A Comparative Study Of Ann For Predicting Nitrate Concentration In Groundwater Wells In The Southern Area Of Gaza Strip

The main source of water in the Gaza Strip is the shallow aquifer which is part of the coastal aquifer. The quality of the groundwater is extremely deteriorated in terms of nitrates and salinity. The Gaza Strip is mostly in catastrophic conditions that desire imperative and great efforts to improve the water situation on conditions of both quality and quantity. In this study, performance of two artificial networks was evaluated to determine which one would have more efficiency in predicting nitrate concentrations of groundwater wells used for desalination purpose in the southern area of Gaza Strip. Multiple layer perceptron (MLP) and radial basis function (RBF) neural networks are trained and developed with reference to seven important variables including pH, EC, TDS, hardness, calcium, magnesium, and abstraction rate. These variables are considered as inputs of the network. The data sets used in this study consist of six months and collected from 15 groundwater wells in Khan Younis and Rafah area. The network performance has been tested with different data sets and the results showed satisfactory performance. The prediction results of the MLP neural network were found to be better than RBF. Prediction results prove that neural network approach has good and wide applicability for modeling nitrate in the groundwater wells of Gaza Strip coastal aquifer. We hope that the established model will help in assisting the local authorities in developing plans and policies to improve the water quality in the Gaza Strip to acceptable levels.