Estimation of Cadmium and Uranium in a stream sediment from Eshtehard region in Iran using an Artificial Neural Network

Abstract

Considering the importance of Cd and U as pollutants of the environment, this study aims to predict the concentrations of these elements in a stream sediment from the Eshtehard region in Iran by means of a developed artificial neural network (ANN) model. The forward selection (FS) method is used to select the input variables and develop hybrid models by ANN. From 45 input candidates, 13 and 14 variables are selected using the FS method for Cadmium and Uranium, respectively. Considering the correlation coefficient (R²) values, both the ANN and FS-ANN models are acceptable for estimation of the Cd and U concentrations. However, the FS-ANN model is superior because the R² values for estimation of Cd and U by the FS-AAN model is higher than those for estimation of these elements by the ANN model. It is also shown that the FS-ANN model is preferred in estimating the Cd and U population due to reduction in the calculation time as a consequence of having less input variables.