IGSNRR OpenIR
Improving global terrestrial evapotranspiration estimation using support vector machine by integrating three process-based algorithms
Yao, Yunjun1; Liang, Shunlin1; Li, Xianglan2; Chen, Jiquan3; Liu, Shaomin4; Jia, Kun1; Zhang, Xiaotong1; Xiao, Zhiqiang1; Fisher, Joshua B.5; Mu, Qiaozhen6; Pan, Ming7; Liu, Meng8,9; Cheng, Jie1; Jiang, Bo1; Xie, Xianhong1; Gruenwald, Thomas10; Bernhofer, Christian10; Roupsard, Olivier11,12
2017-08-15
Source PublicationAGRICULTURAL AND FOREST METEOROLOGY
ISSN0168-1923
Volume242Pages:55-74
Corresponding AuthorYao, Yunjun(boyyunjun@163.com)
AbstractTerrestrial evapotranspiration (ET) for each plant functional type (PFT) is a key variable for linking the energy, water and carbon cycles of the atmosphere, hydrosphere and biosphere. Process-based algorithms have been widely used to estimate global terrestrial ET, yet each ET individual algorithm has exhibited large uncertainties. In this study, the support vector machine (SVM) method was introduced to improve global terrestrial ET estimation by integrating three process-based ET algorithms: MOD16, PT-JPL and SEMI-PM. At 200 FLUXNET flux tower sites, we evaluated the performance of the SVM method and others, including the Bayesian model averaging (BMA) method and the general regression neural networks (GRNNs) method together with three process-based ET algorithms. We found that the SVM method was superior to all other methods we evaluated. The validation results showed that compared with the individual algorithms, the SVM method driven by tower-specific (Modern Era Retrospective Analysis for Research and Applications, MERRA) meteorological data reduced the root mean square error (RMSE) by approximately 0.20 (0.15) mm/day for most forest sites and 0.30 (0.20) mm/day for most crop and grass sites and improved the squared correlation coefficient (R-2) by approximately 0.10 (0.08) (95% confidence) for most flux tower sites. The water balance of basins and the global terrestrial ET calculation analysis also demonstrated that the regional and global estimates of the SVM-merged ET were reliable. The SVM method provides a powerful tool for improving global ET estimation to characterize the long-term spatiotemporal variations of the global terrestrial water budget.
KeywordTerrestrial evapotranspiration Machine learning methods Bayesian model averaging method Plant functional type
DOI10.1016/j.agrformet.2017.04.011
WOS KeywordSURFACE-ENERGY BALANCE ; REMOTELY-SENSED DATA ; EDDY-COVARIANCE ; RIVER-BASIN ; HEAT-FLUX ; REGRESSION ALGORITHMS ; CLOSURE PROBLEM ; CARBON-DIOXIDE ; BOREAL FOREST ; MODIS
Indexed BySCI
Language英语
Funding ProjectCFCAS ; NSERC ; BIOCAP ; Environment Canada ; NRCan ; CarboEuropelP ; FAO-GTOS-TCO ; iLEAPS ; Max Planck Institute for Biogeochemistry ; National Science Foundation ; University of Tuscia ; Universite Laval ; US Department of Energy ; Natural Science Fund of China[41671331] ; National Key Research and Development Program of China[2016YFA0600102] ; National Key Research and Development Program of China[2016YFB0501404]
Funding OrganizationCFCAS ; NSERC ; BIOCAP ; Environment Canada ; NRCan ; CarboEuropelP ; FAO-GTOS-TCO ; iLEAPS ; Max Planck Institute for Biogeochemistry ; National Science Foundation ; University of Tuscia ; Universite Laval ; US Department of Energy ; Natural Science Fund of China ; National Key Research and Development Program of China
WOS Research AreaAgriculture ; Forestry ; Meteorology & Atmospheric Sciences
WOS SubjectAgronomy ; Forestry ; Meteorology & Atmospheric Sciences
WOS IDWOS:000403988500006
PublisherELSEVIER SCIENCE BV
Citation statistics
Cited Times:18[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.igsnrr.ac.cn/handle/311030/63162
Collection中国科学院地理科学与资源研究所
Corresponding AuthorYao, Yunjun
Affiliation1.Beijing Normal Univ, State Key Lab Remote Sensing Sci, Inst Remote Sensing Sci & Engn, Fac Geog Sci, Beijing 100875, Peoples R China
2.Beijing Normal Univ, Coll Global Change & Earth Syst Sci, Beijing 100875, Peoples R China
3.Michigan State Univ, CGCEO Geog, E Lansing, MI 48823 USA
4.Beijing Normal Univ, State Key Lab Earth Surface Proc & Resource Ecol, Sch Nat Resources, Fac Geog Sci, Beijing 100875, Peoples R China
5.CALTECH, Jet Prop Lab, 4800 Oak Grove Dr, Pasadena, CA 91109 USA
6.Univ Montana, Numer Terradynam Simulat Grp, Dept Ecosyst & Conservat Sci, Missoula, MT 59812 USA
7.Princeton Univ, Dept Civil & Environm Engn, Princeton, NJ 08544 USA
8.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China
9.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
10.Tech Univ Dresden, Inst Hydrol & Meteorol, Chair Meteorol, D-01062 Dresden, Germany
11.CIRAD, UMR Eco & Sols Ecol Fonct & Biogeochim Sols & Agr, F-34060 Montpellier, France
12.CATIE Trop Agr Ctr Res & Higher Educ, Turrialba 7170, Costa Rica
Recommended Citation
GB/T 7714
Yao, Yunjun,Liang, Shunlin,Li, Xianglan,et al. Improving global terrestrial evapotranspiration estimation using support vector machine by integrating three process-based algorithms[J]. AGRICULTURAL AND FOREST METEOROLOGY,2017,242:55-74.
APA Yao, Yunjun.,Liang, Shunlin.,Li, Xianglan.,Chen, Jiquan.,Liu, Shaomin.,...&Roupsard, Olivier.(2017).Improving global terrestrial evapotranspiration estimation using support vector machine by integrating three process-based algorithms.AGRICULTURAL AND FOREST METEOROLOGY,242,55-74.
MLA Yao, Yunjun,et al."Improving global terrestrial evapotranspiration estimation using support vector machine by integrating three process-based algorithms".AGRICULTURAL AND FOREST METEOROLOGY 242(2017):55-74.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yao, Yunjun]'s Articles
[Liang, Shunlin]'s Articles
[Li, Xianglan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yao, Yunjun]'s Articles
[Liang, Shunlin]'s Articles
[Li, Xianglan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yao, Yunjun]'s Articles
[Liang, Shunlin]'s Articles
[Li, Xianglan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.