Machine learning-based prediction of effluent total suspended solids in a wastewater treatment plant using different feature selection approaches: A comparative study

Mahdi Gholizadeh; Reza Saeedi; Amin Bagheri; Mohammad Paeezi

doi:10.1016/j.envres.2024.118146

Machine learning-based prediction of effluent total suspended solids in a wastewater treatment plant using different feature selection approaches: A comparative study

Environ Res. 2024 Apr 1:246:118146. doi: 10.1016/j.envres.2024.118146. Epub 2024 Jan 11.

Authors

Mahdi Gholizadeh¹, Reza Saeedi², Amin Bagheri³, Mohammad Paeezi²

Affiliations

¹ Environmental and Occupational Hazards Control Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran; Department of Health, Safety and Environment, School of Public Health and Safety, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
² Department of Health, Safety and Environment, School of Public Health and Safety, Shahid Beheshti University of Medical Sciences, Tehran, Iran; Workplace Health Promotion Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
³ Environmental and Occupational Hazards Control Research Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran; Department of Health, Safety and Environment, School of Public Health and Safety, Shahid Beheshti University of Medical Sciences, Tehran, Iran. Electronic address: amin.bagheri@sbmu.ac.ir.

PMID: 38215928
DOI: 10.1016/j.envres.2024.118146

Abstract

Accurately predicting the characteristics of effluent, discharged from wastewater treatment plants (WWTPs) is crucial for reducing sampling requirements, labor, costs, and environmental pollution. Machine learning (ML) techniques can be effective in achieving this goal. To optimize ML-based models, various feature selection (FS) methods are employed. This study aims to investigate the impact of six FS methods (categorized as Wrapper, Filter, and Embedded methods) on the accuracy of three supervised ML algorithms in predicting total suspended solids (TSS) concentration in the effluent of a municipal wastewater treatment plant. Based on the features proposed by each FS method, five distinct scenarios were defined. Within each scenario, three ML algorithms, namely artificial neural network-multi layer perceptron (ANN-MLP), K-nearest neighbors (KNN), and adaptive boosting (AdaBoost) were applied. The features utilized for predicting TSS concentration in the WWTP effluent included BOD₅, COD, TSS, TN, NH₃ in the influent, and BOD₅, COD, residual Cl_2, NO₃, TN, NH₄ in the effluent. To construct the models, the dataset was randomly divided into training and testing subsets, and K-fold cross-validation was employed to control overfitting and underfitting. The evaluation metrics that are used are root mean squared error (RMSE), mean absolute error (MAE), and correlation coefficient (R²). The most efficient scenario was identified as Scenario IV, with the Sequential Backward Selection FS method. The features selected by this method were COD_e, BOD_5e, BOD_5i, TN_i. Furthermore, the ANN-MLP algorithm demonstrated the best performance, achieving the highest R² value. This algorithm exhibited acceptable performance in both the training and testing subsets (R² = 0.78 and R² = 0.8, respectively).

Keywords: ANN; AdaBoost; Feature selection; KNN; Machine learning; Total suspended solids.

MeSH terms

Algorithms
Machine Learning
Neural Networks, Computer
Waste Disposal, Fluid* / methods
Water Purification* / methods