Hybrid neural networks in rainfall-inundation forecasting based on a synthetic potential inundation database

Abstract. This study attempts to achieve real-time rainfall-inundation forecasting in lowland regions, based on a synthetic potential inundation database. With the principal component analysis and a feed-forward neural network, a rainfall-inundation hybrid neural network (RiHNN) is proposed to forecast 1-h-ahead inundation depth as hydrographs at specific representative locations using spatial rainfall intensities and accumulations. A systematic procedure is presented to construct the RiHNN, which combines the merits of detailed hydraulic modeling in flood-prone lowlands via a two-dimensional overland-flow model and time-saving calculation in a real-time rainfall-inundation forecasting via ANN model. Analytical results from the RiHNNs with various principal components indicate that the RiHNNs with fewer weights can have about the same performance as a feed-forward neural network. The RiHNNs evaluated through four types of real/synthetic rainfall events also show to fit inundation-depth hydrographs well with high rainfall. Moreover, the results of real-time rainfall-inundation forecasting help the emergency manager set operational responses, which are beneficial for flood warning preparations.

[1]  G. Sahoo,et al.  Flow forecasting for a Hawaii stream using rating curves and neural networks , 2006 .

[2]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[3]  R. Abrahart,et al.  Flood estimation at ungauged sites using artificial neural networks , 2006 .

[4]  A GIS‐ASSISTED DISTRIBUTED WATERSHED MODEL FOR SIMULATING FLOODING AND INUNDATION 1 , 2000 .

[5]  Gwo-Fong Lin,et al.  Hybrid Flux-Splitting Finite-Volume Scheme for the Shallow Water Flow Simulations with Source Terms , 2007 .

[6]  A. M. Wasantha Lal,et al.  Performance Comparison of Overland Flow Algorithms , 1998 .

[7]  Horritt,et al.  Evaluation of 1-D and 2-D models for predicting river flood inundation , 2002 .

[8]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[9]  Kieran M. O'Connor,et al.  Real-time flow forecasting in the absence of quantitative precipitation forecasts: A multi-model approach , 2007 .

[10]  Paul D. Bates,et al.  Optimal use of high‐resolution topographic data in flood inundation models , 2003 .

[11]  J. Nash,et al.  River flow forecasting through conceptual models part I — A discussion of principles☆ , 1970 .

[12]  J. Cunge,et al.  Practical aspects of computational river hydraulics , 1980 .

[13]  E. Toth,et al.  Comparison of short-term rainfall prediction models for real-time flood forecasting , 2000 .

[14]  Ozgur Kisi,et al.  Comparison of different ANN techniques in river flow prediction , 2007 .

[15]  Yi-Ming Wei,et al.  Artificial neural network based predictive method for flood disaster , 2002 .

[16]  Tienfuan Kerh,et al.  Neural networks forecasting of flood discharge at an unmeasured station using river upstream information , 2006, Adv. Eng. Softw..

[17]  Chin-Hsiung Loh,et al.  Development and Implementation of Disaster Reduction Technology in Taiwan , 2006 .

[18]  Holger R. Maier,et al.  Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications , 2000, Environ. Model. Softw..

[19]  Giles M. Foody,et al.  The effect of training set size and composition on artificial neural network classification , 1995 .

[20]  L. Bodri,et al.  Prediction of extreme precipitation using a neural network: application to summer flood occurence in Moravia , 2000 .

[21]  S. Blazková,et al.  Spatially distributed observations in constraining inundation modelling uncertainties , 2005 .

[22]  Makarand Deo,et al.  Real‐Time Flood Forecasting Using Neural Networks , 1998 .

[23]  T. Chang,et al.  Inundation simulation for urban drainage basin with storm sewer system , 2000 .

[24]  Jihn-Sung Lai,et al.  A well‐balanced upstream flux‐splitting finite‐volume scheme for shallow‐water flow simulations with irregular bed topography , 2009 .

[25]  David A. Wismer,et al.  Introduction to nonlinear optimization , 1978 .

[26]  Pao-Shan Yu,et al.  Pruning of support vector networks on flood forecasting , 2007 .

[27]  Albert S. Chen,et al.  Establishing the Database of Inundation Potential in Taiwan , 2006 .

[28]  Anthony S Lowe.  The Federal Emergency Management Agency’s Multi-Hazard Flood Map Modernization and The National Map , 2003 .

[29]  S. Lane,et al.  Urban fluvial flood modelling using a two‐dimensional diffusion‐wave treatment, part 1: mesh resolution effects , 2006 .

[30]  Jihn-Sung Lai,et al.  Application of Recurrent Neural Networks to Rainfall-runoff Processes , 2008 .

[31]  P. D. Batesa,et al.  A simple raster-based model for flood inundation simulation , 2000 .

[32]  J. Nazuno.  Haykin, Simon. Neural networks: A comprehensive foundation, Prentice Hall, Inc. Segunda Edición, 1999 , 2000 .

[33]  I. Jolliffe.  Principal Component Analysis , 2002 .

[34]  Ming-Hsu Li,et al.  An Assessment of Structural Measures for Flood-prone Lowlands with High Population Density along the Keelung River in Taiwan , 2006 .

[35]  Patrick Arnaud,et al.  Influence of rainfall spatial variability on flood prediction , 2002 .

[36]  Dynamic inundation simulation of storm water interaction between sewer system and overland flows , 2002 .

[37]  G. Sahoo,et al.  Use of neural network to predict flash flood and attendant water qualities of a mountainous stream on Oahu, Hawaii , 2006 .

[38]  Jihn-Sung Lai,et al.  Finite‐volume multi‐stage schemes for shallow‐water flow simulations , 2008 .

[39]  J. Lai,et al.  An upstream flux‐splitting finite‐volume scheme for 2D shallow water equations , 2005 .

[40]  Kwok-wing Chau.  A split-step particle swarm optimization algorithm in river stage forecasting , 2007 .

[41]  Ana P. Barros,et al.  Quantitative flood forecasting using multisensor data and neural networks , 2001 .

[42]  Jihn-Sung Lai,et al.  A deterministic linearized recurrent neural network for recognizing the transition of rainfall–runoff processes , 2007 .

[43]  Tsung-Yi Pan,et al.  State space neural networks for short term rainfall-runoff forecasting , 2004 .