Water Quality Prediction using Neural Networks

Abstract

Water is necessary for all forms of life. The characteristics of water aid in regulating biotic diversity, vigor, and rate of succession. The deterioration of shared water resources, including lakes, streams, and estuaries, is one of the most serious and alarming problems currently confronting mankind. Each aspect of life is affected by the wide-ranging effects of dirty water. As a result, forecasting water quality has become essential in reducing water pollution. In this project, we have used the Long Short Term Memory(LSTM) algorithm in Neural Network andthe Decision tree and Naive Bayes classifiers will be used for classification for Water Quality Index (WQI). Here we will use Chemical Oxygen Demand (COD), Dissolved oxygen (DO), pH, temp parameters to determine the quality of water. This approach can be useful to accurately simulate the water quality. In order to achieve sustainable development, it is crucial to evaluate the fundamental aspects of the water environment. As a result, this model may potentially give simulated values for desirable places when measured data is unavailable but required for water quality models. Parameters with an impact on or an effect on water quality were estimated for this data.