View in EDS HTML Full Text PDF Full Text

Identification and Segmentation of Internal Solitary Waves in the East China Sea: A TransUNet Approach Using Multi-Source Satellite Imagery.

Saved in:
Bibliographic Details
Title: Identification and Segmentation of Internal Solitary Waves in the East China Sea: A TransUNet Approach Using Multi-Source Satellite Imagery.
Authors: Xu, Jiabao1 (AUTHOR), Liu, Xuanming1,2 (AUTHOR), Yang, Wei1,3 (AUTHOR) wei_yang@tju.edu.cn, Yang, Tianyu1 (AUTHOR), Sha, Ruixuan2 (AUTHOR), Wei, Hao3 (AUTHOR)
Source: Remote Sensing. Jan2026, Vol. 18 Issue 1, p131. 23p.
Subjects: Internal waves, Deep learning, Oceanography, Seasons, Spatial analysis (Statistics), Ocean, Remote-sensing images, Remote sensing
Geographic Terms: East China Sea
Abstract: Highlights: What are the main findings? A TransUNet-based deep learning framework was applied to multi-source satellite imagery (MODIS and SAR), achieving pixel-level ISW segmentation with a Dice coefficient of 71.0% and precision of 72.7%. The study generated the first 22-year (2002–2024) high-resolution spatiotemporal map of ISWs in the East China Sea, revealing two distinct hotspots and a significant summer peak in occurrence frequency. What are the implications of the main findings? The data-driven seasonal patterns align perfectly with the physics of internal tide generation body force, confirming stratification as the dominant control mechanism for ISW variability in this region. This study demonstrates the potential of Transformer-based models in mining massive historical remote sensing archives, providing an efficient tool for large-scale oceanographic big data analysis. The East China Sea (ECS) is a globally active region for internal solitary waves (ISWs); however, its overall spatiotemporal distribution remains poorly understood. To address this gap, this study proposes a deep learning method based on multi-source remote sensing imagery (MODIS and SAR) for the intelligent identification and pixel-level segmentation of ISWs in the ECS. We adopted the TransUNet model, which combines the global context-capturing capability of Transformers with the fine-grained segmentation advantages of U-Net to effectively handle the large-scale continuous characteristics of ISWs. The model achieved a Dice coefficient of 71.0% and a precision of 72.7% on the test set, significantly outperforming existing models such as FCN, SegNet, DeepLabV3+, and U-Net. Using this automated framework, multi-source satellite data from 2002 to 2024 were processed to generate the first high-resolution spatiotemporal map of ISWs covering the entire ECS. The map reveals two spatial hotspots: a primary one at the shelf break northeast of Taiwan and a secondary one in the waters southwest of Jeju Island. Furthermore, ISWs exhibit a marked seasonal cycle in both occurrence frequency and properties, peaking in summer and minimizing in winter. This seasonal pattern aligns closely with the physics of internal tide generation via body forcing. By providing the first long-term, high-resolution ISW dataset for the entire ECS, this study demonstrates the potential of deep learning techniques for ISW research in complex marginal seas. [ABSTRACT FROM AUTHOR]
Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 190787351
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Identification and Segmentation of Internal Solitary Waves in the East China Sea: A TransUNet Approach Using Multi-Source Satellite Imagery.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Xu%2C+Jiabao%22">Xu, Jiabao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Xuanming%22">Liu, Xuanming</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Yang%2C+Wei%22">Yang, Wei</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<i> wei_yang@tju.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Yang%2C+Tianyu%22">Yang, Tianyu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sha%2C+Ruixuan%22">Sha, Ruixuan</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Wei%2C+Hao%22">Wei, Hao</searchLink><relatesTo>3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Jan2026, Vol. 18 Issue 1, p131. 23p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Internal+waves%22">Internal waves</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Oceanography%22">Oceanography</searchLink><br /><searchLink fieldCode="DE" term="%22Seasons%22">Seasons</searchLink><br /><searchLink fieldCode="DE" term="%22Spatial+analysis+%28Statistics%29%22">Spatial analysis (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Ocean%22">Ocean</searchLink><br /><searchLink fieldCode="DE" term="%22Remote-sensing+images%22">Remote-sensing images</searchLink><br /><searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22East+China+Sea%22">East China Sea</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Highlights: What are the main findings? A TransUNet-based deep learning framework was applied to multi-source satellite imagery (MODIS and SAR), achieving pixel-level ISW segmentation with a Dice coefficient of 71.0% and precision of 72.7%. The study generated the first 22-year (2002–2024) high-resolution spatiotemporal map of ISWs in the East China Sea, revealing two distinct hotspots and a significant summer peak in occurrence frequency. What are the implications of the main findings? The data-driven seasonal patterns align perfectly with the physics of internal tide generation body force, confirming stratification as the dominant control mechanism for ISW variability in this region. This study demonstrates the potential of Transformer-based models in mining massive historical remote sensing archives, providing an efficient tool for large-scale oceanographic big data analysis. The East China Sea (ECS) is a globally active region for internal solitary waves (ISWs); however, its overall spatiotemporal distribution remains poorly understood. To address this gap, this study proposes a deep learning method based on multi-source remote sensing imagery (MODIS and SAR) for the intelligent identification and pixel-level segmentation of ISWs in the ECS. We adopted the TransUNet model, which combines the global context-capturing capability of Transformers with the fine-grained segmentation advantages of U-Net to effectively handle the large-scale continuous characteristics of ISWs. The model achieved a Dice coefficient of 71.0% and a precision of 72.7% on the test set, significantly outperforming existing models such as FCN, SegNet, DeepLabV3+, and U-Net. Using this automated framework, multi-source satellite data from 2002 to 2024 were processed to generate the first high-resolution spatiotemporal map of ISWs covering the entire ECS. The map reveals two spatial hotspots: a primary one at the shelf break northeast of Taiwan and a secondary one in the waters southwest of Jeju Island. Furthermore, ISWs exhibit a marked seasonal cycle in both occurrence frequency and properties, peaking in summer and minimizing in winter. This seasonal pattern aligns closely with the physics of internal tide generation via body forcing. By providing the first long-term, high-resolution ISW dataset for the entire ECS, this study demonstrates the potential of deep learning techniques for ISW research in complex marginal seas. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=190787351
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs18010131
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 23
        StartPage: 131
    Subjects:
      – SubjectFull: Internal waves
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Oceanography
        Type: general
      – SubjectFull: Seasons
        Type: general
      – SubjectFull: Spatial analysis (Statistics)
        Type: general
      – SubjectFull: Ocean
        Type: general
      – SubjectFull: Remote-sensing images
        Type: general
      – SubjectFull: Remote sensing
        Type: general
      – SubjectFull: East China Sea
        Type: general
    Titles:
      – TitleFull: Identification and Segmentation of Internal Solitary Waves in the East China Sea: A TransUNet Approach Using Multi-Source Satellite Imagery.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Xu, Jiabao
      – PersonEntity:
          Name:
            NameFull: Liu, Xuanming
      – PersonEntity:
          Name:
            NameFull: Yang, Wei
      – PersonEntity:
          Name:
            NameFull: Yang, Tianyu
      – PersonEntity:
          Name:
            NameFull: Sha, Ruixuan
      – PersonEntity:
          Name:
            NameFull: Wei, Hao
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: Jan2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20724292
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Remote Sensing
              Type: main
ResultId 1