Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10316/104864 https://doi.org/10.1111/jfr3.12684 |
Resumo: | Computational complexity has been the bottleneck for applying physically based simulations in large urban areas with high spatial resolution for efficient and systematic flooding analyses and risk assessment. To overcome the issue of long computational time and accelerate the prediction process, this paper proposes that the prediction of maximum water depth can be considered an image-to-image translation problem in which water depth rasters are generated using the information learned from data instead of by conducting simulations. The proposed data-driven urban pluvial flood approach is based on a deep convolutional neural network trained using flood simulation data obtained from three catchments and 18 hyetographs. Multiple tests to assess the accuracy and validity of the proposed approach were conducted with both design and real hyetographs. The results show that flood prediction based on neural networks use only 0.5% of the time compared with that of physically based models, with promising accuracy and generalizability. The proposed neural network can also potentially be applied to different but relevant problems, including flood analysis for flood-safe urban layout planning. |
id |
RCAP_503b09f74dd23a8737d0c15ba83e96e8 |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/104864 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networksconvolutional neural networkdata-driven emulationfast water depth predictionflood modellingComputational complexity has been the bottleneck for applying physically based simulations in large urban areas with high spatial resolution for efficient and systematic flooding analyses and risk assessment. To overcome the issue of long computational time and accelerate the prediction process, this paper proposes that the prediction of maximum water depth can be considered an image-to-image translation problem in which water depth rasters are generated using the information learned from data instead of by conducting simulations. The proposed data-driven urban pluvial flood approach is based on a deep convolutional neural network trained using flood simulation data obtained from three catchments and 18 hyetographs. Multiple tests to assess the accuracy and validity of the proposed approach were conducted with both design and real hyetographs. The results show that flood prediction based on neural networks use only 0.5% of the time compared with that of physically based models, with promising accuracy and generalizability. The proposed neural network can also potentially be applied to different but relevant problems, including flood analysis for flood-safe urban layout planning.Wiley-Blackwell2020info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/104864http://hdl.handle.net/10316/104864https://doi.org/10.1111/jfr3.12684eng1753-318X1753-318XGuo, ZifengLeitão, João P.Simões, Nuno E.Moosavi, Vahidinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-01-26T21:55:26Zoai:estudogeral.uc.pt:10316/104864Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:21:30.056385Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks |
title |
Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks |
spellingShingle |
Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks Guo, Zifeng convolutional neural network data-driven emulation fast water depth prediction flood modelling |
title_short |
Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks |
title_full |
Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks |
title_fullStr |
Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks |
title_full_unstemmed |
Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks |
title_sort |
Data‐driven flood emulation: Speeding up urban flood predictions by deep convolutional neural networks |
author |
Guo, Zifeng |
author_facet |
Guo, Zifeng Leitão, João P. Simões, Nuno E. Moosavi, Vahid |
author_role |
author |
author2 |
Leitão, João P. Simões, Nuno E. Moosavi, Vahid |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Guo, Zifeng Leitão, João P. Simões, Nuno E. Moosavi, Vahid |
dc.subject.por.fl_str_mv |
convolutional neural network data-driven emulation fast water depth prediction flood modelling |
topic |
convolutional neural network data-driven emulation fast water depth prediction flood modelling |
description |
Computational complexity has been the bottleneck for applying physically based simulations in large urban areas with high spatial resolution for efficient and systematic flooding analyses and risk assessment. To overcome the issue of long computational time and accelerate the prediction process, this paper proposes that the prediction of maximum water depth can be considered an image-to-image translation problem in which water depth rasters are generated using the information learned from data instead of by conducting simulations. The proposed data-driven urban pluvial flood approach is based on a deep convolutional neural network trained using flood simulation data obtained from three catchments and 18 hyetographs. Multiple tests to assess the accuracy and validity of the proposed approach were conducted with both design and real hyetographs. The results show that flood prediction based on neural networks use only 0.5% of the time compared with that of physically based models, with promising accuracy and generalizability. The proposed neural network can also potentially be applied to different but relevant problems, including flood analysis for flood-safe urban layout planning. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10316/104864 http://hdl.handle.net/10316/104864 https://doi.org/10.1111/jfr3.12684 |
url |
http://hdl.handle.net/10316/104864 https://doi.org/10.1111/jfr3.12684 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
1753-318X 1753-318X |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Wiley-Blackwell |
publisher.none.fl_str_mv |
Wiley-Blackwell |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134105649020928 |