干旱区生态环境知识资源中心(Arid): Assessing temporal data partitioning scenarios for estimating reference evapotranspiration with machine learning techniques in arid regions

Arid

DOI	10.1016/j.jhydrol.2020.125252
	Assessing temporal data partitioning scenarios for estimating reference evapotranspiration with machine learning techniques in arid regions
	Kazemi, Mohammad Hossein; Shiri, Jalal; Marti, Pau; Majnooni-Heris, Abolfazl
通讯作者	Shiri, J (corresponding author), Univ Tabriz, Fac Agr, Water Engn Dept, Tabriz, Iran.
来源期刊	JOURNAL OF HYDROLOGY
ISSN	0022-1694
EISSN	1879-2707
出版年	2020
卷号	590
英文摘要	Recently, data driven machine learning techniques has been widely applied for modeling reference evapotranspiration (ETo) values under various climatic conditions taking into account the different number of sites and available data length. A major issue with applying those models is the proper selection of training/testing data sets. Although some spatial generalization approaches have been recommended for this purpose, there are no specified recommended local (temporal) data partitioning strategies for machine learning based ETo estimation. The present study evaluates different hold-out and k-fold validation temporal data partitioning strategies when using gene expression programming (GEP) technique to estimate daily ETo in arid regions. The k-fold validation strategies considered annual, monthly and growing season period patterns as test data sets. Although commonly used partitioning of the available patterns into training and testing sets gave accurate results, statistical analysis showed that the results obtained through k-fold validation assessment were more reliable. A two-block partitioning strategy with chronologic data selection for training and testing provided the most accurate results among the hold-out procedures (mean scatter index (SI) value of 0.162). Fixing the extreme ETo values as training data set in hold-out procedures provided the less accurate results with considerable over/underestimation of the ETo values (mean SI value was 0.506). Results on the basis of hold-out approaches can be biased or only partially valid depending on selection of the test data from the time series. K-fold validation yielded the lowest over/underestimations of ETo values. Further, considering monthly patterns as minimum affordable test size produced higher error magnitudes among k-fold validation strategies, while considering the complete patterns of one growing season provided more accurate results among k-fold validation strategies.
英文关键词	Evapotranspiration Gene expression programming Hold out K-fold validation
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000599754500053
WOS关键词	MODELING REFERENCE EVAPOTRANSPIRATION ; NEURAL-NETWORKS ; TIME-SERIES ; TEMPERATURE ; ALGORITHMS ; STRATEGIES ; EQUATIONS ; SELECTION
WOS类目	Engineering, Civil ; Geosciences, Multidisciplinary ; Water Resources
WOS研究方向	Engineering ; Geology ; Water Resources
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/349001
作者单位	[Kazemi, Mohammad Hossein; Shiri, Jalal; Majnooni-Heris, Abolfazl] Univ Tabriz, Fac Agr, Water Engn Dept, Tabriz, Iran; [Shiri, Jalal] Univ Tabriz, Fac Civil Engn, Ctr Excellence Hydroinformat, Tabriz, Iran; [Marti, Pau] Univ Illes Balears, Area Engn Agroforestal, Carretera Valldemossa Km 7-5, Palma De Mallorca 07022, Spain
推荐引用方式 GB/T 7714	Kazemi, Mohammad Hossein,Shiri, Jalal,Marti, Pau,et al. Assessing temporal data partitioning scenarios for estimating reference evapotranspiration with machine learning techniques in arid regions[J],2020,590.
APA	Kazemi, Mohammad Hossein,Shiri, Jalal,Marti, Pau,&Majnooni-Heris, Abolfazl.(2020).Assessing temporal data partitioning scenarios for estimating reference evapotranspiration with machine learning techniques in arid regions.JOURNAL OF HYDROLOGY,590.
MLA	Kazemi, Mohammad Hossein,et al."Assessing temporal data partitioning scenarios for estimating reference evapotranspiration with machine learning techniques in arid regions".JOURNAL OF HYDROLOGY 590(2020).