气候变化领域集成服务门户(CCPortal): Random forest predictive model development with uncertainty analysis capability for the estimation of evapotranspiration in an arid oasis region

CCPortal

DOI	10.2166/nh.2020.012
	Random forest predictive model development with uncertainty analysis capability for the estimation of evapotranspiration in an arid oasis region
	Wu, Min; Feng, Qi; Wen, Xiaohu; Deo, Ravinesh C.; Yin, Zhenliang; Yang, Linshan; Sheng, Danrui
发表日期	2020
ISSN	0029-1277
EISSN	2224-7955
起始页码	648
结束页码	665
卷号	51 期号:4
英文摘要	The study evaluates the potential utility of the random forest (RF) predictive model used to simulate daily reference evapotranspiration (ET0) in two stations located in the arid oasis area of northwestern China. To construct an accurate RF-based predictive model, ET(0)is estimated by an appropriate combination of model inputs comprising maximum air temperature (T-max), minimum air temperature (T-min), sunshine durations (S-un), wind speed (U-2), and relative humidity (R-h). The output of RF models are tested by ET(0)calculated using Penman-Monteith FAO 56 (PMF-56) equation. Results showed that the RF model was considered as a better way to predict ET(0)for the arid oasis area with limited data. Besides,R(h)was the most influential factor on the behavior of ET0, except for air temperature in the proposed arid area. Moreover, the uncertainty analysis with a Monte Carlo method was carried out to verify the reliability of the results, and it was concluded that RF model had a lower uncertainty and can be used successfully in simulating ET0. The proposed study shows RF as a sound modeling approach for the prediction of ET(0)in the arid areas where reliable weather data sets are available, but relatively limited.
英文关键词	arid areas; evapotranspiration; Monte Carlo; predict; random forest
WOS研究方向	Water Resources
WOS类目	Water Resources
WOS关键词	ARTIFICIAL NEURAL-NETWORK ; SUPPORT-VECTOR-MACHINE ; LIMITED CLIMATIC DATA ; WEATHER PARAMETERS ; REGRESSION ; CLASSIFICATION ; SVM
WOS记录号	WOS:000565303800005
来源期刊	HYDROLOGY RESEARCH
来源机构	中国科学院西北生态环境资源研究院
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/239342
作者单位	[Wu, Min; Feng, Qi; Wen, Xiaohu; Yin, Zhenliang; Yang, Linshan; Sheng, Danrui] Chinese Acad Sci, Northwest Inst Ecoenvironm & Resources, Key Lab Ecohydrol Inland River Basin, Lanzhou 730000, Peoples R China; [Wu, Min; Sheng, Danrui] Univ Chinese Acad Sci, Beijing 100049, Peoples R China; [Deo, Ravinesh C.] Univ Southern Queensland, Sch Agr Computat & Environm Sci, Ctr Sustainable Agr Syst, Springfield, Qld 4300, Australia
推荐引用方式 GB/T 7714	Wu, Min,Feng, Qi,Wen, Xiaohu,et al. Random forest predictive model development with uncertainty analysis capability for the estimation of evapotranspiration in an arid oasis region[J]. 中国科学院西北生态环境资源研究院,2020,51(4).
APA	Wu, Min.,Feng, Qi.,Wen, Xiaohu.,Deo, Ravinesh C..,Yin, Zhenliang.,...&Sheng, Danrui.(2020).Random forest predictive model development with uncertainty analysis capability for the estimation of evapotranspiration in an arid oasis region.HYDROLOGY RESEARCH,51(4).
MLA	Wu, Min,et al."Random forest predictive model development with uncertainty analysis capability for the estimation of evapotranspiration in an arid oasis region".HYDROLOGY RESEARCH 51.4(2020).