Support-Vector-Machine-Based Models for Modeling Daily Reference Evapotranspiration With Limited Climatic Data in Extreme Arid Regions (EI)

CORC > 寒区旱区环境与工程研究所 > 中科院寒区旱区环境与工程研究所（未分类） > 期刊论文

	Support-Vector-Machine-Based Models for Modeling Daily Reference Evapotranspiration With Limited Climatic Data in Extreme Arid Regions (EI)
	Wen X.; Si J.; He Z.; Wu J.; Shao H.; Yu H.
刊名	Water Resources Management
	2015
卷号	29 期号:9 页码:3195-3209
英文摘要	Evapotranspiration is a major factor that controls hydrological process and its accurate estimation provides valuable information for water resources planning and management, particularly in extremely arid regions. The objective of this research was to evaluate the use of a support vector machine (SVM) to model daily reference evapotranspiration (ETinf0/inf) using limited climatic data. For the SVM, four combinations of maximum air temperature (Tinfmax/inf), minimum air temperature (Tinfmin/inf), wind speed (Uinf2/inf) and daily solar radiation (Rinfs/inf) in the extremely arid region of Ejina basin, China, were used as inputs with Tinfmax/inf and Tinfmin/inf as the base data set. The results of SVM models were evaluated by comparing the output with the ETinf0/inf calculated using PenmanMonteith FAO 56 equation (PMF-56). We found that the ETinf0/inf estimated using SVM with limited climatic data was in good agreement with those obtained using the conventional PMF-56 equation employing the full complement of meteorological data. In particular, three climatic parameters, Tinfmax/inf, Tinfmin/inf, and Rinfs/inf were enough to predict the daily ETinf0/inf satisfactorily. Moreover, the performance of SVM method was also compared with that of artificial neural network (ANN) and three empirical models including Priestley-Taylor, Hargreaves, and Ritchie. The results showed that the performance of SVM method was the best among these models. This offers significant potential for more accurate estimation of the ETinf0/inf with scarce data in extreme arid regions. 2015, Springer Science+Business Media Dordrecht.
收录类别	EI
语种	英语
内容类型	期刊论文
源URL	[http://ir.casnw.net/handle/362004/27111]
专题	寒区旱区环境与工程研究所_中科院寒区旱区环境与工程研究所（未分类）_期刊论文
推荐引用方式 GB/T 7714	Wen X.,Si J.,He Z.,et al. Support-Vector-Machine-Based Models for Modeling Daily Reference Evapotranspiration With Limited Climatic Data in Extreme Arid Regions (EI)[J]. Water Resources Management,2015,29(9):3195-3209.
APA	Wen X.,Si J.,He Z.,Wu J.,Shao H.,&Yu H..(2015).Support-Vector-Machine-Based Models for Modeling Daily Reference Evapotranspiration With Limited Climatic Data in Extreme Arid Regions (EI).Water Resources Management,29(9),3195-3209.
MLA	Wen X.,et al."Support-Vector-Machine-Based Models for Modeling Daily Reference Evapotranspiration With Limited Climatic Data in Extreme Arid Regions (EI)".Water Resources Management 29.9(2015):3195-3209.