干旱区生态环境知识资源中心(Arid): Utilizing Machine Learning Models with Limited Meteorological Data as Alternatives for the FAO-56PM Model in Estimating Reference Evapotranspiration

Arid

DOI	10.1007/s11269-023-03670-2
	Utilizing Machine Learning Models with Limited Meteorological Data as Alternatives for the FAO-56PM Model in Estimating Reference Evapotranspiration
	Amani, Shima; Shafizadeh-Moghadam, Hossein; Morid, Saeid
通讯作者	Shafizadeh-Moghadam, H
来源期刊	WATER RESOURCES MANAGEMENT
ISSN	0920-4741
EISSN	1573-1650
出版年	2024
卷号	38 期号:6 页码:1921-1942
英文摘要	The current study evaluated the accuracy of four machine learning (ML) models and thirteen experimental methods calibrated to estimate reference evapotranspiration (ET0) in arid and semi-arid regions. Various scenarios were examined utilizing meteorological data and FAO56-PM as a benchmark. According to the results, the ML models outperformed the experimental methods on both daily and monthly scales. Among the ML models, artificial neural networks (ANNs), generalized additive model (GAM), random forest (RF), and support vector machine (SVM), respectively, demonstrated higher accuracy on a monthly scale, while ANNs, SVM, RF, and GAM exhibited greater accuracy on a daily scale. Notably, ANNs and SVM achieved high accuracy even with a limited number of variables. Conversely, RF showed improved accuracy with an increased number of variables. Comparing the ML and experimental models with equivalent inputs revealed that ANN with inputs similar to Valiantzas-1 performed better on a monthly scale, while SVM with inputs akin to Valiantzas-3 showed superior performance on a daily scale. Our findings suggest that average temperature, wind speed, and sunshine hours contribute significantly to the accuracy of ML models. Consequently, these ML models can serve as an alternative to the FAO56-PM method for estimating ET0.
英文关键词	Reference evapotranspiration FAO-56PM Machine learning Experimental models
类型	Article
语种	英语
开放获取类型	Green Submitted
收录类别	SCI-E
WOS记录号	WOS:001157144700005
WOS关键词	CLIMATIC DATA ; NEURAL-NETWORK ; TEMPERATURE ; EVAPORATION ; SVM ; REGRESSION ; EQUATIONS ; RADIATION ; HUMIDITY ; SOLAR
WOS类目	Engineering, Civil ; Water Resources
WOS研究方向	Engineering ; Water Resources
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/405920
推荐引用方式 GB/T 7714	Amani, Shima,Shafizadeh-Moghadam, Hossein,Morid, Saeid. Utilizing Machine Learning Models with Limited Meteorological Data as Alternatives for the FAO-56PM Model in Estimating Reference Evapotranspiration[J],2024,38(6):1921-1942.
APA	Amani, Shima,Shafizadeh-Moghadam, Hossein,&Morid, Saeid.(2024).Utilizing Machine Learning Models with Limited Meteorological Data as Alternatives for the FAO-56PM Model in Estimating Reference Evapotranspiration.WATER RESOURCES MANAGEMENT,38(6),1921-1942.
MLA	Amani, Shima,et al."Utilizing Machine Learning Models with Limited Meteorological Data as Alternatives for the FAO-56PM Model in Estimating Reference Evapotranspiration".WATER RESOURCES MANAGEMENT 38.6(2024):1921-1942.