File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: A modified neural network for improving river flow prediction

TitleA modified neural network for improving river flow prediction
Authors
KeywordsBackpropagation
Generalization performance
Goal programming
Network sensitivity
Neural network
Objective function
Prior knowledge
Rainfall-runoff transformation
River flow prediction
The South-to-North scheme
Issue Date2005
PublisherTaylor & Francis, co-published with IAHS. The Journal's web site is located at http://www.tandfonline.com/toc/thsj20/current
Citation
Hydrological Sciences Journal, 2005, v. 50 n. 2, p. 299-317 How to Cite?
AbstractArtificial neural network (ANN) models provide huge potential for simulating nonlinear behaviour of hydrological systems. However, the potential of ANN is yet to be fully exploited due to the problems associated with improving the model generalization performance. Generalization refers to the ability of a neural network to correctly process input data that have not been used for calibrating the neural network model. In the hydrological context, better generalization performance implies higher precision of forecasting. The primary objectives of this study are to explore new measures for improving the generalization performance of an ANN-based rainfall-runoff model, and to evaluate the applicability of the new measures. A modified neural network model (entitled goal programming (GP) neural network) for modelling the rainfall-runoff process has been developed, in which three enhancements are made as compared to the widely-used backpropagation (BP) network. The three enhancements are (a) explicit integration of hydrological prior knowledge into the neural network learning; (b) incorporation of a modified training objective function; and (c) reduction of network sensitivity to input errors. Seven watersheds across a range of climatic conditions and watershed areas in China were selected for examining the alternative networks. The results demonstrate that the GP consistently outperformed the BP both in the calibration and verification periods and three proposed measures yielded improvement of performance. Copyright © 2005 IAHS Press.
Persistent Identifierhttp://hdl.handle.net/10722/71518
ISSN
2023 Impact Factor: 2.8
2023 SCImago Journal Rankings: 0.778
ISI Accession Number ID
References

 

DC FieldValueLanguage
dc.contributor.authorHu, TSen_HK
dc.contributor.authorLam, KCen_HK
dc.contributor.authorNg, STen_HK
dc.date.accessioned2010-09-06T06:32:43Z-
dc.date.available2010-09-06T06:32:43Z-
dc.date.issued2005en_HK
dc.identifier.citationHydrological Sciences Journal, 2005, v. 50 n. 2, p. 299-317en_HK
dc.identifier.issn0262-6667en_HK
dc.identifier.urihttp://hdl.handle.net/10722/71518-
dc.description.abstractArtificial neural network (ANN) models provide huge potential for simulating nonlinear behaviour of hydrological systems. However, the potential of ANN is yet to be fully exploited due to the problems associated with improving the model generalization performance. Generalization refers to the ability of a neural network to correctly process input data that have not been used for calibrating the neural network model. In the hydrological context, better generalization performance implies higher precision of forecasting. The primary objectives of this study are to explore new measures for improving the generalization performance of an ANN-based rainfall-runoff model, and to evaluate the applicability of the new measures. A modified neural network model (entitled goal programming (GP) neural network) for modelling the rainfall-runoff process has been developed, in which three enhancements are made as compared to the widely-used backpropagation (BP) network. The three enhancements are (a) explicit integration of hydrological prior knowledge into the neural network learning; (b) incorporation of a modified training objective function; and (c) reduction of network sensitivity to input errors. Seven watersheds across a range of climatic conditions and watershed areas in China were selected for examining the alternative networks. The results demonstrate that the GP consistently outperformed the BP both in the calibration and verification periods and three proposed measures yielded improvement of performance. Copyright © 2005 IAHS Press.en_HK
dc.languageengen_HK
dc.publisherTaylor & Francis, co-published with IAHS. The Journal's web site is located at http://www.tandfonline.com/toc/thsj20/currenten_HK
dc.relation.ispartofHydrological Sciences Journalen_HK
dc.subjectBackpropagationen_HK
dc.subjectGeneralization performanceen_HK
dc.subjectGoal programmingen_HK
dc.subjectNetwork sensitivityen_HK
dc.subjectNeural networken_HK
dc.subjectObjective functionen_HK
dc.subjectPrior knowledgeen_HK
dc.subjectRainfall-runoff transformationen_HK
dc.subjectRiver flow predictionen_HK
dc.subjectThe South-to-North schemeen_HK
dc.titleA modified neural network for improving river flow predictionen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0262-6667&volume=50&issue=2&spage=299&epage=318&date=2005&atitle=A+modified+neural+network+for+improving+river+flow+predictionen_HK
dc.identifier.emailNg, ST:tstng@hkucc.hku.hken_HK
dc.identifier.authorityNg, ST=rp00158en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1623/hysj.50.2.299.60649en_HK
dc.identifier.scopuseid_2-s2.0-17444385970en_HK
dc.identifier.hkuros102513en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-17444385970&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume50en_HK
dc.identifier.issue2en_HK
dc.identifier.spage299en_HK
dc.identifier.epage317en_HK
dc.identifier.isiWOS:000228434400007-
dc.publisher.placeUnited Kingdomen_HK
dc.identifier.scopusauthoridHu, TS=35240334300en_HK
dc.identifier.scopusauthoridLam, KC=55106365500en_HK
dc.identifier.scopusauthoridNg, ST=7403358853en_HK
dc.identifier.issnl0262-6667-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats