Prediction of mine water quality by physical parameters

Abstract

Present paper is an attempt to predict the chemical parameters like sulphate, chlorine, chemical oxygen demand, total dissolved solids and total suspended solids in mine water using artificial neural network (ANN) by incorporating the pH, temperature and hardness. The prediction by ANN is also compared with Multivariate Regression Analysis (MVRA). For prediction of chemical parameters of mine water, 30 data set were taken for the training of the network while testing and validation of network was done by 10 data set with 923 epochs. The predicted results of chemical parameters of mine water by ANN are very satisfactory and acceptable as compared to MVRA, and seem to be a good alternative for pollutants prediction.<b style=""></b>