Title :
Neural network modelling of the 20-year flood event for catchments across the UK
Author :
Dawson, Christian W. ; Abrahart, Robert J. ; Shamseldin, Asaad Y. ; Wilby, Rob L. ; See, Linda M.
Author_Institution :
Dept. of Comput. Sci., Loughborough Univ., UK
fDate :
July 31 2005-Aug. 4 2005
Abstract :
Limited use has been made of artificial neural networks for regionalisation purposes or for flood event estimation in ungauged catchments. This paper uses data from the Centre for Ecology and Hydrology´s Flood Estimation Handbook to predict the 20-year flood event for 850 catchments across the UK. Neural network solutions and stepwise multiple linear regressions are compared. The neural network solutions provided superior flood event predictions and their use for subsequent hydrological modelling and flood engineering applications is recommended.
Keywords :
ecology; floods; neural nets; regression analysis; artificial neural networks; flood engineering; flood event estimation; hydrological modelling; Artificial neural networks; Floods; Frequency estimation; Geography; Hydrologic measurements; Hydrology; Neural networks; Predictive models; Rivers; Storms;
Conference_Titel :
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Conference_Location :
Montreal, Que.
Print_ISBN :
0-7803-9048-2
DOI :
10.1109/IJCNN.2005.1556319