RSCU-Net: A Spatial–Channel Reconstruction U-Net for Seamount Segmentation Using GEBCO Bathymetry.
Saved in:
| Title: | RSCU-Net: A Spatial–Channel Reconstruction U-Net for Seamount Segmentation Using GEBCO Bathymetry. |
|---|---|
| Authors: | Lin, Faran1 (AUTHOR), Guan, Qingsheng1,2 (AUTHOR) guanqs@sio.org.cn, Zhang, Tao1 (AUTHOR), Liu, Hongqin2 (AUTHOR) |
| Source: | Remote Sensing. Apr2026, Vol. 18 Issue 8, p1120. 22p. |
| Subjects: | Seamounts, Bathymetry, Artificial neural networks, Convolutional neural networks, Oceanographic maps, Remote sensing, Geomorphology |
| Abstract: | Highlights: What are the main findings? A novel Spatial–Channel Reconstruction U-Net (RSCU-Net) architecture is developed to address severe class imbalance in bathymetric seamount segmentation. The proposed Residual Spatial–Channel Reconstruction Convolution (Res-SCConv) module effectively suppresses spatial and channel redundancy, significantly improving Recall and Intersection over Union (IoU). What are the implications of the main findings? The framework enhances the reliability of automated seamount extraction from large-scale General Bathymetric Chart of the Oceans (GEBCO) bathymetric data. RSCU-Net provides a robust and effective framework for remote sensing-based seafloor geomorphology mapping. Accurate seamount identification is important for understanding submarine tectonic and magmatic processes and for supporting deep-sea geomorphological analysis. However, seamount recognition faces a severe class imbalance as abyssal plains constitute the majority of deep-sea topography while seamounts occupy only a minimal portion, which makes accurate segmentation difficult. To address this issue, this study proposes an improved U-Net architecture, termed Spatial–Channel Reconstruction U-Net (RSCU-Net), built upon a Residual Spatial–Channel Reconstruction Convolution (Res-SCConv) module. The Res-SCConv module is embedded into each skip connection of the U-Net architecture. The model combines a Spatial Reconstruction Unit (SRU) and a Channel Reconstruction Unit (CRU) to suppress dominant background interference and reduce channel redundancy, and further introduces a Selective Kernel-based Multi-scale Gradient Module (SK-MGM) to improve boundary refinement. Experiments on the GEBCO 2023 bathymetric dataset, including 696 training samples and 88 independent test samples, show that RSCU-Net achieves an Accuracy of 0.938, Recall of 0.833, F1-score of 0.720, and IoU of 0.563. Compared with the baseline U-Net, Recall improves from 0.741 to 0.833 and IoU from 0.405 to 0.563. Additional validation on the Suda Seamount dataset yields an Accuracy of 0.987, F1-score of 0.958, and IoU of 0.920, demonstrating the robustness and generalization capability of the proposed method. [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.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 193435599 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: RSCU-Net: A Spatial–Channel Reconstruction U-Net for Seamount Segmentation Using GEBCO Bathymetry. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Lin%2C+Faran%22">Lin, Faran</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Guan%2C+Qingsheng%22">Guan, Qingsheng</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> guanqs@sio.org.cn</i><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Tao%22">Zhang, Tao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Hongqin%22">Liu, Hongqin</searchLink><relatesTo>2</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Apr2026, Vol. 18 Issue 8, p1120. 22p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Seamounts%22">Seamounts</searchLink><br /><searchLink fieldCode="DE" term="%22Bathymetry%22">Bathymetry</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Oceanographic+maps%22">Oceanographic maps</searchLink><br /><searchLink fieldCode="DE" term="%22Remote+sensing%22">Remote sensing</searchLink><br /><searchLink fieldCode="DE" term="%22Geomorphology%22">Geomorphology</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Highlights: What are the main findings? A novel Spatial–Channel Reconstruction U-Net (RSCU-Net) architecture is developed to address severe class imbalance in bathymetric seamount segmentation. The proposed Residual Spatial–Channel Reconstruction Convolution (Res-SCConv) module effectively suppresses spatial and channel redundancy, significantly improving Recall and Intersection over Union (IoU). What are the implications of the main findings? The framework enhances the reliability of automated seamount extraction from large-scale General Bathymetric Chart of the Oceans (GEBCO) bathymetric data. RSCU-Net provides a robust and effective framework for remote sensing-based seafloor geomorphology mapping. Accurate seamount identification is important for understanding submarine tectonic and magmatic processes and for supporting deep-sea geomorphological analysis. However, seamount recognition faces a severe class imbalance as abyssal plains constitute the majority of deep-sea topography while seamounts occupy only a minimal portion, which makes accurate segmentation difficult. To address this issue, this study proposes an improved U-Net architecture, termed Spatial–Channel Reconstruction U-Net (RSCU-Net), built upon a Residual Spatial–Channel Reconstruction Convolution (Res-SCConv) module. The Res-SCConv module is embedded into each skip connection of the U-Net architecture. The model combines a Spatial Reconstruction Unit (SRU) and a Channel Reconstruction Unit (CRU) to suppress dominant background interference and reduce channel redundancy, and further introduces a Selective Kernel-based Multi-scale Gradient Module (SK-MGM) to improve boundary refinement. Experiments on the GEBCO 2023 bathymetric dataset, including 696 training samples and 88 independent test samples, show that RSCU-Net achieves an Accuracy of 0.938, Recall of 0.833, F1-score of 0.720, and IoU of 0.563. Compared with the baseline U-Net, Recall improves from 0.741 to 0.833 and IoU from 0.405 to 0.563. Additional validation on the Suda Seamount dataset yields an Accuracy of 0.987, F1-score of 0.958, and IoU of 0.920, demonstrating the robustness and generalization capability of the proposed method. [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=193435599 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/rs18081120 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 22 StartPage: 1120 Subjects: – SubjectFull: Seamounts Type: general – SubjectFull: Bathymetry Type: general – SubjectFull: Artificial neural networks Type: general – SubjectFull: Convolutional neural networks Type: general – SubjectFull: Oceanographic maps Type: general – SubjectFull: Remote sensing Type: general – SubjectFull: Geomorphology Type: general Titles: – TitleFull: RSCU-Net: A Spatial–Channel Reconstruction U-Net for Seamount Segmentation Using GEBCO Bathymetry. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Lin, Faran – PersonEntity: Name: NameFull: Guan, Qingsheng – PersonEntity: Name: NameFull: Zhang, Tao – PersonEntity: Name: NameFull: Liu, Hongqin IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 04 Text: Apr2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 20724292 Numbering: – Type: volume Value: 18 – Type: issue Value: 8 Titles: – TitleFull: Remote Sensing Type: main |
| ResultId | 1 |
