Predictive Modeling Of Water Quality Index Using Machine Learning Technique

Abstract

Water quality is a crucial factor in the sustainability of aquatic ecosystems and the health of human populations. The Water Quality Index (WQI) provides an aggregate measure that combines several water quality parameters into a single value, enabling the assessment of water quality for consumption, agriculture, and industrial use. Traditional methods of calculating WQI often rely on manual sampling and analysis, which can be time-consuming and labor-intensive. This study aims to leverage machine learning (ML) algorithms to predict the WQI in a specific study area Bhopal district of Madhya Pradesh, India. These regions have the highest population density of Bhopal city along with villages around Bhopal city using a dataset of water quality parameters. By utilizing Python, this research employs various ML models such as Linear Regression, Random Forest, and Support Vector Machines (SVM) to predict the WQI based on input features like pH, temperature, dissolved oxygen, turbidity, and other relevant water quality parameters. The results show that ML-based prediction models can offer accurate, efficient, and timely insights for water quality management, contributing to proactive water resource management and public health safety.