Prediction of river salinity with artificial neural networks

Abstract

Abstract This paper presents the development and evaluation of an Artificial Neural Network (ANN) based on the model for predicting the salinity of the Warta River. The study focused on the prediction of river water salinity, expressed in terms of electrical conductivity (EC), using the proposed ANN structure of 7-10-1. The network showed a satisfactory ability to capture the interrelationships between the input data: sulphates, chlorides, calcium, magnesium, total hardness, pH, and total dissolved solids. The correlation coefficient (R) values for the training, validation and test sets were 0.99444, 0.96988 and 0.97174, respectively. From the results, it can be concluded that the developed model is suitable for predicting the EC of the river.