Performance Analysis of Machine Learning Techniques for Predicting Water Quality Index using Physiochemical Parameters

Developing precise and trustworthy models for monitoring and managing water quality is crucial, as it is a key component of environmental management. Traditional water quality index (WQI) models often rely on simplistic statistical methods, leading to inaccurate predictions. This study addresses the limitations of traditional approaches by proposing a machine learning (ML)-based model for predicting WQI based on physicochemical parameters. The proposed model overcomes the challenge of capturing complex, non-linear relationships between physicochemical parameters and water quality. To assess its effectiveness, the proposed model is compared to four prior studies that used ML techniques for WQI prediction. Performance is evaluated using mean absolute error (MAE), root means squared error (RMSE), and coefficient of determination (R-squared) metrics. The results demonstrate that the proposed model outperforms the other studies in terms of both MAE and RMSE while also achieving a comparable or higher R-squared value. This study emphasizes the potential of ML techniques in improving WQI models and contributing to better decision-making regarding water quality management. By offering a more accurate and reliable prediction of WQI, the proposed model can facilitate more effective water quality management practices globally.