Regional Glacier Mapping and Change Analysis in the Gangshika Region of Qilian Mountain Based on Deep Learning and Satellite Data Time-Series

Time-series glacier change analysis that is closely linked to global climate patterns has drawn increasing attention. However, few studies focused on regional glacier mapping with high spatial resolution and accuracy. This study combined a lightweight DeeplabV3+ model and activation thres...

Full description

Saved in:
Bibliographic Details
Main Authors: Lihao Chen, Wei Xu, Zhen Cao, Jiaqi Zhang, Zhizhong Kang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10969556/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850265722856407040
author Lihao Chen
Wei Xu
Zhen Cao
Jiaqi Zhang
Zhizhong Kang
author_facet Lihao Chen
Wei Xu
Zhen Cao
Jiaqi Zhang
Zhizhong Kang
author_sort Lihao Chen
collection DOAJ
description Time-series glacier change analysis that is closely linked to global climate patterns has drawn increasing attention. However, few studies focused on regional glacier mapping with high spatial resolution and accuracy. This study combined a lightweight DeeplabV3&#x002B; model and activation threshold optimization strategy for regional glacier mapping and change analysis in the Gangshika region of Qilian Mountain, mainly using high-resolution satellite images from 2012 to 2023. For the extraction of glaciers with different scales, multiscale contextual information was represented through Atrous spatial pyramid pooling module. The predicted probability maps were first obtained. And the optimized activation thresholds were selected to determine which areas were glaciers. The accuracies of extracted glacier boundaries from 2012 to 2023 fluctuated between 82&#x0025; and 96&#x0025;, with an averaged value of 93&#x0025;. Considering that the quality of images in 2012&#x2013;2014 and corresponding glacier boundary accuracy were not very good, the change analysis was just conducted from 2015 to 2023. As of 2023, the Gangshika region hosts 45 glaciers, with a total area of 20.652 km<sup>2</sup> and a total perimeter of 148.8 km. From 2015 to 2023, they reduce by 9.2&#x0025; and 1.7&#x0025; respectively. Glaciers were predominantly concentrated in medium elevation zones (4200&#x2013;4500 m) with a proportion of 46.6&#x0025; and largest ablation rate of 1.68&#x0025; between 2021 and 2023. The thickness and ice reserves were calculated by an empirical formula. From 2015 to 2023, the Gangshika glaciers showed reduction rates in thickness and ice reserves by 1.15&#x0025; and 12.5&#x0025;, respectively.
format Article
id doaj-art-6639f76959664e4bae85582276521fbb
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-6639f76959664e4bae85582276521fbb2025-08-20T01:54:20ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118121031211510.1109/JSTARS.2025.356227310969556Regional Glacier Mapping and Change Analysis in the Gangshika Region of Qilian Mountain Based on Deep Learning and Satellite Data Time-SeriesLihao Chen0https://orcid.org/0009-0004-9138-3971Wei Xu1Zhen Cao2Jiaqi Zhang3Zhizhong Kang4https://orcid.org/0000-0002-9728-4702School of Land Science and Geomatics, China University of Geosciences, Beijing, ChinaQinghai Remote Sensing Center for Natural Resources, Xining, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin, ChinaNatural Resources Satellite Application Technology Center, Xinjiang Production and Construction Corps, Xinjiang, ChinaSchool of Land Science and Geomatics, China University of Geosciences, Beijing, ChinaTime-series glacier change analysis that is closely linked to global climate patterns has drawn increasing attention. However, few studies focused on regional glacier mapping with high spatial resolution and accuracy. This study combined a lightweight DeeplabV3&#x002B; model and activation threshold optimization strategy for regional glacier mapping and change analysis in the Gangshika region of Qilian Mountain, mainly using high-resolution satellite images from 2012 to 2023. For the extraction of glaciers with different scales, multiscale contextual information was represented through Atrous spatial pyramid pooling module. The predicted probability maps were first obtained. And the optimized activation thresholds were selected to determine which areas were glaciers. The accuracies of extracted glacier boundaries from 2012 to 2023 fluctuated between 82&#x0025; and 96&#x0025;, with an averaged value of 93&#x0025;. Considering that the quality of images in 2012&#x2013;2014 and corresponding glacier boundary accuracy were not very good, the change analysis was just conducted from 2015 to 2023. As of 2023, the Gangshika region hosts 45 glaciers, with a total area of 20.652 km<sup>2</sup> and a total perimeter of 148.8 km. From 2015 to 2023, they reduce by 9.2&#x0025; and 1.7&#x0025; respectively. Glaciers were predominantly concentrated in medium elevation zones (4200&#x2013;4500 m) with a proportion of 46.6&#x0025; and largest ablation rate of 1.68&#x0025; between 2021 and 2023. The thickness and ice reserves were calculated by an empirical formula. From 2015 to 2023, the Gangshika glaciers showed reduction rates in thickness and ice reserves by 1.15&#x0025; and 12.5&#x0025;, respectively.https://ieeexplore.ieee.org/document/10969556/Change analysisdeep learningglacier mappingqilian mountainremote sensingtime-series
spellingShingle Lihao Chen
Wei Xu
Zhen Cao
Jiaqi Zhang
Zhizhong Kang
Regional Glacier Mapping and Change Analysis in the Gangshika Region of Qilian Mountain Based on Deep Learning and Satellite Data Time-Series
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Change analysis
deep learning
glacier mapping
qilian mountain
remote sensing
time-series
title Regional Glacier Mapping and Change Analysis in the Gangshika Region of Qilian Mountain Based on Deep Learning and Satellite Data Time-Series
title_full Regional Glacier Mapping and Change Analysis in the Gangshika Region of Qilian Mountain Based on Deep Learning and Satellite Data Time-Series
title_fullStr Regional Glacier Mapping and Change Analysis in the Gangshika Region of Qilian Mountain Based on Deep Learning and Satellite Data Time-Series
title_full_unstemmed Regional Glacier Mapping and Change Analysis in the Gangshika Region of Qilian Mountain Based on Deep Learning and Satellite Data Time-Series
title_short Regional Glacier Mapping and Change Analysis in the Gangshika Region of Qilian Mountain Based on Deep Learning and Satellite Data Time-Series
title_sort regional glacier mapping and change analysis in the gangshika region of qilian mountain based on deep learning and satellite data time series
topic Change analysis
deep learning
glacier mapping
qilian mountain
remote sensing
time-series
url https://ieeexplore.ieee.org/document/10969556/
work_keys_str_mv AT lihaochen regionalglaciermappingandchangeanalysisinthegangshikaregionofqilianmountainbasedondeeplearningandsatellitedatatimeseries
AT weixu regionalglaciermappingandchangeanalysisinthegangshikaregionofqilianmountainbasedondeeplearningandsatellitedatatimeseries
AT zhencao regionalglaciermappingandchangeanalysisinthegangshikaregionofqilianmountainbasedondeeplearningandsatellitedatatimeseries
AT jiaqizhang regionalglaciermappingandchangeanalysisinthegangshikaregionofqilianmountainbasedondeeplearningandsatellitedatatimeseries
AT zhizhongkang regionalglaciermappingandchangeanalysisinthegangshikaregionofqilianmountainbasedondeeplearningandsatellitedatatimeseries