Machine Learning Models for Predicting River Pollution from Industrial Discharge

Abstract

This research focuses on measuring river pollution due to industrial activities using machine learning (ML) models. The goal is to create and assess ML algorithms which, given specific environmental and industrial indicators, could reliably forecast the level of pollutants. The approach includes gathering information, feature selection, and model training with techniques including Artificial Neural Networks (ANN) and Random Forests (RF). Results clearly reveal that ML models attain a high level of accuracy which allows the sophisticated control of pollution and the development of early alert systems for pollution. It is shown that ML can significantly assist in the management of the environment and water resources, which is vital for industries and decision makers who strive for the reduction of environmental harm.