<?xml version="1.0" encoding="utf-8" standalone="no"?>
<!DOCTYPE article SYSTEM "http://www.adv-geosci.net/inc/adgeo/copernicus.dtd">
<article language="en">
	<journal>
		<journal_title>Advances in Geosciences</journal_title>
		<journal_url>www.adv-geosci.net</journal_url>
		<issn>1680-7340</issn>
		<eissn>1680-7359</eissn>
		<volume_number>9</volume_number>
		<volume_title>Integration of hydrological models on different spatial and temporal scales</volume_title>
		<publication_year>2006</publication_year>
	</journal>
	<doi>10.5194/adgeo-9-131-2006</doi>
	<article_url>http://www.adv-geosci.net/9/131/2006/</article_url>
	<abstract_html>http://www.adv-geosci.net/9/131/2006/adgeo-9-131-2006.html</abstract_html>
	<fulltext_pdf>http://www.adv-geosci.net/9/131/2006/adgeo-9-131-2006.pdf</fulltext_pdf>
	<start_page>131</start_page>
	<end_page>136</end_page>
	<publication_date>2006-09-26</publication_date>
	<article_title content_type="html">Flood routing modelling with Artificial Neural Networks</article_title>
	<authors>
		<author numeration="1" affiliations="1">
			<name>R. Peters</name>
			<email>ronny.peters@tu-dresden.de</email>
		</author>
		<author numeration="2" affiliations="1">
			<name>G. Schmitz</name>
		</author>
		<author numeration="3" affiliations="1">
			<name>J. Cullmann</name>
		</author>
	</authors>
	<affiliations>
		<affiliation numeration="1" content_type="html">Institute of Hydrology and Meteorology, University of Technology, Dresden, Germany</affiliation>
	</affiliations>
	<abstract content_type="html">For the modelling of the flood routing in the lower reaches of the
Freiberger Mulde river and its tributaries the one-dimensional hydrodynamic
modelling system HEC-RAS has been applied. Furthermore, this model was used
to generate a database to train multilayer feedforward networks.

&lt;P&gt;

To guarantee numerical stability for the hydrodynamic modelling of some 60 km
of streamcourse an adequate resolution in space requires very
small calculation time steps, which are some two orders of magnitude smaller
than the input data resolution. This leads to quite high computation
requirements seriously restricting the application &amp;ndash; especially when dealing
with real time operations such as online flood forecasting.

&lt;P&gt;

In order to solve this problem we tested the application of Artificial
Neural Networks (ANN). First studies show the ability of adequately trained
multilayer feedforward networks (MLFN) to reproduce the model performance.</abstract>
	<references>
		<reference numeration="1" content_type="text"> Hagan, M. T., Demuth, H. B., and Beale, M.: Neural Network Design, PWS Publishing Company, Boston, 1996. </reference>
		<reference numeration="2" content_type="text"> Hornik, K. M., Stinchcombe, M., and White, H.: Multilayer feedforward networks are universal approximators, Neural Networks, 2, 5, 359&amp;ndash;366, 1989. </reference>
		<reference numeration="3" content_type="text"> Minns, A. W. and Hall, M. J.: Artificial neural networks as rainfall-runoff models, Hydrol. Sci., 41, 399&amp;ndash;417, 1996. </reference>
		<reference numeration="4" content_type="text"> Shrestha, R. R., Theobald, S., and Nestmann, F.: Simulation of flood flow in a river system using artificial neural networks, Hydrol. Earth Syst. Sci., 9(4), 313&amp;ndash;321, 2005. </reference>
		<reference numeration="5" content_type="text"> USACE1: US-Army Corps of Engineers, HEC-River Analysis System. Hydraulic Reference Manual, Version 3.1, http://www.hec.usace.army.mil/software/hec-ras/, 2002. </reference>
		<reference numeration="6" content_type="text"> USACE2: US-Army Corps of Engineers. HEC-GeoRAS, An extension for support of HEC-RAS using ArcView, http://www.hec.usace.army.mil/software/hec-ras/, 2002. </reference>
	</references>
</article>

