干旱区生态环境知识资源中心(Arid): Reliable Evapotranspiration Predictions with a Probabilistic Machine Learning Framework

Arid

DOI	10.3390/w13040557
	Reliable Evapotranspiration Predictions with a Probabilistic Machine Learning Framework
	Basagaoglu, Hakan; Chakraborty, Debaditya; Winterle, James
通讯作者	Basagaoglu, H (corresponding author), Edwards Aquifer Author, San Antonio, TX 78215 USA.
来源期刊	WATER
EISSN	2073-4441
出版年	2021
卷号	13 期号:4
英文摘要	Evapotranspiration is often expressed in terms of reference crop evapotranspiration (ETo), actual evapotranspiration (ETa), or surface water evaporation (E-sw), and their reliable predictions are critical for groundwater, irrigation, and aquatic ecosystem management in semi-arid regions. We demonstrated that a newly developed probabilistic machine learning (ML) model, using a hybridized boosting framework, can simultaneously predict the daily ETo, E-sw, & ETa from local hydroclimate data with high accuracy. The probabilistic approach exhibited great potential to overcome data uncertainties, in which 100% of the ETo, 89.9% of the E-sw, and 93% of the ETa test data at three watersheds were within the models' 95% prediction intervals. The modeling results revealed that the hybrid boosting framework can be used as a reliable computational tool to predict ETo while bypassing net solar radiation calculations, estimate E-sw while overcoming uncertainties associated with pan evaporation & pan coefficients, and predict ETa while offsetting high capital & operational costs of EC towers. In addition, using the Shapley analysis built on a coalition game theory, we identified the order of importance and interactions between the hydroclimatic variables to enhance the models' transparency and trustworthiness.
英文关键词	evapotranspiration machine learning probabilistic model shapley analysis
类型	Article
语种	英语
开放获取类型	gold
收录类别	SCI-E
WOS记录号	WOS:000624883500001
WOS类目	Environmental Sciences ; Water Resources
WOS研究方向	Environmental Sciences & Ecology ; Water Resources
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/351938
作者单位	[Basagaoglu, Hakan; Winterle, James] Edwards Aquifer Author, San Antonio, TX 78215 USA; [Chakraborty, Debaditya] Univ Texas San Antonio, Dept Construct Sci, San Antonio, TX 78207 USA
推荐引用方式 GB/T 7714	Basagaoglu, Hakan,Chakraborty, Debaditya,Winterle, James. Reliable Evapotranspiration Predictions with a Probabilistic Machine Learning Framework[J],2021,13(4).
APA	Basagaoglu, Hakan,Chakraborty, Debaditya,&Winterle, James.(2021).Reliable Evapotranspiration Predictions with a Probabilistic Machine Learning Framework.WATER,13(4).
MLA	Basagaoglu, Hakan,et al."Reliable Evapotranspiration Predictions with a Probabilistic Machine Learning Framework".WATER 13.4(2021).