Application of artificial neural networks for the prediction of Gaza wastewater treatment plant performance-Gaza strip

This paper is concerned with the use of artificial neural network and multiple linear regression (MLR) models for the prediction of three major water quality parameters in the Gaza wastewater treatment plant. The data sets used in this study consist of nine years and collected from Gaza wastewater treatment plant during monthly records. Treatment efficiency of the plant was determined by taking into account of influent input values of pH, temperature (T), biological oxygen demand (BOD), chemical oxygen demand (COD) and total dissolved solids (TSS) with effluent output values of BOD, COD and TSS. Performance of the model was compared via the parameters of root mean squared error (RMSE), mean absolute percentage error (MAPE) and correlation coefficient (r). The suitable architecture of the neural network model is determined after several trial and error steps. Results showed that the artificial neural network (ANN) performance model was better than the MLR model. It was found that the ANN model could be employed successfully in estimating the BOD, COD and TSS in the outlet of Gaza wastewater treatment plant. Moreover, sensitive examination results showed that influent TSS and T parameters have more effect on BOD, COD and TSS predicting to other parameters.