Deep Feature Learning for Detecting Water Pollution from Industrial Waste

Anthropogenic activities that affect most adversely water quality encompass urbanization, infrastructure development, and industrial operations. The presence of industrial waste in water bodies has led to a decline in the quality of freshwater, resulting in water pollution. Chemical parameters resulting from industrialization encompass the presence of lead, chromium, copper, aluminum, silver, barium, nitrites, radium, perchlorate, chloramine, arsenic, fluoride, etc. A comprehensive and in-depth study helps to establish correlations between the sources of water pollution due to industrialization and the class of water quality. It facilitates the implementation of appropriate procedures to detect the presence of water pollutants. The effectiveness of using Deep Neural Networks (DNNs) for the classification of water pollution lies in their ability to process complex relationships among the data available. We applied a multi-layer deep neural network to identify the water quality. We received an impressive result of our experiment by achieving 87% accuracy.