干旱区生态环境知识资源中心(Arid): Interpretable vs. noninterpretable machine learning models for data-driven hydro-climatological process modeling (R)

Arid

DOI	10.1016/j.eswa.2020.114498
	Interpretable vs. noninterpretable machine learning models for data-driven hydro-climatological process modeling (R)
	Chakraborty, Debaditya; Basagaoglu, Hakan; Winterle, James
通讯作者	Chakraborty, D (corresponding author), Univ Texas San Antonio, Dept Construct Sci, 501 W Cesar E Chavez Blvd, San Antonio, TX 78207 USA.
来源期刊	EXPERT SYSTEMS WITH APPLICATIONS
ISSN	0957-4174
EISSN	1873-6793
出版年	2021
卷号	170
英文摘要	Due to their enhanced predictive capabilities, noninterpretable machine learning (ML) models (e.g. deep learning) have recently gained a growing interest in analyzing and modeling earth & planetary science data. However, noninterpretable ML models are often treated as ?black boxes? by end-users, which could limit their applicability in critical decision making processes. In this paper, we compared the predictive capabilities of three interpretable ML models with three noninterpretable ML models to answer the overarching question: Is it essential to use noninterpretable ML models for enhanced model predictions from hydro-climatological datasets? The ML model development and comparative analysis were performed using measured climate data and synthetic reference crop evapotranspiration (ETo) data, with varying levels of missing values, from five weather stations across the karstic Edwards aquifer region in semi-arid south-central Texas. Our analysis revealed that interpretable tree based ensemble models produce comparable results to noninterpretable deep learning models on structured hydro-climatological datasets. We showed that the tree-based ensemble model is also capable of imputing varying levels of missing climate data at the weather stations, employing the newly developed sequential transfer-learning technique. We applied an explainable machine learning (eXML) framework to quantify the global order of importance of hydro-climatic (predictor) variables on ETo, while highlighting the local dependencies and interactions amongst the predictors and ETo. The eXML framework also revealed the inflection points of the climate variables at which the transition from low to high daily ETo rates occur. The ancillary explainability of ML models are expected to increase users? confidence and support any future decision-making process in water resource management.
英文关键词	Deep learning Boosting Transfer learning Hydroclimate Reference crop evapotranspiration Model explainability
类型	Article
语种	英语
收录类别	SCI-E
WOS记录号	WOS:000626414500001
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Operations Research & Management Science
WOS研究方向	Computer Science ; Engineering ; Operations Research & Management Science
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/368772
作者单位	[Chakraborty, Debaditya] Univ Texas San Antonio, Dept Construct Sci, 501 W Cesar E Chavez Blvd, San Antonio, TX 78207 USA; [Basagaoglu, Hakan; Winterle, James] Edwards Aquifer Author, 900 E Quincy St, San Antonio, TX 78215 USA
推荐引用方式 GB/T 7714	Chakraborty, Debaditya,Basagaoglu, Hakan,Winterle, James. Interpretable vs. noninterpretable machine learning models for data-driven hydro-climatological process modeling (R)[J],2021,170.
APA	Chakraborty, Debaditya,Basagaoglu, Hakan,&Winterle, James.(2021).Interpretable vs. noninterpretable machine learning models for data-driven hydro-climatological process modeling (R).EXPERT SYSTEMS WITH APPLICATIONS,170.
MLA	Chakraborty, Debaditya,et al."Interpretable vs. noninterpretable machine learning models for data-driven hydro-climatological process modeling (R)".EXPERT SYSTEMS WITH APPLICATIONS 170(2021).