Forecasting and Optimizing Dual Media Filter Performance via Machine Learning. (15th May 2023)

• Record Type: Journal Article
• Authors: Moradi, Sina; Omar, Amr; Zhou, Zhuoyu; Agostino, Anthony; Gandomkar, Ziba; Bustamante, Heriberto; Power, Kaye; Henderson, Rita; Leslie, Greg
• Is Part Of: Water research. Volume 235(2023)
• Publication Date: 2023-05-15
• Subjects: Filtration performance -- Machine learning approach -- Hyper-parameter optimisation -- Unit filter run volume; Water -- Pollution -- Research -- Periodicals; 363.7394
• DOI: 10.1016/j.watres.2023.119874
• Languages: English
• ISSNs: 0043-1354

Abstract

Highlights: Machine learning is applied in water quality monitoring and prediction. Random search and grid search (GS) were used to optimise the hyperparameters. Random forest (RF) with GS and a 1-day lag time model was the most reliable. RF with GS has the shortest training time and prediction accuracy. Abstract: Four different machine learning algorithms, including Decision Tree (DT), Random Forest (RF), Multivariable Linear Regression (MLR), Support Vector Regressions (SVR), and Gaussian Process Regressions (GPR), were applied to predict the performance of a multi-media filter operating as a function of raw water quality and plant operating variables. The models were trained using data collected over a seven year period covering water quality and operating variables, including true colour, turbidity, plant flow, and chemical dose for chlorine, KMnO4, FeCl3, and Cationic Polymer (PolyDADMAC). The machine learning algorithms have shown that the best prediction is at a 1-day time lag between input variables and unit filter run volume (UFRV). Furthermore, the RF algorithm with grid search using the input metrics mentioned above with a 1-day time lag has provided the highest reliability in predicting UFRV with a RMSE and R 2 of 31.58 and 0.98, respectively. Similarly, RF with grid search has shown the shortest training time, prediction accuracy, and forecasting events using a ROC-AUC curve analysis (AUC over 0.8) in extreme wet weather events. Therefore, Random Forest with grid search and a 1-day time lag is an effective and robust machine learning algorithm that can predict the filter performance to aid water treatment operators in their decision makings by providing real-time warning of the potential turbidity breakthrough from the filters. Graphical abstract: Image, graphical abstract