View in EDS

Evaluating different strategies for machine learning training applied to flow forecasting based on clustering of flood events

Saved in:
Bibliographic Details
Title: Evaluating different strategies for machine learning training applied to flow forecasting based on clustering of flood events
Authors: Patrícia Cristina Steffen, Júlio Gomes, Eloy Kaviski, Daniel Henrique Marco Detzel
Source: Revista Brasileira de Recursos Hídricos, Vol 30 (2025)
Publisher Information: FapUNIFESP (SciELO), 2025.
Publication Year: 2025
Subject Terms: TC401-506, Data-driven intelligent models, Technology, Hydraulic engineering, Hydrological modeling, Support Vector Regression algorithm, Artificial Intelligence techniques, River, lake, and water-supply engineering (General), Environmental sciences, Geography. Anthropology. Recreation, GE1-350, TC1-978, Fuzzy C-Means algorithm
Description: This paper presents a new hydrological modeling approach for discharge prediction based on flood clustering. Combined with Machine Learning techniques, river flow simulation is optimized through increased data similarity within clusters. Using daily mean discharge from 1964 to 2015 in União da Vitória (Iguaçu River basin, Paraná State, Brazil), the Fuzzy C-Means algorithm clustered flood events into three groups. So, five models were trained: one for the complete series, one for all flood events, and one for each cluster. The Support Vector Regression algorithm was used to develop Artificial Intelligence (AI) models, that had better performance in predicting discharge for each group they were trained and showed similar efficiency to the model trained for the entire series for a 1-day forecast time. The present paper discusses only the results from the training and testing phases. A future paper (in elaboration) will present the development and evaluation of the flow forecast models based on the proposed methodology.
Document Type: Article
ISSN: 2318-0331
1414-381X
DOI: 10.1590/2318-0331.302520240087
Access URL: https://doaj.org/article/9e5024b51cff4a8a85095a4af0debb97
Rights: CC BY
Accession Number: edsair.doi.dedup.....d07254b51ee9001c75c8f365ec2f9ce1
Database: OpenAIRE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://explore.openaire.eu/search/publication?articleId=doi_dedup___%3A%3Ad07254b51ee9001c75c8f365ec2f9ce1
    Name: EDS - OpenAIRE (s4221598)
    Category: fullText
    Text: View record at OpenAIRE
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Steffen%20PC
    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: edsair
DbLabel: OpenAIRE
An: edsair.doi.dedup.....d07254b51ee9001c75c8f365ec2f9ce1
RelevancyScore: 965
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 964.736328125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Evaluating different strategies for machine learning training applied to flow forecasting based on clustering of flood events
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Patrícia+Cristina+Steffen%22">Patrícia Cristina Steffen</searchLink><br /><searchLink fieldCode="AR" term="%22Júlio+Gomes%22">Júlio Gomes</searchLink><br /><searchLink fieldCode="AR" term="%22Eloy+Kaviski%22">Eloy Kaviski</searchLink><br /><searchLink fieldCode="AR" term="%22Daniel+Henrique+Marco+Detzel%22">Daniel Henrique Marco Detzel</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Revista Brasileira de Recursos Hídricos, Vol 30 (2025)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: FapUNIFESP (SciELO), 2025.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22TC401-506%22">TC401-506</searchLink><br /><searchLink fieldCode="DE" term="%22Data-driven+intelligent+models%22">Data-driven intelligent models</searchLink><br /><searchLink fieldCode="DE" term="%22Technology%22">Technology</searchLink><br /><searchLink fieldCode="DE" term="%22Hydraulic+engineering%22">Hydraulic engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Hydrological+modeling%22">Hydrological modeling</searchLink><br /><searchLink fieldCode="DE" term="%22Support+Vector+Regression+algorithm%22">Support Vector Regression algorithm</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence+techniques%22">Artificial Intelligence techniques</searchLink><br /><searchLink fieldCode="DE" term="%22River%2C+lake%2C+and+water-supply+engineering+%28General%29%22">River, lake, and water-supply engineering (General)</searchLink><br /><searchLink fieldCode="DE" term="%22Environmental+sciences%22">Environmental sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Geography%2E+Anthropology%2E+Recreation%22">Geography. Anthropology. Recreation</searchLink><br /><searchLink fieldCode="DE" term="%22GE1-350%22">GE1-350</searchLink><br /><searchLink fieldCode="DE" term="%22TC1-978%22">TC1-978</searchLink><br /><searchLink fieldCode="DE" term="%22Fuzzy+C-Means+algorithm%22">Fuzzy C-Means algorithm</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: This paper presents a new hydrological modeling approach for discharge prediction based on flood clustering. Combined with Machine Learning techniques, river flow simulation is optimized through increased data similarity within clusters. Using daily mean discharge from 1964 to 2015 in União da Vitória (Iguaçu River basin, Paraná State, Brazil), the Fuzzy C-Means algorithm clustered flood events into three groups. So, five models were trained: one for the complete series, one for all flood events, and one for each cluster. The Support Vector Regression algorithm was used to develop Artificial Intelligence (AI) models, that had better performance in predicting discharge for each group they were trained and showed similar efficiency to the model trained for the entire series for a 1-day forecast time. The present paper discusses only the results from the training and testing phases. A future paper (in elaboration) will present the development and evaluation of the flow forecast models based on the proposed methodology.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Article
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 2318-0331<br />1414-381X
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1590/2318-0331.302520240087
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://doaj.org/article/9e5024b51cff4a8a85095a4af0debb97" linkWindow="_blank">https://doaj.org/article/9e5024b51cff4a8a85095a4af0debb97</link>
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: CC BY
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsair.doi.dedup.....d07254b51ee9001c75c8f365ec2f9ce1
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsair&AN=edsair.doi.dedup.....d07254b51ee9001c75c8f365ec2f9ce1
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1590/2318-0331.302520240087
    Languages:
      – Text: Undetermined
    Subjects:
      – SubjectFull: TC401-506
        Type: general
      – SubjectFull: Data-driven intelligent models
        Type: general
      – SubjectFull: Technology
        Type: general
      – SubjectFull: Hydraulic engineering
        Type: general
      – SubjectFull: Hydrological modeling
        Type: general
      – SubjectFull: Support Vector Regression algorithm
        Type: general
      – SubjectFull: Artificial Intelligence techniques
        Type: general
      – SubjectFull: River, lake, and water-supply engineering (General)
        Type: general
      – SubjectFull: Environmental sciences
        Type: general
      – SubjectFull: Geography. Anthropology. Recreation
        Type: general
      – SubjectFull: GE1-350
        Type: general
      – SubjectFull: TC1-978
        Type: general
      – SubjectFull: Fuzzy C-Means algorithm
        Type: general
    Titles:
      – TitleFull: Evaluating different strategies for machine learning training applied to flow forecasting based on clustering of flood events
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Patrícia Cristina Steffen
      – PersonEntity:
          Name:
            NameFull: Júlio Gomes
      – PersonEntity:
          Name:
            NameFull: Eloy Kaviski
      – PersonEntity:
          Name:
            NameFull: Daniel Henrique Marco Detzel
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 23180331
            – Type: issn-print
              Value: 1414381X
            – Type: issn-locals
              Value: edsair
            – Type: issn-locals
              Value: edsairFT
          Numbering:
            – Type: volume
              Value: 30
          Titles:
            – TitleFull: RBRH
              Type: main
ResultId 1