EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MOCA-Net: A Model for Automatic Segmentation of Retrogressive Thaw Slumps from Sentinel-2 Imagery Along the Qinghai–Tibet Engineering Corridor

Yijiang Li, Qiong Li iD, Guoxin Chen iD, Wenqi Li, Changyan Bao

Sensors · 21.05.2026 · 26 (10) · 3267

DOI: 10.3390/s26103267 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.05.2026. Verfasst von Yijiang Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Civil Engineering and Water Resources, Qinghai University, Xining 810016, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Special Project for Enhancing Scientific Research Capacity of Qinghai University, Major Science and Technology Projects of Qinghai Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retrogressive thaw slumps (RTSs) serve as key indicators of global climate change and also pose significant risks to critical infrastructure along the Qinghai–Tibet Engineering Corridor (QTEC). Accurate automatic segmentation of RTSs using Sentinel-2 imagery is of great value for climate change research and risk assessment, owing to the dataset’s ready availability and extensive spatiotemporal coverage. However, this segmentation task remains challenging due to the complex morphology and variable sizes of RTSs, as well as their low contrast and fuzzy boundaries against the surrounding landscape in medium-resolution satellite imagery. To deal with these challenges, this study proposes the Multi-Scale Object-aware Context Attention Network (MOCA-Net), which enhances the Swin Transformer backbone through two critical components: the Feature Enhancement Network and Enhanced Decoder. Evaluation metrics show that MOCA-Net outperforms seven mainstream baseline models, achieving a Mean Intersection over Union (mIoU) of 0.8609 and an RTS-class IoU of 0.7473. The qualitative visual evaluation further confirms MOCA-Net’s improved performance in delineating RTSs through more accurate morphologies and boundaries. Ablation studies confirm that each designed component contributes to the MOCA-Net’s segmentation performance, and their combination yields more balanced results. This model unlocks the capability of Sentinel-2 imagery for accurate RTS segmentation, making it promising for applications over large spatiotemporal extents.

Schlagwörter

Stichwörter der Autor:innen

MOCA-NetSentinel-2deep learningretrogressive thaw slumpsemantic segmentation

Autor:innen und Institutionen

  • School of Civil Engineering and Water Resources, Qinghai University, Xining 810016, China.
  • Key Laboratory of Water Ecology Remediation and Protection at Headwater Regions of Big Rivers, Ministry of Water Resources, Xining 810016, China.
  • Laboratory of Ecological Protection and High Quality Development in the Upper Yellow River, Qinghai University, Xining 810016, China.
  • School of Geological Engineering, Qinghai University, Xining 810016, China.
  • State Key Laboratory of Plateau Ecology and Agriculture, Qinghai University, Xining 810016, China.
  • Qinghai Remote Sensing Center for Natural Resources, Xining 810010, China.

ORCID-Profile: Qiong Li, Guoxin Chen

Förderung

  • Special Project for Enhancing Scientific Research Capacity of Qinghai University
  • Major Science and Technology Projects of Qinghai Province

Zitieren

APA

Li, Y., Li, Q., Chen, G., Li, W., & Bao, C. (2026). MOCA-Net: A Model for Automatic Segmentation of Retrogressive Thaw Slumps from Sentinel-2 Imagery Along the Qinghai–Tibet Engineering Corridor. Sensors, 26(10), 3267. https://doi.org/10.3390/s26103267

Vancouver

Li Y, Li Q, Chen G, Li W, Bao C. MOCA-Net: A Model for Automatic Segmentation of Retrogressive Thaw Slumps from Sentinel-2 Imagery Along the Qinghai–Tibet Engineering Corridor. Sensors. 2026;26(10):3267. doi:10.3390/s26103267

BibTeX
@article{Li2026,
  author = {Li, Yijiang and Li, Qiong and Chen, Guoxin and Li, Wenqi and Bao, Changyan},
  title = {MOCA-Net: A Model for Automatic Segmentation of Retrogressive Thaw Slumps from Sentinel-2 Imagery Along the Qinghai–Tibet Engineering Corridor},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {10},
  pages = {3267},
  doi = {10.3390/s26103267}
}
Kostenlos starten →