Regional flood inundation nowcast using hybrid SOM and dynamic neural networks

doi:10.1016/j.jhydrol.2014.07.036

機構典藏 > College of Engineering > Graduate Institute & Department of Water Resources and Environmental Engineering > Journal Article > Item 987654321/100121

Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/100121

Title:	Regional flood inundation nowcast using hybrid SOM and dynamic neural networks
Authors:	Chang, Li-Chiu;Sheng, Hung-Yu;Chang, Fi-John
Contributors:	淡江大學水資源及環境工程學系
Keywords:	Artificial neural network (ANN);Self-organizing map (SOM);Recurrent configuration of nonlinear autoregressive with exogenous inputs (R-NARX);Flood inundation map;Regional flood forecasting model
Date:	2014-11-27
Issue Date:	2015-01-28 11:08:12 (UTC+8)
Publisher:	Netherlands: Elsevier BV
Abstract:	This study proposes a hybrid SOM–R-NARX methodology for nowcasting multi-step-ahead regional flood inundation maps during typhoon events. The core idea is to form a meaningful topology of inundation maps and then real-time update the selected inundation map according to a forecasted total inundated volume. The methodology includes three major schemes: (1) configuring the self-organizing map (SOM) to categorize a large number of regional inundation maps into a meaningful topology; (2) building a recurrent configuration of nonlinear autoregressive with exogenous inputs (R-NARX) to forecast the total inundated volume; and (3) adjusting the weights of the selected neuron in the constructed SOM based on the forecasted total inundated volume to obtain a real-time adapted regional inundation map. The proposed models are trained and tested based on a large number of inundation data sets collected in an inundation-prone region (270 km2) in the Yilan County, Taiwan. The results show that (1) the SOM–R-NARX model can suitably forecast multi-step-ahead regional inundation maps; and (2) the SOM–R-NARX model consistently outperforms the comparative model in providing regional inundation maps with smaller forecast errors and higher correlation (RMSE < 0.1 m and R2 > 0.9 in most cases). The proposed modelling approach offers an insightful and promising methodology for real-time forecasting 2-dimensional visible inundation maps during storm events.
Relation:	Journal of Hydrology 519(pt.A), pp.476-489
DOI:	10.1016/j.jhydrol.2014.07.036
Appears in Collections:	[Graduate Institute & Department of Water Resources and Environmental Engineering] Journal Article

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	311	View/Open
Regional flood inundation nowcast using hybrid SOM and dynamic neural networks.pdf		3988Kb	Adobe PDF	1	View/Open

Loading...