Water Quality Prediction using Machine Learning: A Comparative Study
M Anita, M. Dinesh, C Lakshmipriya, V. Ceronmani Sharmila, A. Muthuram, R. Sıva Subramanıan
Abstract
The discharge of chemicals into water sources may lead to water pollution, which in turn presents serious threats to the health of humans in addition to the natural environment. It is generally acknowledged to be one of the most debilitating difficulties that mankind has ever faced, and it has resulted in the annihilation of crops, animals, forests, and other essential elements of ecosystems. As a consequence of this, it is very necessary to explore efficient methods of machine learning in order to properly estimate water quality. In this investigation, one of the goals is to suggest a machine learning-based technique for forecasting the Water Quality Index (WQI) that makes use of supervised classification algorithms and aims to achieve a high level of accuracy. This will determine which of the several machine learning approaches produces the best reliable prediction model by comparing the results of these approaches. This study intends to assess and contrast the performance of various machine learning approaches by making use of the dataset that has been supplied, with the end goal of improving one's ability to forecast water quality.