A comparative study of three neural network forecast combination methods for simulated river flows of different rainfall-runoff models

DC FieldValueLanguage
dc.contributor.authorShamseldin, Asaad Y.-
dc.contributor.authorO'Connor, Kieran M.-
dc.contributor.authorNasr, Ahmed Elssidig-
dc.date.accessioned2010-08-23T16:00:39Z-
dc.date.available2010-08-23T16:00:39Z-
dc.date.copyright2007 IAHS Pressen
dc.date.issued2007-10-
dc.identifier.citationHydrological Sciences Journal-Journal Des Sciences Hydrologiquesen
dc.identifier.issn2150-3435 (electronic)-
dc.identifier.issn0262-6667 (paper)-
dc.identifier.urihttp://hdl.handle.net/10197/2421-
dc.description.abstractThe performance of three artificial neural network (NN) methods for combining simulated river flows, based on three different neural network structures, are compared. These network structures are; the simple neural network (SNN), the radial basis function neural network (RBFNN) and the multi-layer perceptron neural network (MLPNN). Daily data of eight catchments, located in different parts of the world, and having different hydrological and climatic conditions, are used to enable comparisons of the performances of these three methods. In the case of each catchment, each neural network combination method synchronously uses the simulated river flows of four rainfall-runoff models operating in design non-updating mode to produce the combined river flows. Two of these four models are black-box, the other two being conceptual models. The results of the study show that the performances of all three combination methods are, on average, better than that of the best individual rainfall-runoff model utilized in the combination, i.e. that the combination concept works. In terms of the Nash-Sutcliffe R2 model efficiency index, the MLPNN combination method generally performs better than the other two combination methods tested. For most of the catchments, the differences in the R2 values of the SNN and the RBFNN combination methods are not significant but, on average, the SNN form performs marginally better than the more complex RBFNN alternative. Based on the results obtained for the three NN combination methods, the use of the multi-layer perceptron neural network (MLPNN) is recommended as the appropriate NN form for use in the context of combining simulated river flows.en
dc.description.sponsorshipNot applicableen
dc.format.extent671015 bytes-
dc.format.mimetypeapplication/pdf-
dc.language.isoenen
dc.publisherTaylor & Francisen
dc.relation.requiresCritical Infrastructure Group Research Collectionen
dc.subjectNeural network combination methodsen
dc.subjectRainfall-runoff modelen
dc.subjectRiver flow forecastingen
dc.subjectMulti-layer perceptronen
dc.subjectRadial basis functionen
dc.subjectSimple neural networken
dc.subject.lcshNeural networks (Computer science)en
dc.subject.lcshRunoff--Computer programsen
dc.subject.lcshStreamflow--Forecastingen
dc.titleA comparative study of three neural network forecast combination methods for simulated river flows of different rainfall-runoff modelsen
dc.typeJournal Articleen
dc.internal.availabilityFull text availableen
dc.internal.webversionshttp://dx.doi.org/10.1623/hysj.52.5.896-
dc.statusPeer revieweden
dc.identifier.volume52en
dc.identifier.issue5en
dc.identifier.startpage896en
dc.identifier.endpage916en
dc.identifier.doi10.1623/hysj.52.5.896-
dc.neeo.contributorShamseldin|Asaad Y.|aut|-
dc.neeo.contributorO'Connor|Kieran M.|aut|-
dc.neeo.contributorNasr|Ahmed Elssidig|aut|-
dc.description.adminPublisher version - http://www.informaworld.com/smpp/content~db=all~content=a918669638~frm=titlelink DG 17/07/10 au, ti, ke, vo, is, pg OR 20/08/10en
item.fulltextWith Fulltext-
item.grantfulltextopen-
Appears in Collections:Critical Infrastructure Group Research Collection
Civil Engineering Research Collection
Files in This Item:
File Description SizeFormat 
21 corrected.pdf655.29 kBAdobe PDFDownload
Show simple item record

SCOPUSTM   
Citations 10

37
Last Week
0
Last month
checked on Sep 11, 2020

Page view(s) 50

1,356
Last Week
4
Last month
16
checked on Oct 24, 2020

Download(s) 5

1,978
checked on Oct 24, 2020

Google ScholarTM

Check

Altmetric


This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.