Prediction of long-term water quality using machine learning enhanced by Bayesian optimisation

Tao Yan; Annan Zhou; Shui-Long Shen

doi:10.1016/j.envpol.2022.120870

Prediction of long-term water quality using machine learning enhanced by Bayesian optimisation

Environ Pollut. 2023 Feb 1:318:120870. doi: 10.1016/j.envpol.2022.120870. Epub 2022 Dec 13.

Authors

Tao Yan¹, Annan Zhou², Shui-Long Shen³

Affiliations

¹ MOE Key Laboratory of Intelligent Manufacturing Technology, Department of Civil and Environmental Engineering, College of Engineering, Shantou University, Shantou, Guangdong, 515063, China; Discipline of Civil and Infrastructure Engineering, School of Engineering, Royal Melbourne Institute of Technology (RMIT), Victoria, 3001, Australia. Electronic address: yantao@stu.edu.cn.
² Discipline of Civil and Infrastructure Engineering, School of Engineering, Royal Melbourne Institute of Technology (RMIT), Victoria, 3001, Australia. Electronic address: annan.zhou@rmit.edu.au.
³ MOE Key Laboratory of Intelligent Manufacturing Technology, Department of Civil and Environmental Engineering, College of Engineering, Shantou University, Shantou, Guangdong, 515063, China. Electronic address: shensl@stu.edu.cn.

PMID: 36526051
DOI: 10.1016/j.envpol.2022.120870

Abstract

Water quality assessment is critical to better recognise the importance of water in human society. In this study, a new framework to predict long-term water quality is proposed by using Bayesian-optimised machine learning methods and key pollution indicators collected from monitoring stations in the Pearl River Estuary, Guangdong, China. The optimised stacked generalisation (SG-op) model achieved the best performance with the highest accuracy (0.992) and Kappa coefficient (0.987). Feature importance of the prediction model was consistent with key pollution indicators. The Spearman rank correlation coefficient was used to determine the significance level of the variation trends of different pollution indicators. The results show that the total phosphorus (TOP), dissolved oxygen (DO), chemical oxygen demand (COD), and petroleum (PET) among the key pollution indicators were on an upward trend in the study area. This framework can be applied to efficiently predict future water quality and to provide technical support for emergency pollution control.

Keywords: Bayesian optimisation; Key pollution indicators; Machine learning; Trend analysis; Water quality prediction.

MeSH terms

Bayes Theorem
China
Environmental Monitoring / methods
Humans
Machine Learning
Phosphorus / analysis
Rivers
Water Pollutants, Chemical* / analysis
Water Quality*

Substances

Water Pollutants, Chemical
Phosphorus