Artificial Intelligence based Models to Support Water Quality Prediction using Machine Learning Approach

Abstract

The purpose of this study is to simulate the propagation of bio-contamination risk in Water Distribution System (WDS). This will be accomplished by putting an emphasis on source identification and response modelling. This will be accomplished in the WDS via the process of simulating the bio-contamination risk propagation under real environmental circumstances. This will be done in order to accomplish this goal. Due to the failure to take into consideration the ability for the bulk of the pollutants to undergo chemical degradation and the neglecting of dynamic responses, an overestimation of the population that is exposed has resulted. The study presented here takes into account the connected change in a variety of water quality indicators that are caused by the mixing of the pollutants. These measurements include the total organic carbon content, pH, and alkalinity. In practise, the baseline requirements for each of the aforementioned metrics are set at the beginning of the regular WDS monitoring. Contamination is then indicated by considerable deviations from the base line. The study's goal was to determine whether it is feasible to develop a smart monitoring system powered by artificial intelligence (AI) that would successfully enable water operators to ensure near real-time quality control for the early detection of chemical and/or biological pollution and risk management. The study's goal was to see whether it was possible to develop an artificial intelligence (AI)-based smart monitoring system. The study's purpose was to investigate the viability of building a sophisticated monitoring system that would allow water operators to perform quality control in near real time. Artificial Neural Networks (ANN) and other sophisticated pattern recognizers like Support Vector Machines (SVMs) are examples of cutting-edge sensor technologies that have been implemented as solutions to identify anomalies and estimate the severity of such irregularities.