Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia.docVIP

下载本文档

9
0
约5.95万字
约 44页
2017-05-08 发布于上海
举报
版权申诉

Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia.doc

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

Dynamic versus static neural network model for rainfall forecasting at Klang River Basin, Malaysia

Hydrol.EarthSyst.Sci.Discuss.,8,6489–6532,2011 /8/6489/2011/ doi:10.5194/hessd-8-6489-2011 Hydrology and Earth System Sciences HESSD 8,6489–6532,2011 Discussions ?Author(s)2011.CCAttribution3.0License. Dynamicversus staticneuralnetwork modelforrainfall Thisdiscussionpaperis/hasbeenunderreviewforthejournalHydrologyandEarth SystemSciences(HESS).Pleaserefertothecorresponding?nalpaperinHESS ifavailable. forecasting,Malaysia A.El-Sha?eetal. Dynamicversusstaticneuralnetwork modelforrainfallforecastingatKlang RiverBasin,Malaysia TitlePage Abstract Conclusions Tables Introduction References Figures A.El-Sha?e ,A.Noureldin ,M.R.Taha ,andA.Hussain3 1 2 1 1CivilandStructuralEngineeringDepartment,UniversityKebangsaanMalaysia, Kebangsaan,Malaysia 2AssociateProfessor,ElectricalandComputerEngineering,RoyalMilitaryCollege, Kingston,Canada J J I I 3Electric,ElectronicsSystemsEngineeringDepartment,UniversityKebangsaanMalaysia, Kebangsaan,Malaysia Back Close FullScreen/Esc Received:3June2011–Accepted:28June2011–Published:6July2011 Correspondenceto:A.El-Sha?e(elsha?e@vlsi.eng.ukm.my) Printer-friendlyVersion InteractiveDiscussion PublishedbyCopernicusPublicationsonbehalfoftheEuropeanGeosciencesUnion. 6489 Abstract HESSD Rainfall is considered as one of the major component of the hydrological process, it takes signi?cant part of evaluating drought and ?ooding events. Therefore, it is im- portant tohaveaccuratemodelforrainfallforecasting. Recently, severaldata-driven modeling approaches have been investigated to perform such forecasting task such asMulti-LayerPerceptronNeuralNetworks(MLP-NN).Infact,therainfalltimeseries modelinginvolvesanimportanttemporaldimension. Ontheotherhand,theclassical MLP-NNisastaticandmemorylessnetworkarchitecturethatise?ectiveforcomplex nonlinearstaticmapping. Thisresearchfocusesoninvestigatingthepotentialofintro- 8,6489–6532,2011 Dynamicversus staticneuralnetwork modelforrainfall 5 forecasting,Malaysia 10 ducing a neural network that could address