Application of Artificial Neural Network to Predict TDS in Talkheh Rud River

Abstract

Salinity ranks high among the list of parameters which demand attention during the planning and management of water quality, particularly for drinking and irrigation. If water quality is adequately predicted, then the proper management is possible within the time. Looking into this importance, in the present study, an artificial neural network (ANN) model was developed to predict the total dissolved solids (TDS) as water quality indicator for the water quality management. Two ANN networks viz, multilayer perceptron (MLP) and recurrent neural network (RNN), which are further referred as the Elman network were developed and applied to the Talkheh Rud River. Comparing the results of the TDS at two monitoring stations, it was observed that the Elman network predicts the TDS very close to the observed values (R = 0.9639). Possession of 1 month’s worth of TDS data beforehand may be helpful for the water quality management decision-making process.