Preprints
https://doi.org/10.5194/egusphere-2025-3628
https://doi.org/10.5194/egusphere-2025-3628
07 Oct 2025
 | 07 Oct 2025
Status: this preprint is open for discussion and under review for The Cryosphere (TC).

Global Attention of Transformer Empowers Montane Periglacial Lake Identification

Jinhao Xu, Min Feng, Yijie Sui, Yanan Su, Xuefei Zhang, Qinglin Wu, Zhimin Hu, and Ruilin Wang

Abstract. Montane periglacial lakes, as sensitive indicators of cryospheric change, are undergoing rapid expansion under global warming. Investitating their evolving distribution is essential for monitoring climate understanding impacts and assessing associated geohazards. The complex topography and heterogeneous landscapes in high-mountain regions pose significant challenges for conventional methods, leading to the underdetection of small lakes, elevated false positive rates, and limited ability to discriminate between lake formation types. This study introduces a Vision Transformer (ViT)-based framework for montane periglacial lake identification, employing a two-step process of lake boundary segmentation and type classification. By leveraging ViT’s global attention mechanism, the framework captures long-range spatial and spectral relationships, enhancing contextual understanding of lakes and their surroundings. Compared to CNN-based models, the ViT-based approach achieved a mean intersection over union (MIoU) of 91.01 % for segmentation and an F1-score of 89.75 % for classification. It significantly improved detection of small lakes (as small as 0.0001 km2), reduced artifacts from shadows, snow, ice, and river fragments, and provided more accurate lake type classification. Applied to the Southeastern Tibetan Plateau Gorge Region, a region with high glacial lake density and outburst flood risks, the framework identified 3,266 lakes (1,708 glacial and 1,558 non-glacial), surpassing existing inventories in completeness and accuracy.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this paper. While Copernicus Publications makes every effort to include appropriate place names, the final responsibility lies with the authors. Views expressed in the text are those of the authors and do not necessarily reflect the views of the publisher.
Share
Jinhao Xu, Min Feng, Yijie Sui, Yanan Su, Xuefei Zhang, Qinglin Wu, Zhimin Hu, and Ruilin Wang

Status: open (until 18 Nov 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Jinhao Xu, Min Feng, Yijie Sui, Yanan Su, Xuefei Zhang, Qinglin Wu, Zhimin Hu, and Ruilin Wang
Jinhao Xu, Min Feng, Yijie Sui, Yanan Su, Xuefei Zhang, Qinglin Wu, Zhimin Hu, and Ruilin Wang
Metrics will be available soon.
Latest update: 07 Oct 2025
Download
Short summary
Montane periglacial lakes, key climate change indicators, are expanding rapidly but hard to map in complex terrain. Our AI framework, powered by Vision Transformer (ViT), significantly enhances lake detection. ViT's global image context analysis excels at identifying small lakes, minimizing errors from rugged landscapes. This approach delivers exceptional accuracy in mapping and classifying these critical environmental features, surpassing traditional methods.
Share