Fusing stacked autoencoder and long short-term memory for regional multistep-ahead flood inundation forecasts

•Use Stacked Autoencoder (SAE) to reduce the dimension of regional inundation data.•Use PCA to adjust the network structure and initialize network weights of the SAE.•SAE-RNN nowcasts multistep-ahead regional inundation maps of typhoon events.•Offer 2D-visualization of spatio-temporal distribution o...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of hydrology (Amsterdam) Vol. 598; p. 126371
Main Authors:	Kao, I-Feng, Liou, Jia-Yi, Lee, Meng-Hsin, Chang, Fi-John
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.07.2021
Subjects:	case studies data collection disaster preparedness hydrology Long short-term memory (LSTM) Multistep-ahead forecast neural networks rain Recurrent neural network (RNN) Regional flood inundation Stacked autoencoder (SAE) Taiwan uncertainty Taiwan Stacked autoencoder (SAE) Regional flood inundation Multistep-ahead forecast Long short-term memory (LSTM) Recurrent neural network (RNN)
ISSN:	0022-1694, 1879-2707
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!