Predictive Analysis of River Water Quality Using Machine Learning Techniques

Access to clean drinking water is essential for human health, yet contamination from pathogens and toxic substances remains a global concern.This study proposes a predictive system for monitoring water quality and alerting users before contamination occurs.By leveraging machine learning and web technologies, the system utilizes critical parameters such as pH, turbidity, dissolved oxygen (DO), and conductivity to assess water quality.Data for this analysis was sourced from Kaggle, and multiple machine learning algorithms, including Gradient Boosting, Naive Bayes, Random Forest, Decision Tree, and deep learning models, were applied to predict water contamination levels.The model effectively forecasts water quality deterioration, allowing timely intervention.Results are visualized through a web-based interface, enabling users to monitor water conditions in real time.While initially designed for residential water tanks connected to natural sources like rivers, the proposed framework is scalable and can be implemented in water treatment plants and industrial applications.Experimental results indicate that the water quality index (WQI) often falls into a moderate range, suggesting progressive degradation due to pollutants.The study emphasizes the importance of assessing environmental factors and water quality indicators to prevent potential health risks.The proposed method demonstrates reliable predictive accuracy using a minimal set of parameters, highlighting its potential for real-time water quality monitoring systems.