We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Enhancing water quality prediction: a machine learning approach across diverse water environments
Summary
Researchers compared seven machine learning models for predicting water quality parameters using six years of wastewater treatment plant data. The gradient boosting model performed best overall, accurately predicting parameters related to water contamination. While the study focuses on general water quality rather than microplastics specifically, these predictive tools could be applied to monitoring microplastic-relevant conditions in treatment systems.
ABSTRACT Rapid urbanization and industrialization have significantly contributed to the pollution and degradation of water bodies through urban runoff, industrial discharge, and inadequate wastewater treatment infrastructure. This study explores the role of machine learning (ML) as a decision-support tool for addressing water quality challenges across diverse environments, including surface water, groundwater, seawater, and wastewater. We evaluated the performance of seven ML models for predicting water quality parameters using data from six years (2014–2019) of the Melbourne Eastern wastewater treatment plant, encompassing energy consumption, climate variables, and wastewater characteristics. Among the models tested, the gradient boosting model demonstrated the highest predictive accuracy, achieving a statistical measure coefficient of determination R2 score of 0.75. Key findings highlight the importance of integrating climate and water quality data to improve prediction accuracy and identify critical water parameters for enhancing future models. This review provides insights into the applicability of ML techniques in water quality management and identifies potential avenues for further research in predictive modeling.
Sign in to start a discussion.
More Papers Like This
Efficient Data-Driven Machine Learning Models for Water Quality Prediction
This study tested machine learning methods for predicting water quality based on physical, chemical, and biological measurements. While focused on water safety testing rather than microplastics specifically, the automated classification tools developed here could help water treatment facilities quickly identify contaminated water. Better monitoring technology is important because current methods for detecting microplastics in water are slow and expensive.
A Comprehensive Review of Machine Learning for Water Quality Prediction over the Past Five Years
This comprehensive review analyzes over 170 studies on using machine learning to predict water quality, covering both individual pollutant indicators and overall water quality indices. The authors highlight key challenges including data acquisition, model uncertainty, and the need to incorporate water flow dynamics into predictions. While broadly focused on water quality, these predictive tools are relevant to microplastics research because they could help forecast microplastic concentrations in water systems based on environmental conditions.
Machine learning modeling of microplastics removal by coagulation in water and wastewater treatment
Researchers developed machine learning models to predict how effectively coagulation, a common water treatment process, can remove microplastics under different conditions. The best model achieved 96% accuracy and found that water temperature had the biggest negative effect on removal, while adding coagulant aids had the most positive effect. These tools could help water treatment plants optimize their processes to better remove microplastics from drinking water.
Machine Learning to Access and Ensure Safe Drinking Water Supply: A Systematic Review
This systematic review examines machine learning applications for monitoring, predicting, and controlling drinking water quality, covering contaminants from disinfection byproducts to biofilms and antimicrobial resistance genes. While not specifically about microplastics, the ML approaches described are directly applicable to detecting and predicting microplastic contamination in engineered water systems.
Predicting aqueous sorption of organic pollutants on microplastics with machine learning
Researchers developed machine learning models to predict how organic pollutants bind to microplastics in water, using data from 475 published experiments. The models outperformed traditional approaches by accounting for properties of both the microplastics and the pollutants simultaneously. The study provides a more universal tool for understanding how microplastics can transport and concentrate harmful chemicals in freshwater systems.