ABSTRACT
The problem addressed in this study is to predict development potential of a groundwater aquifer with uncertain aquifer parameters subjected to quality constraint. The quality constraint is imposed because of the presence of contamination sources near the aquifer. Dealing with this problem in the presence subsurface uncertainty using the traditional methods of groundwater simulation and optimization models needs millions of CPU hours. In this paper it is proposed to capitalize the capabilities of new computational techniques including Artificial Neural Networks (ANN), and Genetic Algorithms (GA) for creating a comprehensive analytical package that can be used to manage and evaluate groundwater resources near potential contamination sources. To test the developed package, it is applied to a case study of El-Sadat City groundwater aquifer system in Egypt. The combined tools are found to be very efficient in evaluating millions of development scenarios that would not otherwise have been evaluated with traditional techniques. The main conclusion is that ANN and GA are robust techniques that can lead to improved management plans because the end result is a tool that enhances the ability of water resources managers to maximize the benefits from groundwater aquifers while minimizing adverse impacts on the environment through minimizing the spread of potential contamination.
