Please use this identifier to cite or link to this item: http://ktisis.cut.ac.cy/handle/10488/9441
Title: Artificial neural networks for the generation of a conductivity map of the ground
Authors: Kalogirou, Soteris A. 
Florides, Georgios A. 
Pouloupatis, Panayiotis 
Christodoulides, Paul 
Joseph-Stylianou, Josephina 
Keywords: Artificial neural networks;Boreholes;Geothermal maps;Ground conductivity
Category: Computer and Information Sciences
Field: Natural Sciences
Issue Date: 1-May-2015
Publisher: Elsevier Ltd
Source: Renewable Energy, 2015, Volume 77, Pages 400-407
metadata.dc.doi: http://dx.doi.org/10.1016/j.renene.2014.12.033
Abstract: In this paper a neural network is used for the generation of a contour map of the ground conductivity in Cyprus. Archived data of thermal conductivity of ground recorded at 41 boreholes are used for training a multiple hidden layer neural network with feedforward architecture. The correlation coefficient obtained between the predicted and training data set is 0.9657, indicating an accurate mapping of the data. The validation of the network was performed using an unknown dataset. The correlation coefficient for the unknown cases was 0.9553. In order to broaden the database, the patterns used for the validation of the technique were embedded into the training data set and a new training of the network was performed. The correlation coefficient value for this case was equal to 0.9718. A 10×10km grid is then drawn over a detailed topographic map of Cyprus and the various input parameters were recorded for each grid point. This information was then supplied to the trained network and by doing so ground conductivity was predicted at each grid-point. This map will be a helpful tool for engineers in designing geothermal heat pump systems in Cyprus.
URI: http://ktisis.cut.ac.cy/handle/10488/9441
ISSN: 09601481
Rights: © 2014 Elsevier Ltd.
Type: Article
Appears in Collections:Άρθρα/Articles

Show full item record

Page view(s) 20

38
Last Week
4
Last month
3
checked on Nov 20, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.