A Bayesian method to improve the extrapolation ability of ANNs

Simple item page
dc.contributor.authorHumphrey, G.
dc.contributor.authorMaier, H.
dc.contributor.authorLambert, M.
dc.contributor.conferenceInternational Conference on Applied Simulation and Modelling (14th : 2005 : Benalmadena, Spain)
dc.contributor.editorHamza, M.
dc.date.issued2005
dc.description.abstractAlthough artificial neural networks have been shown to be superior prediction models in many hydrology-related areas, their known lack of extrapolation capability has limited the wider use and acceptance of ANNs as forecasting models. This problem lies mainly with the fact that a single 'most likely' weight vector, which is determined by calibration with a finite set of data, is used to define the function modelled by the ANN. There are, in fact, many different weight vectors that result in approximately equal model performance; however, standard ANN development approaches do not allow for any weight vectors, other than that which provides the best fit to the calibration data, to impact on the predictions made. In this paper, a Bayesian method is presented that enables the entire range of plausible weight vectors to be accounted for in the model predictions. In doing so, the relationship modelled by the ANN is more general and less dominated by the information contained in the calibration data. The method is applied to a real-world case study known to require extrapolation and the resulting ANN is shown to perform significantly better than an ANN developed using standard approaches.
dc.description.statementofresponsibilityG.B. Kingston, H.R. Maier, and M.F. Lambert
dc.description.urihttp://www.actapress.com/Abstract.aspx?paperId=20853
dc.identifier.citationProceedings of the 14th IASTED International Conference on Applied Simulation and Modelling, June 15-17, 2005, Benalmadena, Spain / M.H. Hamza (ed.): pp.126-131
dc.identifier.isbn0889864675
dc.identifier.orcidHumphrey, G. [0000-0001-7782-5463]
dc.identifier.orcidMaier, H. [0000-0002-0277-6887]
dc.identifier.orcidLambert, M. [0000-0001-8272-6697]
dc.identifier.urihttp://hdl.handle.net/2440/29323
dc.language.isoen
dc.publisherACTA Press
dc.publisher.placeAnaheim, CA, USA
dc.rightsCopyright © 2005 ACTA Press
dc.subjectArtificial neural networks
dc.subjecthydrological forecasting
dc.subjectBayesian estimation
dc.subjectMarkov chain Monte Carlo
dc.titleA Bayesian method to improve the extrapolation ability of ANNs
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Civil and Environmental Engineering publications
Environment Institute publications