Mapping Debris-Covered Glaciers Using High-Resolution Imagery (GF-2) and Deep Learning Algorithms

被引:0
|
作者
Yang, Xin [1 ,2 ]
Xie, Fuming [1 ,2 ]
Liu, Shiyin [1 ,2 ,3 ]
Zhu, Yu [1 ,2 ]
Fan, Jinghui [4 ]
Zhao, Hongli [4 ]
Fu, Yuying [4 ]
Duan, Yunpeng [1 ,2 ]
Fu, Rong [1 ,2 ]
Guo, Siyang [1 ,2 ]
机构
[1] Yunnan Prov Key Lab Int Rivers & Transboundary Eco, Kunming 650500, Peoples R China
[2] Yunnan Univ, Inst Int Rivers & Ecosecur, Kunming 650500, Peoples R China
[3] Yunnan Int Joint Lab China Laos Bangladesh Myanmar, Kunming 650500, Peoples R China
[4] China Aero Geophys Survey & Remote Sensing Ctr Nat, Beijing 100083, Peoples R China
基金
中国国家自然科学基金;
关键词
supraglacial debris; deep learning; GF-2; imagery; LAND-SURFACE TEMPERATURE; CLASSIFICATION; GREENLAND; KARAKORAM; INVENTORY; ACCURACY; SAR;
D O I
10.3390/rs16122062
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Glacier inventories are fundamental in understanding glacier dynamics and glacier-related environmental processes. High-resolution mapping of glacier outlines is lacking, although high-resolution satellite images have become available in recent decades. Challenges in development of glacier inventories have always included accurate delineation of boundaries of debris-covered glaciers, which is particularly true for high-resolution satellite images due to their limited spectral bands. To address this issue, we introduced an automated, high-precision method in this study for mapping debris-covered glaciers based on 1 m resolution Gaofen-2 (GF-2) imagery. By integrating GF-2 reflectance, topographic features, and land surface temperature (LST), we used an attention mechanism to improve the performance of several deep learning network models (the U-Net network, a fully convolutional neural network (FCNN), and DeepLabV3+). The trained models were then applied to map the outlines of debris-covered glaciers, at 1 m resolution, in the central Karakoram regions. The results indicated that the U-Net model enhanced with the Convolutional Block Attention Module (CBAM) outperforms other deep learning models (e.g., FCNN, DeepLabV3+, and U-Net model without CBAM) in terms of precision for supraglacial debris identification. On the testing dataset, the CBAM-enhanced U-Net model achieved notable performance metrics, with its accuracy, F1 score, mean intersection over union (MIoU), and kappa coefficient reaching 0.93, 0.74, 0.79, and 0.88. When applied at the regional scale, the model even exhibits heightened precision (accuracies = 0.94, F1 = 0.94, MIoU = 0.86, kappa = 0.91) in mapping debris-covered glaciers. The experimental glacier outlines were accurately extracted, enabling the distinction of supraglacial debris, clean ice, and other features on glaciers in central Karakoram using this trained model. The results for our method revealed differences of 0.14% for bare ice and 10.36% against the manually interpreted glacier boundary for supraglacial debris. Comparison with previous glacier inventories revealed raised precisions of 8.74% and 4.78% in extracting clean ice and with supraglacial debris, respectively. Additionally, our model demonstrates exceptionally high exclusion for bare rock outside glaciers and could reduce the influence of non-glacial snow on glacier delineation, showing substantial promise in mapping debris-covered glaciers.
引用
收藏
页数:23
相关论文
共 50 条
  • [1] Mapping high-resolution mangrove forests in China using GF-2 imagery under the tide
    Xia, Qing
    Li, Jianghua
    Dai, Shuo
    Zhang, Han
    Xing, Xuemin
    [J]. National Remote Sensing Bulletin, 2023, 27 (06) : 6 - 19
  • [2] Novel Machine Learning Method Integrating Ensemble Learning and Deep Learning for Mapping Debris-Covered Glaciers
    Lu, Yijie
    Zhang, Zhen
    Shangguan, Donghui
    Yang, Junhua
    [J]. REMOTE SENSING, 2021, 13 (13)
  • [3] Machine-Learning Algorithms for Mapping Debris-Covered Glaciers: The Hunza Basin Case Study
    Khan, Aftab Ahmed
    Jamil, Akhtar
    Hussain, Dostdar
    Taj, Murtaza
    Jabeen, Gul
    Malik, Muhammad Kamran
    [J]. IEEE ACCESS, 2020, 8 : 12725 - 12734
  • [4] Mapping of Debris-Covered Glaciers Using Object-Based Machine Learning Technique
    Shikha Sharda
    Mohit Srivastava
    [J]. Journal of the Indian Society of Remote Sensing, 2024, 52 : 399 - 411
  • [5] Mapping of Debris-Covered Glaciers Using Object-Based Machine Learning Technique
    Sharda, Shikha
    Srivastava, Mohit
    [J]. JOURNAL OF THE INDIAN SOCIETY OF REMOTE SENSING, 2024, 52 (02) : 399 - 411
  • [6] Super-resolution for mapping the debris-covered glaciers, central Himalaya, India
    Shukla, Aparna
    Yousuf, Bisma
    Bindal, Ankit
    Arora, Manoj Kumar
    Jasrotia, Avtar Singh
    [J]. ADVANCES IN SPACE RESEARCH, 2022, 69 (08) : 3019 - 3031
  • [7] An integrated deep learning and object-based image analysis approach for mapping debris-covered glaciers
    Thomas, Daniel Jack
    Robson, Benjamin Aubrey
    Racoviteanu, Adina
    [J]. FRONTIERS IN REMOTE SENSING, 2023, 4
  • [8] Quantifying volume loss from ice cliffs on debris-covered glaciers using high-resolution terrestrial and aerial photogrammetry
    Brun, Fanny
    Buri, Pascal
    Miles, Evan S.
    Wagnon, Patrick
    Steiner, Jakob
    Berthier, Etienne
    Ragettli, Silvan
    Kraaijenbrink, Philip
    Immerzeel, Walter W.
    Pellicciotti, Francesca
    [J]. JOURNAL OF GLACIOLOGY, 2016, 62 (234) : 684 - 695
  • [9] A new band ratio technique for mapping debris-covered glaciers using Landsat imagery and a digital elevation model
    Alifu, Haireti
    Tateishi, Ryutaro
    Johnson, Brian
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2015, 36 (08) : 2063 - 2075
  • [10] Mapping ice cliffs on debris-covered glaciers using multispectral satellite images
    Kneib, M.
    Miles, E. S.
    Jola, S.
    Buri, P.
    Herreid, S.
    Bhattacharya, A.
    Watson, C. S.
    Bolch, T.
    Quincey, D.
    Pellicciotti, F.
    [J]. REMOTE SENSING OF ENVIRONMENT, 2021, 253