View in EDS

Enhancing multi-step-ahead prediction of wave propagation with the CAE-LSTM model: a novel deep learning-based approach to flood dynamics

Saved in:
Bibliographic Details
Title: Enhancing multi-step-ahead prediction of wave propagation with the CAE-LSTM model: a novel deep learning-based approach to flood dynamics
Authors: Zheng Han, Guanping Long, Changli Li, Yange Li, Bin Su, Linrong Xu, Weidong Wang, Guangqi Chen
Source: Geomatics, Natural Hazards & Risk, Vol 16, Iss 1 (2025)
Publisher Information: Taylor & Francis Group, 2025.
Publication Year: 2025
Collection: LCC:Environmental technology. Sanitary engineering
LCC:Environmental sciences
LCC:Risk in industry. Risk management
Subject Terms: Wave propagation, flood dynamics, deep learning, convolutional autoencoders, long short-term memory, Environmental technology. Sanitary engineering, TD1-1066, Environmental sciences, GE1-350, Risk in industry. Risk management, HD61
Description: A deep understanding of the wave propagation process during flood dynamics is fundamental for hazard prediction and mitigation, wherein up-to-date Physics-Informed Neural Networks (PINNs) have emerged as a promising alternative to conventional numerical methods, offering a paradigm shift in scientific modeling. However, traditional fully connected neural network-based PINNs have shown limitations of insufficient learning ability for long-term wave propagation processes and limited generalization to various untrained scenarios. This paper introduces a novel Convolutional Autoencoder (CAE)-integrated Long Short-Term Memory (LSTM) model to address these problems. Inspired by the Finite Difference Method for solving Shallow Water Equations, the proposed CAE-LSTM model is designed to enhance the capture and prediction ability for wave propagation by integrating both spatial and temporal dimensions. The CAE component employs convolutional neural networks to extract spatial features, producing compact latent representations that simplify the complexity of wave propagation. The LSTM captures temporal dependencies within this latent space, enabling precise predictions based on time series data. Validated on four dam-break scenarios, the CAE-LSTM model generally achieves an RMSE less than 0.5 after 3,000 steps of rolling prediction, with computational efficiency approximately 200 times higher than traditional finite volume method (FVM) simulations.
Document Type: article
File Description: electronic resource
Language: English
ISSN: 1947-5713
1947-5705
Relation: https://doaj.org/toc/1947-5705; https://doaj.org/toc/1947-5713
DOI: 10.1080/19475705.2025.2588708
Access URL: https://doaj.org/article/3e10f6e71d724d5a922f6d9c77ca1330
Accession Number: edsdoj.3e10f6e71d724d5a922f6d9c77ca1330
Database: Directory of Open Access Journals
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://doaj.org/article/3e10f6e71d724d5a922f6d9c77ca1330
    Name: EDS - DOAJ (s4221598)
    Category: fullText
    Text: View record in DOAJ
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsdoj&genre=article&issn=19475713&ISBN=&volume=16&issue=1&date=20251201&spage=&pages=&title=Geomatics, Natural Hazards & Risk&atitle=Enhancing%20multi-step-ahead%20prediction%20of%20wave%20propagation%20with%20the%20CAE-LSTM%20model%3A%20a%20novel%20deep%20learning-based%20approach%20to%20flood%20dynamics&aulast=Zheng%20Han&id=DOI:10.1080/19475705.2025.2588708
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Han%20Z
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsdoj
DbLabel: Directory of Open Access Journals
An: edsdoj.3e10f6e71d724d5a922f6d9c77ca1330
RelevancyScore: 1057
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1056.69604492188
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Enhancing multi-step-ahead prediction of wave propagation with the CAE-LSTM model: a novel deep learning-based approach to flood dynamics
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zheng+Han%22">Zheng Han</searchLink><br /><searchLink fieldCode="AR" term="%22Guanping+Long%22">Guanping Long</searchLink><br /><searchLink fieldCode="AR" term="%22Changli+Li%22">Changli Li</searchLink><br /><searchLink fieldCode="AR" term="%22Yange+Li%22">Yange Li</searchLink><br /><searchLink fieldCode="AR" term="%22Bin+Su%22">Bin Su</searchLink><br /><searchLink fieldCode="AR" term="%22Linrong+Xu%22">Linrong Xu</searchLink><br /><searchLink fieldCode="AR" term="%22Weidong+Wang%22">Weidong Wang</searchLink><br /><searchLink fieldCode="AR" term="%22Guangqi+Chen%22">Guangqi Chen</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Geomatics, Natural Hazards & Risk, Vol 16, Iss 1 (2025)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Taylor & Francis Group, 2025.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: LCC:Environmental technology. Sanitary engineering<br />LCC:Environmental sciences<br />LCC:Risk in industry. Risk management
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Wave+propagation%22">Wave propagation</searchLink><br /><searchLink fieldCode="DE" term="%22flood+dynamics%22">flood dynamics</searchLink><br /><searchLink fieldCode="DE" term="%22deep+learning%22">deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22convolutional+autoencoders%22">convolutional autoencoders</searchLink><br /><searchLink fieldCode="DE" term="%22long+short-term+memory%22">long short-term memory</searchLink><br /><searchLink fieldCode="DE" term="%22Environmental+technology%2E+Sanitary+engineering%22">Environmental technology. Sanitary engineering</searchLink><br /><searchLink fieldCode="DE" term="%22TD1-1066%22">TD1-1066</searchLink><br /><searchLink fieldCode="DE" term="%22Environmental+sciences%22">Environmental sciences</searchLink><br /><searchLink fieldCode="DE" term="%22GE1-350%22">GE1-350</searchLink><br /><searchLink fieldCode="DE" term="%22Risk+in+industry%2E+Risk+management%22">Risk in industry. Risk management</searchLink><br /><searchLink fieldCode="DE" term="%22HD61%22">HD61</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: A deep understanding of the wave propagation process during flood dynamics is fundamental for hazard prediction and mitigation, wherein up-to-date Physics-Informed Neural Networks (PINNs) have emerged as a promising alternative to conventional numerical methods, offering a paradigm shift in scientific modeling. However, traditional fully connected neural network-based PINNs have shown limitations of insufficient learning ability for long-term wave propagation processes and limited generalization to various untrained scenarios. This paper introduces a novel Convolutional Autoencoder (CAE)-integrated Long Short-Term Memory (LSTM) model to address these problems. Inspired by the Finite Difference Method for solving Shallow Water Equations, the proposed CAE-LSTM model is designed to enhance the capture and prediction ability for wave propagation by integrating both spatial and temporal dimensions. The CAE component employs convolutional neural networks to extract spatial features, producing compact latent representations that simplify the complexity of wave propagation. The LSTM captures temporal dependencies within this latent space, enabling precise predictions based on time series data. Validated on four dam-break scenarios, the CAE-LSTM model generally achieves an RMSE less than 0.5 after 3,000 steps of rolling prediction, with computational efficiency approximately 200 times higher than traditional finite volume method (FVM) simulations.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic resource
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 1947-5713<br />1947-5705
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://doaj.org/toc/1947-5705; https://doaj.org/toc/1947-5713
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1080/19475705.2025.2588708
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doaj.org/article/3e10f6e71d724d5a922f6d9c77ca1330" linkWindow="_blank">https://doaj.org/article/3e10f6e71d724d5a922f6d9c77ca1330</link>
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsdoj.3e10f6e71d724d5a922f6d9c77ca1330
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsdoj&AN=edsdoj.3e10f6e71d724d5a922f6d9c77ca1330
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/19475705.2025.2588708
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Wave propagation
        Type: general
      – SubjectFull: flood dynamics
        Type: general
      – SubjectFull: deep learning
        Type: general
      – SubjectFull: convolutional autoencoders
        Type: general
      – SubjectFull: long short-term memory
        Type: general
      – SubjectFull: Environmental technology. Sanitary engineering
        Type: general
      – SubjectFull: TD1-1066
        Type: general
      – SubjectFull: Environmental sciences
        Type: general
      – SubjectFull: GE1-350
        Type: general
      – SubjectFull: Risk in industry. Risk management
        Type: general
      – SubjectFull: HD61
        Type: general
    Titles:
      – TitleFull: Enhancing multi-step-ahead prediction of wave propagation with the CAE-LSTM model: a novel deep learning-based approach to flood dynamics
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zheng Han
      – PersonEntity:
          Name:
            NameFull: Guanping Long
      – PersonEntity:
          Name:
            NameFull: Changli Li
      – PersonEntity:
          Name:
            NameFull: Yange Li
      – PersonEntity:
          Name:
            NameFull: Bin Su
      – PersonEntity:
          Name:
            NameFull: Linrong Xu
      – PersonEntity:
          Name:
            NameFull: Weidong Wang
      – PersonEntity:
          Name:
            NameFull: Guangqi Chen
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 19475713
            – Type: issn-print
              Value: 19475705
          Numbering:
            – Type: volume
              Value: 16
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Geomatics, Natural Hazards & Risk
              Type: main
ResultId 1