Identification and Segmentation of Internal Solitary Waves in the East China Sea: A TransUNet Approach Using Multi-Source Satellite Imagery.
Saved in:
| 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.
Login for full access.
|
|
| 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] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18010131 |
