A Contemporary Method of Assessing Water Quality based on the Fusion of Predictive Analytics and Deep Structured Learning

The human activities that cause untreated wastewater, sewage water, and rubbish to contaminate water bodies pose a danger to natural water supplies. Monitoring water quality is essential for protecting water resources and ensuring that only clean water is available for consumption. This study assesses the performance of several machine learning methods, including deep learning models, support vector machines, Naive Bayes, K-Nearest Neighbours, Decision Trees, Random Forests, and Logistic Regression. The findings show that Random Forests performed better than other machine learning methods, with an accuracy of 79.6093%. With an accuracy of 70.9402%, deep learning models also demonstrated encouraging results.