Research Bank

Investigation of the internal functioning of the radial basis function neural network river flow forecasting models

Unitec Research Bank

Show simple item record

dc.contributor.author Fernando, Achela
dc.contributor.author Shamseldin, Asaad
dc.date.accessioned 2012-05-27T21:22:22Z
dc.date.available 2012-05-27T21:22:22Z
dc.date.issued 2009-03
dc.identifier.issn 1084-0699
dc.identifier.uri http://hdl.handle.net/10652/1883
dc.description.abstract This paper deals with the challenging problem of hydrological interpretation of the internal functioning of ANNs by extracting knowledge from their solutions. The neural network used in this study is based on the structure of the Radial Basis Function Neural Network (RBFNN) which is considered as an alternative to the Multi Layer Perceptron (MLPNN) for solving complex modelling problems. This network consists of an input, hidden and an output layer. The network is trained using the daily data of two catchments having different characteristics and from two different regions in the world. The present day and antecedent observed discharges are used as inputs to the network to forecast the flow one day ahead. A range of quantitative and qualitative techniques are used for hydrological interpretation of the internal functioning by examining the responses of the hidden layer neurons. The results of the study show that a single hidden layered RBFNN is an effective tool to forecast the daily flows and that the activation of the hidden layer nodes are far from arbitrary but appear to represent flow components of the predicted hydrograph. The results of the study confirm that the three neurons in the hidden layer of this model effectively divide the input data space in such a way that the contribution from each neurone dominates in one of the flow domains – low, medium or high – and form, in a crude manner, the base flow, interflow and surface runoff components of the hydrograph. en_NZ
dc.language.iso en en_NZ
dc.publisher American Society of Civil Engineers en_NZ
dc.relation.uri http://cedb.asce.org/cgi/WWWdisplay.cgi?169672 en_NZ
dc.subject Hydrological interpretation en_NZ
dc.subject Hidden neurons en_NZ
dc.subject Radial basis function en_NZ
dc.subject Artificial neural networks en_NZ
dc.title Investigation of the internal functioning of the radial basis function neural network river flow forecasting models en_NZ
dc.type Journal Article en_NZ
dc.rights.holder American Society of Civil Engineers en_NZ
dc.identifier.doi 10.1061/(ASCE)1084-0699(2009)14:3(286) en_NZ
dc.subject.marsden 091501 Computational Fluid Dynamics en_NZ
dc.identifier.bibliographicCitation Fernando, D.A.K., & Shamseldin, A.Y. (2009). Investigation of the internal functioning of the radial basis function neural network river flow forecasting models. Journal of Hydrologic Engineering, 14(3), 286-292. doi: 10.1061/(ASCE)1084-0699(2009)14:3(286) en_NZ
unitec.institution Unitec Institute of Technology en_NZ
unitec.institution University of Auckland en_NZ
unitec.publication.spage 286 en_NZ
unitec.publication.lpage 292 en_NZ
unitec.publication.volume 14 en_NZ
unitec.publication.title Journal of Hydrologic Engineering en_NZ
unitec.peerreviewed yes en_NZ
unitec.identifier.roms 45186


This item appears in

Show simple item record

Search


Browse Research Bank

My Account

Help

Share

  • Bookmark and Share

Usage Statistics