219035]
WOS研究方向	Engineering ; Physical Geography ; Remote Sensing ; Imaging Science & Photographic Technology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000607413900032
资助机构	National Natural Science Foundation for Distinguished Young Scholars of China ; National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Sciences ; Scientific Research Fund of Nanjing University of Posts and Telecommunications under NUPTSF
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/136722]
专题	中国科学院地理科学与资源研究所
通讯作者	Ge, Yong
作者单位	1.Nanjing Univ, Int Inst Earth Syst Sci, Nanjing 210023, Peoples R China 2.Wageningen Univ, Soil Geog & Landscape Grp, NL-6700 AA Wageningen, Netherlands 3.Nanjing Univ Posts & Telecommun, Sch Geog & Biol Informat, Nanjing 210023, Peoples R China 4.Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 5.Hohai Univ, Sch Earth Sci & Engn, Nanjing 210098, Peoples R China
推荐引用方式 GB/T 7714	Jin, Yan,Ge, Yong,Liu, Yaojie,et al. A Machine Learning-Based Geostatistical Downscaling Method for Coarse-Resolution Soil Moisture Products[J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,2021,14:1025-1037.
APA	Jin, Yan,Ge, Yong,Liu, Yaojie,Chen, Yuehong,Zhang, Haitao,&Heuvelink, Gerard B. M..(2021).A Machine Learning-Based Geostatistical Downscaling Method for Coarse-Resolution Soil Moisture Products.IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING,14,1025-1037.
MLA	Jin, Yan,et al."A Machine Learning-Based Geostatistical Downscaling Method for Coarse-Resolution Soil Moisture Products".IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 14(2021):1025-1037.