Groundwater Numerical Modeling and Environmental Design Using Artificial Neural Networks and Differential Evolution

  • Authors:

  • Ioannis K. Nikolos;Maria Stergiadi;Maria P. Papadopoulou;George P. Karatzas

  • Affiliations:

  • Department of Production Engineering and Management, Technical University of Crete, Chania, Greece 73100;Department of Environmental Engineering, Technical University of Crete, Chania, Greece 73100;Department of Environmental Engineering, Technical University of Crete, Chania, Greece 73100;Department of Environmental Engineering, Technical University of Crete, Chania, Greece 73100

  • Venue:
  • KES '08 Proceedings of the 12th international conference on Knowledge-Based Intelligent Information and Engineering Systems, Part II
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

A Differential Evolution (DE) algorithm is combined with an Artificial Neural Network (ANN) to examine different operational strategies for the productive pumping wells located in the Northern part of Rhodes Island in Greece. The objective is to maximize the pumping rate without violating the environmental constraints associated with the water table drawdown at critical locations. The hydraulic head field is simulated using a groundwater flow simulator that solves numerically a system of partial differential equations. Successive calls to the simulator are used to provide the training data to the ANN. Then the ANN is used as an approximation model to the simulator, successively called by the DE algorithm to evaluate candidate solutions. The adopted procedure provides the ability to test different scenarios, concerning the optimization constraints, without retraining of the ANN, which significantly reduces the computational cost of the procedure.