Constraints of artificial neural networks for rainfall-runoff modelling trade-offs in hydrological state representation and model evaluation.docVIP

下载本文档

3
0
约6.91万字
约 16页
2017-05-08 发布于上海
举报
版权申诉

Constraints of artificial neural networks for rainfall-runoff modelling trade-offs in hydrological state representation and model evaluation.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

Constraints of artificial neural networks for rainfall-runoff modelling trade-offs in hydrological state representation and model evaluation

Hydrology and Earth System Sciences, 9, 111–126, 2005 /EGU/hess/hess/9/111/ SRef-ID: 1607-7938/hess/2005-9-111 Hydrologyand EarthSystem Sciences European Geosciences Union Constraints of arti?cial neural networks for rainfall-runoff modelling: trade-offs in hydrological state representation and model evaluation N. J. de Vos1 and T. H. M. Rientjes1,2 1Water Resources Section, Delft University of Technology, Delft, The Netherlands 2Department of Water Resources, International Institute for Geo-Information Science and Earth Observation (ITC), Enschede, The Netherlands Received: 4 February 2005 – Published in Hydrology and Earth System Sciences Discussions: 23 February 2005 Revised: 2 June 2005 – Accepted: 12 June 2005 – Published: 5 July 2005 Abstract. The application of Arti?cial Neural Networks (ANNs) in rainfall-runoff modelling needs to be researched more extensively in order to appreciate and ful?l the poten- tial of this modelling approach. This paper reports on the application of multi-layer feedforward ANNs for rainfall- runoff modelling of the Geer catchment (Belgium) using both daily and hourly data. The daily forecast results indi- cate that ANNs can be considered good alternatives for tra- ditional rainfall-runoff modelling approaches, but the simu- lations based on hourly data reveal timing errors as a result of a dominating autoregressive component. This component is introduced in model simulations by using previously ob- served runoff values as ANN model input, which is a popular method for indirectly representing the hydrological state of a catchment. Two possible solutions to this problem of lagged predictions are presented. Firstly, several alternatives for rep- resentation of the hydrological state are tested as ANN in- puts: moving averages over time of observed discharges and rainfall, and the output of the simple GR4J model component for soil moisture. A combination of these hydrological state representers produces good resu