干旱区生态环境知识资源中心(Arid): A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates

Arid

DOI	10.3390/atmos10060311
	A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates
	Valipour, Mohammad 1; Sefidkouhi, Mohammad Ali Gholami 2; Raeini-Sarjaz, Mahmoud 2; Guzman, Sandra M.1
通讯作者	Valipour, Mohammad
来源期刊	ATMOSPHERE
EISSN	2073-4433
出版年	2019
卷号	10 期号:6
英文摘要	In the current research, gene expression programming (GEP) was applied to model reference evapotranspiration (ETo) in 18 regions of Iran with limited meteorological data. Initially, a genetic algorithm (GA) was employed to detect the most important variables for estimating ETo among mean temperature (Tmean), maximum temperature (Tmax), minimum temperature (Tmin), relative humidity (RH), sunshine (n), and wind speed (WS). The results indicated that a coupled model containing the Tmean and WS can predict ETo accurately (RMSE = 0.3263 mm day(-1)) for arid, semiarid, and Mediterranean climates. Therefore, this model was adjusted using the GEP for all 18 synoptic stations. Under very humid climates, it is recommended to use a temperature-based GEP model versus wind speed-based GEP model. The optimal and lowest performance of the GEP belonged to Shahrekord (SK), RMSE = 0.0650 mm day(-1), and Kerman (KE), RMSE = 0.4177 mm day(-1), respectively. This research shows that the GEP is a robust tool to model ETo in semiarid and Mediterranean climates (R-2 > 0.80). However, GEP is recommended to be used cautiously under very humid climates and some of arid regions (R-2 < 0.50) due to its poor performance under such extreme conditions.
英文关键词	machine learning crop water requirement Iran hydrological extremes uncertainty weather parameters
类型	Article
语种	英语
国家	USA ; Iran
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000473749900020
WOS关键词	GENETIC PROGRAMMING APPROACH ; ARTIFICIAL-INTELLIGENCE ; NEURAL-NETWORKS ; PERFORMANCE ; CALIBRATION ; PREDICTION ; EQUATION ; SOUTH
WOS类目	Environmental Sciences ; Meteorology & Atmospheric Sciences
WOS研究方向	Environmental Sciences & Ecology ; Meteorology & Atmospheric Sciences
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/214448
作者单位	1.Univ Florida, Indian River Res & Educ Ctr, Dept Agr & Biol Engn, Ft Pierce, FL 34945 USA; 2.Sari Agr Sci & Nat Resources Univ, Dept Water Engn, Sari, Iran
推荐引用方式 GB/T 7714	Valipour, Mohammad,Sefidkouhi, Mohammad Ali Gholami,Raeini-Sarjaz, Mahmoud,et al. A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates[J],2019,10(6).
APA	Valipour, Mohammad,Sefidkouhi, Mohammad Ali Gholami,Raeini-Sarjaz, Mahmoud,&Guzman, Sandra M..(2019).A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates.ATMOSPHERE,10(6).
MLA	Valipour, Mohammad,et al."A Hybrid Data-Driven Machine Learning Technique for Evapotranspiration Modeling in Various Climates".ATMOSPHERE 10.6(2019).