Water Quality Assessment Using Ensemble Technique

Compromised water quality poses risks to human health which necessitates the need for accurate water quality assessment. Our paper employs ensemble machine learning to accurately classify water samples. We present a comprehensive study focusing on the application of machine learning algorithms for the classification of water samples to determine their suitability for human consumption. The soft voting technique incorporates four algorithms, namely Naive Bayes, decision tree, random forest, and ANN. To assess water quality, we calculated WQI based on 12 parameters, classifying water samples into five distinct categories: excellent, good, moderate, poor, and very poor. The ensemble model achieved an accuracy of 92.22%.