Improving terrestrial evapotranspiration estimation across China during 2000-2018 with machine learning methods

doi:10.1016/j.jhydrol.2021.126538

	Improving terrestrial evapotranspiration estimation across China during 2000-2018 with machine learning methods
	Yin, Lichang 1,2; Tao, Fulu 1,2,3; Chen, Yi 1,2; Liu, Fengshan 1,4; Hu, Jian 5
刊名	JOURNAL OF HYDROLOGY
	2021-09-01
卷号	600 页码:18
关键词	Evapotranspiration Machine learning process-based ET ET integration China Gaussian process regression
ISSN号	0022-1694
DOI	10.1016/j.jhydrol.2021.126538
通讯作者	Tao, Fulu(taofl@igsnrr.ac.cn)
英文摘要	Estimating terrestrial evapotranspiration (ET) accurately at various temporal and spatial scales is crucial for understanding the hydrological cycle and water resource management. The currently available ET estimates have some uncertainties and need to be further improved. In this study, six machine learning methods including the random forests, support vector machine, Gaussian process regression (GPR), ensemble trees, general regression neural network, and Bayesian Model Averaging, are applied and evaluated to improve China terrestrial ET estimation by integrating five process-based ET algorithms including SEMI-PM, RS-PM, RRS-PM, MOD16, and PMLv2. Then evaluations are conducted with the eddy covariance flux observations at 14 China flux tower sites distributing in forest, shrub, wetland, grassland, and cropland, as well as with water balance-based ET at basin scale. According to the multiple training, validation, and testing, the GPR method is superior to all the other methods. Compared with the individual algorithms, the GPR method can reduce the root mean square error (RMSE) by 0.45 mm day(-1) (for SEMI-PM) similar to 0.81 mm day(-1) (for PMLv2), improve the coefficient of determination (R-2) by 0.061 (for PMLv2) similar to 0.33 (for MOD16), and decrease the absolute relative percent error (RPE) by 8.32% (for RS-PM) similar to 42.47% (for PMLv2) for all the test data. At basin scale, the results demonstrate that the annual GPR-merged China terrestrial ET is reliable (R-2 = 0.88, RMSE = 57.18 mm year RPE = -0.26%) and has higher accuracy than the currently available eight high-resolution ET products and the estimates from the other five machine learning methods and the five single ET models. The annual average terrestrial ET across China for 2000-2018 estimated by the GPR method is approximately 397.65 mm year More ground-based observations of terrestrial ET covering various land types should be collected to update the integrating methods and improve ET estimates. The resultant China terrestrial ET product with a spatial and temporal resolution of 1 km and 10 days (ChinaET 1 km 10days) produced by the GPR method is available at https://doi.org/10.6084/m9.fighare.12278684.v5.
资助项目	National Key Research and Development Program of China[2017YFA0604703] ; National Science Foundation of China[41571493] ; National Science Foundation of China[31761143006] ; National Earth System Science Data Center, National Science & Technology Infrastructure of China
WOS关键词	LATENT-HEAT FLUX ; EDDY-COVARIANCE ; GLOBAL EVAPOTRANSPIRATION ; COMPREHENSIVE EVALUATION ; RIVER-BASIN ; WATER ; EVAPORATION ; MODIS ; ALGORITHM ; UNCERTAINTY
WOS研究方向	Engineering ; Geology ; Water Resources
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000685246900044
资助机构	National Key Research and Development Program of China ; National Science Foundation of China ; National Earth System Science Data Center, National Science & Technology Infrastructure of China
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/165263]
专题	中国科学院地理科学与资源研究所
通讯作者	Tao, Fulu
作者单位	1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Key Lab Land Surface Pattern & Simulat, Beijing 100101, Peoples R China 2.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China 3.Nat Resources Inst Finland Luke, FI-00790 Helsinki, Finland 4.Fujian Agr & Forestry Univ, China Natl Engn Res Ctr JUNCAO Technol, Fuzhou 350002, Peoples R China 5.Southwest Minzu Univ, Inst Qinghai Tibetan Plateau, Chengdu 610041, Peoples R China
推荐引用方式 GB/T 7714	Yin, Lichang,Tao, Fulu,Chen, Yi,et al. Improving terrestrial evapotranspiration estimation across China during 2000-2018 with machine learning methods[J]. JOURNAL OF HYDROLOGY,2021,600:18.
APA	Yin, Lichang,Tao, Fulu,Chen, Yi,Liu, Fengshan,&Hu, Jian.(2021).Improving terrestrial evapotranspiration estimation across China during 2000-2018 with machine learning methods.JOURNAL OF HYDROLOGY,600,18.
MLA	Yin, Lichang,et al."Improving terrestrial evapotranspiration estimation across China during 2000-2018 with machine learning methods".JOURNAL OF HYDROLOGY 600(2021):18.