The Quality of Drinkable Water using Machine Learning Techniques

Predicting potable water quality is more effective for management and pollution prevention. Polluted causes serious waterborne illnesses poses a threat to human health. the of drinkable may reduce incidence water-related diseases. The latest machine learning approach has shown promising predictive accuracy quality. This research uses five different algorithms determine drinking First, data gathered from public sources presented in accordance with World Health Organization (WHO) standards. Several parameters, including hardness, conductivity, pH, organic carbon, solids, others, are essential predicting Second, Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), Deep (DNN), Gaussian Nave Bayes used estimate water. conventional laboratory technique assessing time-consuming sometimes costly. proposed this work can predict within short period time. ANN 99 percent height training error 0.75 during period. RF an F1 score 87.86% prediction 82.45%. An (ANN) predicted 96.51 study. Using extended set could improve how well predictions made help stop diseases long run.