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

Search

Browse

My Space

A spatio-temporal hybrid neural network-Kriging model for groundwater level simulation

Tapoglou Evdokia, Karatzas Giorgos, Trichakis Ioannis, Varouchakis Emmanouil

Full record


URI: http://purl.tuc.gr/dl/dias/02A02B31-83B9-424C-A008-AAF4FB23E56A
Year 2014
Type of Item Peer-Reviewed Journal Publication
License
Details
Bibliographic Citation E. Tapoglou , G. P. Karatzas, I. C. Trichakis and E. A. Varouchakis,"A spatio-temporal hybrid neural network-Kriging model for groundwater level simulation," Journal of Hydrology, vol. 519, Part D, pp. 3193–3203, Nov. 2014. doi: 10.1016/j.jhydrol.2014.10.040 https://doi.org/10.1016/j.jhydrol.2014.10.040
Appears in Collections

Summary

Artificial Neural Networks (ANNs) and Kriging have both been used for hydraulic head simulation. In this study, the two methodologies were combined in order to simulate the spatial and temporal distribution of hydraulic head in a study area. In order to achieve that, a fuzzy logic inference system can also be used. Different ANN architectures and variogram models were tested, together with the use or not of a fuzzy logic system. The developed algorithm was implemented and applied for predicting, spatially and temporally, the hydraulic head in an area located in Bavaria, Germany. The performance of the algorithm was evaluated using leave one out cross validation and various performance indicators were derived. The best results were achieved by using ANNs with two hidden layers, with the use of the fuzzy logic system and by utilizing the power-law variogram. The results obtained from this procedure can be characterized as favorable, since the RMSE of the method is in the order of magnitude of 10−2 m. Therefore this method can be used successfully in aquifers where geological characteristics are obscure, but a variety of other, easily accessible data, such as meteorological data can be easily found.

Services

Statistics