Groundwater quality assessment using artificial neural network: A case study of Bahabad plain, Yazd, Iran

Groundwater quality management is the most important issue in many arid and semi-arid countries, including Iran. Artificial neural network (ANN) has an extensive range of applications in water resources management. In this study, artificial neural network was developed using MATLAB R2013 software package, and Cl, EC, SO4 and NO3 qualitative parameters were estimated and compared with the measured values, in order to evaluate the influence of key input parameters. The number of neurons in the hidden layer was obtained by the trial-and-error method. For this purpose, data from 260 water samples of 13 wells in Bahabad plain were collected during 2003- 2013. The results show that the performance of ANN model was more accurate for Cl (R=0.96), EC(R=0.98), and SO4(R=0.95), using back-propagation algorithms according to the best chosen input parameters. It was observed that the use of ANN model for NO3 was not very accurate, perhaps this was because of the different water sources or the impact of other parameters; thus, this result is in contrast with the study of Diamantopoulou et al. (2005). However, this study confirms that the number of neurons in the hidden layer cannot be found using a specific formula (double the number of inputs plus one) for all parameters but can be obtained using a trial-and-error method.