Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Computational benefits using artificial intelligent methodologies for the solution of an environmental design problem: saltwater intrusion.

Papadopoulou MP, Nikolos Ioannis, Karatzas Giorgos

Full record


URI: http://purl.tuc.gr/dl/dias/F94A8E13-059C-4A6C-9065-6F430B8C16B7
Year 2010
Type of Item Peer-Reviewed Journal Publication
License
Details
Bibliographic Citation M.P. Papadopoulou , I.K. Nikolos, and G.P. Karatzas, "Computational benefits using artificial intelligent methodologies for the solution of an environmental design problem: saltwater intrusion.,"Water Science and Technology, vol. 62, no. 7,pp. 1479-1490, 2010. doi: 10.2166/wst.2010.442. https://doi.org/10.2166/wst.2010.442.
Appears in Collections

Summary

Artificial Neural Networks (ANNs) comprise a powerful tool to approximate the complicated behavior and response of physical systems allowing considerable reduction in computation time during time-consuming optimization runs. In this work, a Radial Basis Function Artificial Neural Network (RBFN) is combined with a Differential Evolution (DE) algorithm to solve a water resources management problem, using an optimization procedure. The objective of the optimization scheme is to cover the daily water demand on the coastal aquifer east of the city of Heraklion, Crete, without reducing the subsurface water quality due to seawater intrusion. The RBFN is utilized as an on-line surrogate model to approximate the behavior of the aquifer and to replace some of the costly evaluations of an accurate numerical simulation model which solves the subsurface water flow differential equations. The RBFN is used as a local approximation model in such a way as to maintain the robustness of the DE algorithm. The results of this procedure are compared to the corresponding results obtained by using the Simplex method and by using the DE procedure without the surrogate model. As it is demonstrated, the use of the surrogate model accelerates the convergence of the DE optimization procedure and additionally provides a better solution at the same number of exact evaluations, compared to the original DE algorithm.

Services

Statistics