Application of Deep Learning in Glacier Boundary Extraction: A Case Study of the Tomur Peak Region, Tianshan, Xinjiang
Abstract
1. Introduction
2. Study Area and Data
2.1. Overview of the Study Area
2.2. Data Sources
2.2.1. Satellite Data
2.2.2. Reference Data
3. Materials and Methods
3.1. Data Preprocessing
3.2. Glacier Boundary Extraction Method
3.2.1. Deeplabv3+ Model
3.2.2. Accuracy Evaluation Method
4. Results
4.1. Glacier Boundary Extraction Classification Experiment
4.1.1. Comparison of Classification Results with Different Band Combinations
4.1.2. Comparison of Model Classification Results
5. Discussion
5.1. Dynamic Change Monitoring and Analysis
5.2. Error Analysis and Model Sensitivity
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Bolch, T.; Kulkarni, A.; Kääb, A.; Huggel, C.; Paul, F.; Cogley, J.G.; Stoffel, M. The state and fate of Himalayan glaciers. Science 2012, 336, 310–314. [Google Scholar] [CrossRef] [PubMed]
- Cao, B.; Guan, W.; Li, K.; Wen, Z.; Han, H.; Pan, B. Area and Mass Changes of Glaciers in the West Kunlun Mountains Based on the Analysis of Multi-Temporal Remote Sensing Images and DEMs from 1970 to 2018. Remote Sens. 2020, 12, 2632. [Google Scholar] [CrossRef]
- Shean, D.E.; Bhushan, S.; Montesano, P.; Rounce, D.R.; Arendt, A.; Osmanoglu, B. A systematic, regional assessment of high mountain Asia glacier mass balance. Front. Earth Sci. 2020, 7, 363. [Google Scholar] [CrossRef]
- Yang, J.; Li, M.; Yang, S.; Tan, C. Vulnerability of the Glaciers to Climate Change in China:Current Situation and Evaluation. J. Glaciol. Geocryol. 2013, 35, 1077–1087. (In Chinese) [Google Scholar] [CrossRef]
- Xing, W.; Li, Z.; Zhang, H.; Zhang, M.; Liang, P.; Mou, J. Spatial-temporal variation of glacier resources in Chinese Tianshan Mountains since 1959. Acta Geogr. Sin. 2017, 72, 1594–1605. [Google Scholar] [CrossRef]
- Liu, S.; Yao, X.; Guo, W.; Xu, J.; Shangguan, D.; Wei, J.; Bao, W.; Wu, L. The Contemporary Glaciers in China Based on the Second Chinese Glacier Inventory. Acta Geogr. Sin. 2015, 70, 3–16. [Google Scholar] [CrossRef]
- Singh, S.; Tiwari, R.K.; Sood, V.; Kaur, R.; Prashar, S. The Legacy of Scatterometers: Review of Applications and Perspective. IEEE Geosci. Remote Sens. Mag. 2022, 10, 39–65. [Google Scholar] [CrossRef]
- Wang, S.; Zhang, M.; Li, Z.; Wang, F.; Li, H.; Li, Y.; Huang, X. Response of Glacier Area Variation to Climate Change in the Chinese Tianshan Mountains in the Past 50 Years. Acta Geogr. Sin. 2011, 66, 38–46. [Google Scholar] [CrossRef]
- Shen, Y.; Su, H.; Wang, G.; Mao, W.; Wang, S.; Han, P.; Wang, N.; Li, Z. The Responses of Glaciers and Snow Cover to Climate Change in Xinjiang (I): Hydrological Effects. J. Glaciol. Geocryol. 2013, 35, 513–527. [Google Scholar] [CrossRef]
- Shen, Y.; Su, H.; Wang, G.; Mao, W.; Wang, S.; Han, P.; Wang, N.; Li, Z. The Responses of Glaciers and Snow Cover to Climate Change in Xinjiang (II): Hazards Effects. J. Glaciol. Geocryol. 2013, 35, 1355–1370. [Google Scholar] [CrossRef]
- Zhang, M. Extracting the Temperate Glacier Information in Mount Namjagbarwa, Tibet Autonomous Region, Based on ETM+ Image. J. Glaciol. Geocryol. 2005, 27, 226–232. (In Chinese) [Google Scholar] [CrossRef]
- Gao, J.; Yao, T.; Masson-Delmotte, V.; Steen-Larsen, H.C.; Wang, W. Collapsing Glaciers Threaten Asia’s Water Supplies. Nature 2019, 565, 19–21. [Google Scholar] [CrossRef] [PubMed]
- Jacob, T.; Wahr, J.; Pfeffer, W.T.; Swenson, S. Recent Contributions of Glaciers and Ice Caps to Sea Level Rise. Nature 2012, 482, 514–518. [Google Scholar] [CrossRef]
- Gao, K.; Kääb, A.; Leinss, S.; Gilbert, A.; Bühler, Y.; Gascoin, S.; Evans, S.G.; Yao, T. Massive Collapse of Two Glaciers in Western Tibet in 2016 After Surge-Like Instability. Nat. Geosci. 2018, 11, 114–120. [Google Scholar] [CrossRef]
- Zhou, Y.; Li, X.; Zheng, D.; Li, Z.; An, B.; Wang, Y.; Jiang, D.; Su, J.; Cao, B. The Joint Driving Effects of Climate and Weather Changes Caused the Chamoli Glacier-Rock Avalanche in the High Altitudes of the India Himalaya. Sci. China Earth Sci. 2021, 64, 1909–1921. [Google Scholar] [CrossRef]
- Veh, G.; Korup, O.; von Specht, S.; Roessner, S.; Walz, A. Unchanged Frequency of Moraine-Dammed Glacial Lake Outburst Floods in the Himalaya. Nat. Clim. Change 2019, 9, 379–383. [Google Scholar] [CrossRef]
- Zhang, C.; Yue, P.; Tapete, D.; Shangguan, B.; Wang, M.; Wu, Z. A Multi-Level Context-Guided Classification Method with Object-Based Convolutional Neural Network for Land Cover Classification Using Very High Resolution Remote Sensing Images. Int. J. Appl. Earth Obs. Geoinf. 2020, 88, 102086. [Google Scholar] [CrossRef]
- Gu, H.; Han, Y.; Yang, Y.; Li, H.; Liu, Z.; Soergel, U.; Blaschke, T.; Cui, S. An Efficient Parallel Multi-Scale Segmentation Method for Remote Sensing Imagery. Remote Sens. 2018, 10, 590. [Google Scholar] [CrossRef]
- Zhou, W.; Xu, M.; Han, H. Spatial Distribution and Variation in Debris Cover and Flow Velocities of Glaciers during 1989–2022 in Tomur Peak Region, Tianshan Mountains. Remote Sens. 2024, 16, 2587. [Google Scholar] [CrossRef]
- Paul, F. Evaluation of different methods for glacier mapping using Landsat TM. EARSeL eProc. 2000, 1, 239–245. [Google Scholar]
- Bhambri, R.; Bolch, T.; Chaujar, R.K.; Kulshreshtha, S.C. Glacier changes in the Garhwal Himalaya, India, from 1968 to 2006 based on remote sensing. J. Glaciol. 2011, 57, 543–556. [Google Scholar] [CrossRef]
- Paul, F.; Kääb, A.; Haeberli, W. Recent glacier changes in the Alps observed by satellite: Consequences for future monitoring strategies. Glob. Planet. Change 2007, 56, 111–122. [Google Scholar] [CrossRef]
- Chand, P.; Sharma, M.C. Glacier changes in the Ravi basin, North-Western Himalaya (India) during the last four decades (1971–2010/13). Glob. Planet. Change 2015, 135, 133–147. [Google Scholar] [CrossRef]
- Shelhamer, E.; Long, J.; Darrell, T. Fully Convolutional Networks for Semantic Segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 2017, 39, 640–651. [Google Scholar] [CrossRef]
- Mohajerani, Y.; Wood, M.; Velicogna, I.; Rignot, E. Detection of Glacier Calving Margins with Convolutional Neural Networks: A Case Study. Remote Sens. 2019, 11, 74. [Google Scholar] [CrossRef]
- Davari, A.; Baller, C.; Seehaus, T.; Braun, M.; Maier, A.; Christlein, V. Pixelwise Distance Regression for Glacier Calving Front Detection and Segmentation. IEEE Trans. Geosci. Remote Sens. 2022, 60, 5224610. [Google Scholar] [CrossRef]
- Xie, Z.; Haritashya, U.K.; Asari, V.K.; Young, B.W.; Bishop, M.P.; Kargel, J.S. GlacierNet: A Deep-Learning Approach for Debris-Covered Glacier Mapping. IEEE Access 2020, 8, 83495–83510. [Google Scholar] [CrossRef]
- Wang, Z.; Wang, Z.; You, S.; Lei, F.; Cao, L.; Yang, K. Landsat Image Glacier Extraction Based on Context Semantic Segmentation Network. Acta Geod. Cartogr. Sin. 2020, 49, 1575–1582. (In Chinese) [Google Scholar] [CrossRef]
- Zhang, D.; Fan, H.; Kang, B.; Gao, J.; Li, T. Glacier Remote Sensing Image Detection Method under Complex Background Based on Improved U-Net Network. J. Appl. Basic Eng. Sci. 2022, 4, 806–818. (In Chinese) [Google Scholar] [CrossRef]
- Zhou, Y.; Wang, Y.; Zhou, W. Monitoring Glacier Area Change in Tianshan Mountains Based on Remote Sensing Images. Min. Surv. 2012, 3, 21–25. (In Chinese) [Google Scholar] [CrossRef]
- Lei, S.; Fang, L.; Li, C.; Yang, M. Improved Algorithm for Extracting Debris-Covered Glacier Regions in Optical Satellite Images. Comput. Eng. 2025, 51, 269–277. [Google Scholar] [CrossRef]
- Chen, Y.; Ji, X. Comparative Study of Glacier Identification Methods Based on Landsat 8 OLI Images. Front. Earth Sci. 2017, 7, 812–818. (In Chinese) [Google Scholar] [CrossRef]
- Herreid, S.; Pellicciotti, F. The State of Rock Debris Covering Earth’s Glaciers. Nat. Geosci. 2020, 13, 621–627. [Google Scholar] [CrossRef]
- Chen, G.; Zhang, X.; Wang, Q.; Dai, F.; Gong, Y.; Zhu, K. Symmetrical Dense-Shortcut Deep Fully Convolutional Networks for Semantic Segmentation of Very-High-Resolution Remote Sensing Images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2018, 11, 1633–1644. [Google Scholar] [CrossRef]
- Pereira, T.D.; Tabris, N.; Matsliah, A.; Turner, D.M.; Li, J.; Ravindranath, S.; Papadoyannis, E.S.; Normand, E.; Deutsch, D.S.; Wang, Z.Y.; et al. SLEAP: A Deep Learning System for Multi-Animal Pose Tracking. Nat. Methods 2022, 19, 486–495. [Google Scholar] [CrossRef]
- Emek Soylu, B.; Guzel, M.S.; Bostanci, G.E.; Ekinci, F.; Asuroglu, T.; Acici, K. Deep-Learning-Based Approaches for Semantic Segmentation of Natural Scene Images: A Review. Electronics 2023, 12, 2730. [Google Scholar] [CrossRef]
- Rybczak, M.; Kozakiewicz, K. Deep Machine Learning of MobileNet, Efficient, and Inception Models. Algorithms. 2024, 17, 96. [Google Scholar] [CrossRef]
- Mo, L.; Fan, Y.; Wang, G.; Yi, X.; Wu, X.; Wu, P. DeepMDSCBA: An Improved Semantic Segmentation Model Based on DeepLabV3+ for Apple Images. Foods. 2022, 11, 3999. [Google Scholar] [CrossRef]
- Wang, Y.; Yang, L.; Liu, X.; Yan, P. An Improved Semantic Segmentation Algorithm for High-Resolution Remote Sensing Images Based on DeepLabv3+. Sci. Rep. 2024, 14, 9716. [Google Scholar] [CrossRef]
- Deng, X.; Liu, Q.; Deng, Y.; Mahadevan, S. An Improved Method to Construct Basic Probability Assignment Based on the Confusion Matrix for Classification Problem. Inf. Sci. 2016, 340, 250–261. [Google Scholar] [CrossRef]
- Chicco, D.; Jurman, G. The Advantages of the Matthews Correlation Coefficient (MCC) over F1 Score and Accuracy in Binary Classification Evaluation. BMC Genom. 2020, 21, 6. [Google Scholar] [CrossRef] [PubMed]
- Rezatofighi, H.; Tsoi, N.; Gwak, J.; Sadeghian, A.; Reid, I.; Savarese, S. Generalized Intersection over Union: A Metric and a Loss for Bounding Box Regression. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 658–666. [Google Scholar]
- Chen, L.C.; Papandreou, G.; Kokkinos, I.; Murphy, K.; Yuille, A.L. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 2018, 40, 834–848. [Google Scholar] [CrossRef] [PubMed]
- Zhou, S.; Yao, X.; Zhang, D.; Zhang, Y.; Liu, S.; Min, Y. Remote Sensing Monitoring of Advancing and Surging Glaciers in the Tien Shan, 1990–2019. Remote Sens. 2021, 13, 1973. [Google Scholar] [CrossRef]
- Yang, S.; Wang, F.; Xie, Y.; Zhao, W.; Bai, C.; Liu, J.; Xu, C. Delineation Evaluation and Variation of Debris-Covered Glaciers Based on the Multi-Source Remote Sensing Images, Take Glaciers in the Eastern Tomur Peak Region for Example. Remote Sens. 2023, 15, 2575. [Google Scholar] [CrossRef]
- He, X.; Liu, B.; Feng, Z. Glacier Variations in Response to Climate Change in the Karlik Mountain from 1990 to 2020. Remote Sens. Technol. Appl. 2024, 39, 1373–1382. (In Chinese) [Google Scholar] [CrossRef]
Path/Row | Date | LANDSAT_SCENE_ID | Sensor | Cloud Cover (%) |
---|---|---|---|---|
147-031 | 22 August 1989 | LT51470311989234ISP00 | TM | 3 |
147-031 | 6 June 1990 | LT51470311990157ISP00 | TM | 3 |
147-031 | 17 August 1993 | LT51470311993229ISP00 | TM | 17 |
147-031 | 9 August 1996 | LT51470311996222ISP00 | TM | 3 |
147-031 | 9 September 1997 | LT51470311997272ISP00 | TM | 4 |
147-031 | 2 October 1998 | LT51470311998275BIK00 | TM | 4 |
147-031 | 26 August 1999 | LE71470311999238SGS00 | ETM+ | 10 |
147-031 | 5 October 2002 | LE71470312002278SGS00 | ETM+ | 2 |
147-031 | 20 July 2003 | LE71470312003201ASN01 | ETM+ | 9 |
147-031 | 23 June 2005 | LE71470312005174ASN00 | ETM+ | 6 |
147-031 | 6 September 2006 | LT51470312006249IKR00 | TM | 6 |
147-031 | 24 August 2007 | LT51470312007236IKR00 | TM | 10 |
147-031 | 10 August 2008 | LT51470312008223KHC01 | TM | 10 |
147-031 | 29 August 2012 | LE71470312012242PFS00 | ETM+ | 4 |
147-031 | 31 July 2013 | LE71470312013212PFS00 | ETM+ | 2 |
147-031 | 28 September 2017 | LE71470312017271NPA00 | ETM+ | 4 |
147-031 | 7 September 2021 | LE71470312021250NPA00 | ETM+ | 2 |
147-031 | 19 August 2023 | LE71470312023231NPA00 | ETM+ | 4 |
Band Combinations | MIoU | F1 (%) | Precision (%) | Recall (%) |
---|---|---|---|---|
543 | 79.06 | 87.58 | 88.04 | 87.12 |
542 | 78.98 | 87.54 | 87.74 | 87.34 |
541 | 75.93 | 84.28 | 81.68 | 87.04 |
145 | 78.55 | 87.32 | 89.05 | 85.66 |
245 | 79.08 | 87.66 | 89.44 | 85.95 |
345 | 79.45 | 87.82 | 88.07 | 87.61 |
Model | MIoU | F1 (%) | Precision (%) | Recall (%) |
---|---|---|---|---|
U-Net | 73.56 | 83.32 | 81.56 | 85.14 |
PSPNet+ (MobileNet) | 71.39 | 81.42 | 83.20 | 79.72 |
HRNet | 70.97 | 80.28 | 78.57 | 82.05 |
SegFormer | 75.31 | 84.36 | 84.57 | 84.17 |
DeepLabv3+ (MobileNet) | 76.91 | 86.42 | 90.44 | 82.75 |
Feature Type | Indices | Semantic Segmentation Models | ||||
---|---|---|---|---|---|---|
U-Net | DeepLabv3+ | PSPNet | HRNet | SegFormer | ||
IoU | 0.80 | 0.86 | 0.80 | 0.82 | 0.84 | |
Precision (%) | 88 | 92 | 91 | 89 | 85 | |
pure glacier | Recall (%) | 90 | 93 | 875 | 92 | 91 |
F1 | 0.89 | 0.92 | 0.89 | 0.90 | 0.88 | |
debris-covered | IoU | 0.73 | 0.76 | 0.70 | 0.73 | 0.76 |
Precision (%) | 82 | 86 | 84 | 82 | 91 | |
Recall (%) | 87 | 87 | 82 | 87 | 88 | |
F1 | 0.85 | 0.86 | 0.83 | 0.84 | 0.89 | |
IoU | 0.44 | 0.48 | 0.39 | 0.31 | 0.44 | |
Precision (%) | 56 | 85 | 60 | 45 | 63 | |
glacier lake | Recall (%) | 68 | 52 | 52 | 51 | 59 |
F1 | 0.62 | 0.65 | 0.56 | 0.48 | 0.61 |
Feature Type | Area Change (km2) | Annual Change Rate (km2·a−1) | ||||
---|---|---|---|---|---|---|
1989–2002 | 2002–2012 | 2012–2023 | 1989–2002 | 2002–2012 | 2012–2023 | |
debris-covered | −12.05 | +24.31 | +47.46 | −1.08 | +2.43 | +4.31 |
pure glacier | −129.85 | −149.05 | −18.11 | −9.98 | −14.90 | −1.64 |
glacier lake | −0.617 | −0.18 | −2.69 | −0.05 | −0.02 | −0.24 |
Category | Pixel Count |
---|---|
Pure Glacier | 34,478,510 |
Debris-Covered | 4,274,948 |
Glacier Lake | 142,027 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, Y.; Han, F.; Zhou, M.; Hou, Y.; Wang, S. Application of Deep Learning in Glacier Boundary Extraction: A Case Study of the Tomur Peak Region, Tianshan, Xinjiang. Sustainability 2025, 17, 3678. https://doi.org/10.3390/su17083678
Zhang Y, Han F, Zhou M, Hou Y, Wang S. Application of Deep Learning in Glacier Boundary Extraction: A Case Study of the Tomur Peak Region, Tianshan, Xinjiang. Sustainability. 2025; 17(8):3678. https://doi.org/10.3390/su17083678
Chicago/Turabian StyleZhang, Yan, Feng Han, Mingfeng Zhou, Yichen Hou, and Song Wang. 2025. "Application of Deep Learning in Glacier Boundary Extraction: A Case Study of the Tomur Peak Region, Tianshan, Xinjiang" Sustainability 17, no. 8: 3678. https://doi.org/10.3390/su17083678
APA StyleZhang, Y., Han, F., Zhou, M., Hou, Y., & Wang, S. (2025). Application of Deep Learning in Glacier Boundary Extraction: A Case Study of the Tomur Peak Region, Tianshan, Xinjiang. Sustainability, 17(8), 3678. https://doi.org/10.3390/su17083678