Articles | Volume 16, issue 10
https://doi.org/10.5194/tc-16-4273-2022
https://doi.org/10.5194/tc-16-4273-2022
Research article
 | 
13 Oct 2022
Research article |  | 13 Oct 2022

Glacier extraction based on high-spatial-resolution remote-sensing images using a deep-learning approach with attention mechanism

Xinde Chu, Xiaojun Yao, Hongyu Duan, Cong Chen, Jing Li, and Wenlong Pang

Data sets

Glacier coverage data on the Tibetan Plateau in 2017 (TPG2017, Version1.0) Q. H. Ye https://doi.org/10.11888/Glacio.tpdc.270924

Model code and software

yiyou101/Attention-DeepLab-V3plus: A deep learning approach to extract the glacier outlines (v2.1) Xinde Chu https://doi.org/10.5281/zenodo.7132888

Download
Short summary
The available remote-sensing data are increasingly abundant, and the efficient and rapid acquisition of glacier boundaries based on these data is currently a frontier issue in glacier research. In this study, we designed a complete solution to automatically extract glacier outlines from the high-resolution images. Compared with other methods, our method achieves the best performance for glacier boundary extraction in parts of the Tanggula Mountains, Kunlun Mountains and Qilian Mountains.