Title: Artificial Neural Network and Differential Evolution methodologies used in single- and multi-objective formulations for the solution of subsurface water management problems
Authors: Ioannis K. Nikolos, Maria P. Papadopoulou, George P. Karatzas
Addresses: Department of Production Engineering and Management, Technical University of Crete, University Campus, Kounoupidiana, 73100, Chania, Greece. ' School of Rural and Surveying Engineering, National Technical University of Athens, University Campus, 9 Iroon Polytechneiou, Zografou 15780, Greece. ' Department of Environmental Engineering, Technical University of Crete, University Campus, Kounoupidiana 73100, Chania, Greece
Abstract: A single-objective Differential Evolution (DE) algorithm is combined with an Artificial Neural Network (ANN) to examine different operational strategies to cover the water demand in the Northern part of Rhodes Island, Greece. Successive calls to the simulator are used to provide the training data to the ANN, which is used as an approximation model to the simulator. Additionally, a multi-objective DE algorithm is combined with the pre-trained ANN to solve the same problem; the environmental constraints are realised through the definition of a second objective function, whereas the first objective function is the total pumping of the supply wells.
Keywords: multi-objective optimisation; subsurface water management; ANNs; artificial neural networks; differential evolution; groundwater management; simulation.
International Journal of Advanced Intelligence Paradigms, 2010 Vol.2 No.4, pp.365 - 377
Published online: 02 Nov 2010 *Full-text access for editors Access for subscribers Purchase this article Comment on this article