Machine Learning Based Contamination Detection in Water Distribution System

Abstract

Water is a necessary component of all human activities. According to the United Nations World Water Assessment Program, every day, 2  million tons of sewage, manufacturing, and agricultural waste are discharged into the world's water. Due to population demands and  dwindling clean water supplies as well as available water pollution management mechanisms; there is an urgent need to use  computational methods to intelligently manage available water. This paper proposes artificial neural networks, specifically, Convolutional  Neural Networks (CNNs), for automated water impurity detection. To refine the model, the picture of turbid water in the  pipe was used to detect events. The algorithm of deep learning achieved 96.3 %t accuracy after extensive training with a dataset of 4220  images reflecting various levels of contamination. This shows that, the model can be used in water system pollution detection.