Real-time prediction of river chloride concentration using ensemble learning

doi:10.1016/j.envpol.2021.118116

	Real-time prediction of river chloride concentration using ensemble learning
	Zhang, Qianqian 1,2; Li, Zhong 2; Zhu, Lu 3; Zhang, Fei 4,5; Sekerinski, Emil 6; Han, Jing-Cheng 7; Zhou, Yang 7
刊名	ENVIRONMENTAL POLLUTION
	2021-12-15
卷号	291 页码:12
关键词	Chloride prediction MLP-SCA Ensemble learning Stepwise-cluster analysis Multi-layer perceptron
ISSN号	0269-7491
DOI	10.1016/j.envpol.2021.118116
通讯作者	Li, Zhong(zoeli@mcmaster.ca)
英文摘要	Real-time river chloride prediction has received a lot of attention for its importance in chloride control and management. In this study, an artificial neural network model (i.e., multi-layer perceptron, MLP) and a statistical inference model (i.e., stepwise-cluster analysis, SCA) are developed for predicting chloride concentration in stream water. Then, an ensemble learning model based on MLP and SCA is proposed to further improve the modeling accuracy. A case study of hourly river chloride prediction in the Grand River, Canada is presented to demonstrate the model applicability. The results show that the proposed ensemble learning model, MLP-SCA, provides the best overall performance compared with its two ensemble members in terms of RMSE, MAPE, NSE, and R-2 with values of 11.58 mg/L, 27.55%, 0.90, and 0.90, respectively. Moreover, MLP-SCA is more competent for predicting extremely high chloride concentration. The prediction of observed concentrations above 150 mg/L has RMSE and MAPE values of 9.88 mg/L and 4.40%, respectively. The outstanding performance of the proposed MLP-SCA, particularly in extreme value prediction, indicates that it can provide reliable chloride prediction using commonly available data (i.e., conductivity, water temperature, river flow rate, and rainfall). The high-frequency prediction of chloride concentration in the Grand River can supplement the existing water quality monitoring programs, and further support the real-time control and management of chloride in the watershed. MLP-SCA is the first ensemble learning model for river chloride prediction and can be extended to other river systems for water quality prediction.
资助项目	MacDATA Institute at McMaster University, Canada
WOS关键词	STEPWISE CLUSTER-ANALYSIS ; LOW-FLOW NITRATE ; NEURAL-NETWORK ; MULTILAYER PERCEPTRON ; AIR-QUALITY ; WATER ; REGRESSION ; DISCHARGE ; SYSTEM ; MODEL
WOS研究方向	Environmental Sciences & Ecology
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000697348900006
资助机构	MacDATA Institute at McMaster University, Canada
内容类型	期刊论文
源URL	[http://ir.ieecas.cn/handle/361006/17031]
专题	地球环境研究所_加速器质谱中心第四纪科学与全球变化卓越创新中心
通讯作者	Li, Zhong
作者单位	1.Chengdu Univ Informat Technol, Chengdu 610225, Peoples R China 2.McMaster Univ, Dept Civil Engn, Hamilton, ON L8S 4L8, Canada 3.McMaster Univ, Dept Chem Engn, Hamilton, ON L8S 4L8, Canada 4.Chinese Acad Sci, Inst Earth Environm, SKLLQG, Xian 710061, Peoples R China 5.CAS Ctr Excellence Quaternary Sci & Global Change, Xian 710061, Peoples R China 6.McMaster Univ, Dept Comp & Software, Hamilton, ON L8S 4L8, Canada 7.Shenzhen Univ, Coll Chem & Environm Engn, Water Sci & Environm Engn Res Ctr, Shenzhen 518060, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Qianqian,Li, Zhong,Zhu, Lu,et al. Real-time prediction of river chloride concentration using ensemble learning[J]. ENVIRONMENTAL POLLUTION,2021,291:12.
APA	Zhang, Qianqian.,Li, Zhong.,Zhu, Lu.,Zhang, Fei.,Sekerinski, Emil.,...&Zhou, Yang.(2021).Real-time prediction of river chloride concentration using ensemble learning.ENVIRONMENTAL POLLUTION,291,12.
MLA	Zhang, Qianqian,et al."Real-time prediction of river chloride concentration using ensemble learning".ENVIRONMENTAL POLLUTION 291(2021):12.