Potable Water Quality Prediction: By Artificial Intelligence Techniques with Advanced Machine Learning Algorithm’s

Abstract

Abstract: Water is necessary for humans to survive, and everyone's health depends on maintaining the quality of the resource. Drinking polluted water can put one's health at risk, raising the chances of contracting diseases like cholera and other waterborne infections. By predicting the water's quality, ‘machine learning algorithms’ have developed into beneficial tools for quickly and reliably monitoring water supplies. Many forecasting techniques are the main subject of this study. This project aims to estimate water potability using various algorithms by forecasting the physicochemical characteristics of water samples taken from the Drinking Water dataset on Kaggle. To find the potability of drinking water, we use a variety of methods, including 'random forest', 'logistic regression', 'decision tree', 'SVM', 'AdaBoost', and 'KNN'. There is hence a strong chance that the investigation will yield precise data regarding the quality of the water