View in EDS HTML Full Text PDF Full Text

Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems.

Saved in:
Bibliographic Details
Title: Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems.
Authors: Yu, Hangyi1 (AUTHOR), Gao, Sheng1 (AUTHOR), Zhao, Hanqing1 (AUTHOR), Zhang, Yu1 (AUTHOR), Lin, Lianlei1 (AUTHOR) linlianlei@hit.edu.cn, Zhang, Zongwei1 (AUTHOR), Wang, Junkai1 (AUTHOR)
Source: Energies (19961073). Jun2026, Vol. 19 Issue 12, p2847. 24p.
Subject Terms: *Wind forecasting, *Partial differential equations, *Energy infrastructure, *Dynamical systems, *Deep learning, *Atmospheric circulation, *Spatiotemporal processes
Abstract: Wind speed prediction is an essential spatiotemporal forecasting task in wind energy systems, yet it remains challenging due to the nonlinear and dynamic characteristics of atmospheric processes. The evolution of wind is governed by physical laws, which can be effectively described using partial differential equations (PDEs). To improve forecasting reliability and accuracy, this paper proposes a novel network model, termed DynWindNet, which integrates equation-based dynamics with data-driven dynamics within a unified framework. Specifically, an interactive dual-branch architecture is designed, where a Physics–Data Coupling Module (PDCM) enables adaptive information exchange between the two dynamics via attention-based gating mechanisms. In addition, a frequency-aware enhancement module (FAEM) is introduced to refine the representations of the data-driven branch by selectively emphasizing informative frequency components. Experimental results on the ERA5 dataset demonstrate that DynWindNet consistently outperforms representative baseline methods across atmospheric pressure levels. Overall, the proposed framework provides an effective approach for integrating physics-guided evolution modeling with deep spatiotemporal representation learning in wind field forecasting. [ABSTRACT FROM AUTHOR]
Database: Energy & Power Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: enr
DbLabel: Energy & Power Source
An: 194909296
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Yu%2C+Hangyi%22">Yu, Hangyi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Gao%2C+Sheng%22">Gao, Sheng</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhao%2C+Hanqing%22">Zhao, Hanqing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhang%2C+Yu%22">Zhang, Yu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lin%2C+Lianlei%22">Lin, Lianlei</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> linlianlei@hit.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Zongwei%22">Zhang, Zongwei</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wang%2C+Junkai%22">Wang, Junkai</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Energies+%2819961073%29%22">Energies (19961073)</searchLink>. Jun2026, Vol. 19 Issue 12, p2847. 24p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: *<searchLink fieldCode="DE" term="%22Wind+forecasting%22">Wind forecasting</searchLink><br />*<searchLink fieldCode="DE" term="%22Partial+differential+equations%22">Partial differential equations</searchLink><br />*<searchLink fieldCode="DE" term="%22Energy+infrastructure%22">Energy infrastructure</searchLink><br />*<searchLink fieldCode="DE" term="%22Dynamical+systems%22">Dynamical systems</searchLink><br />*<searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br />*<searchLink fieldCode="DE" term="%22Atmospheric+circulation%22">Atmospheric circulation</searchLink><br />*<searchLink fieldCode="DE" term="%22Spatiotemporal+processes%22">Spatiotemporal processes</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Wind speed prediction is an essential spatiotemporal forecasting task in wind energy systems, yet it remains challenging due to the nonlinear and dynamic characteristics of atmospheric processes. The evolution of wind is governed by physical laws, which can be effectively described using partial differential equations (PDEs). To improve forecasting reliability and accuracy, this paper proposes a novel network model, termed DynWindNet, which integrates equation-based dynamics with data-driven dynamics within a unified framework. Specifically, an interactive dual-branch architecture is designed, where a Physics–Data Coupling Module (PDCM) enables adaptive information exchange between the two dynamics via attention-based gating mechanisms. In addition, a frequency-aware enhancement module (FAEM) is introduced to refine the representations of the data-driven branch by selectively emphasizing informative frequency components. Experimental results on the ERA5 dataset demonstrate that DynWindNet consistently outperforms representative baseline methods across atmospheric pressure levels. Overall, the proposed framework provides an effective approach for integrating physics-guided evolution modeling with deep spatiotemporal representation learning in wind field forecasting. [ABSTRACT FROM AUTHOR]
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=enr&AN=194909296
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/en19122847
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 24
        StartPage: 2847
    Subjects:
      – SubjectFull: Wind forecasting
        Type: general
      – SubjectFull: Partial differential equations
        Type: general
      – SubjectFull: Energy infrastructure
        Type: general
      – SubjectFull: Dynamical systems
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Atmospheric circulation
        Type: general
      – SubjectFull: Spatiotemporal processes
        Type: general
    Titles:
      – TitleFull: Bridging Equation-Based and Data-Driven Dynamics for Reliable Wind Speed Prediction in Energy Systems.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yu, Hangyi
      – PersonEntity:
          Name:
            NameFull: Gao, Sheng
      – PersonEntity:
          Name:
            NameFull: Zhao, Hanqing
      – PersonEntity:
          Name:
            NameFull: Zhang, Yu
      – PersonEntity:
          Name:
            NameFull: Lin, Lianlei
      – PersonEntity:
          Name:
            NameFull: Zhang, Zongwei
      – PersonEntity:
          Name:
            NameFull: Wang, Junkai
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 15
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 19961073
          Numbering:
            – Type: volume
              Value: 19
            – Type: issue
              Value: 12
          Titles:
            – TitleFull: Energies (19961073)
              Type: main
ResultId 1