pH Prediction by Artificial Neural Networks for the Drinking Water of the Distribution System of Hyderabad City

TL;DR

This study develops and validates an artificial neural network model to accurately predict pH levels at multiple locations in Hyderabad's drinking water distribution system, aiding water quality management.

Contribution

The paper introduces a novel ANN-based model for pH prediction across different water treatment phases in Hyderabad, demonstrating high accuracy and extrapolative capability.

Findings

High correlation coefficient (R2=0.999) between predicted and actual pH values.

Mean Square Error (MSE) below 5% indicates precise predictions.

Model effectively predicts pH across raw, treated, and distributed water.

Abstract

In this research, feedforward ANN (Artificial Neural Network) model is developed and validated for predicting the pH at 10 different locations of the distribution system of drinking water of Hyderabad city. The developed model is MLP (Multilayer Perceptron) with back propagation algorithm.The data for the training and testing of the model are collected through an experimental analysis on weekly basis in a routine examination for maintaining the quality of drinking water in the city. 17 parameters are taken into consideration including pH. These all parameters are taken as input variables for the model and then pH is predicted for 03 phases;raw water of river Indus,treated water in the treatment plants and then treated water in the distribution system of drinking water. The training and testing results of this model reveal that MLP neural networks are exceedingly extrapolative for predicting the pH of river water, untreated and treated water at all locations of the distribution system of drinking water of Hyderabad city. The optimum input and output weights are generated with minimum MSE (Mean Square Error) < 5%.Experimental, predicted and tested values of pH are plotted and the effectiveness of the model is determined by calculating the coefficient of correlation (R2=0.999) of trained and tested results.