Geo-knowledge-informed Deep Learning for Auto-identification of Supraglacial Lakes on the Greenland Ice Sheet from Satellite Imagery
Authors: 
Chen Wei, Song Gao, Feng ZhangAuthors Info & Claims
Chen Wei, Song Gao, Feng ZhangAuthors Info & ClaimsArticle No.: 19, Pages 1 - 4
Abstract
Melting glaciers are indicators of global climate change. The formation and dynamics of supraglacial lakes on the Greenland's ice sheet, which appear during the summer melt season, are of particular interest due to their impact on ice dynamics. Detecting these lakes is essential, yet challenging. This paper presents a comprehensive geo-knowledge-informed deep leaning workflow for auto-identification of supraglacial lakes from Sentinel-2 satellite images. The U-Net deep neural network is employed for pixel-level segmentation, distinguishing lakes from other features. Post-processing techniques filter false positives and incorporate geographical knowledge to re-fine results. The experiment results demonstrate the superior performance of our proposed method with F1-score of 0.78. This research contributes to the understanding of supraglacial lake dynamics and the development of robust automated detection methods.
References
[1]
Mariel Dirscherl, Andreas J Dietz, Christof Kneisel, and Claudia Kuenzer. "A novel method for automated supraglacial lake mapping in Antarctica using Sentinel-1 SAR imagery and deep learning". In: Remote Sensing 13.2 (2021), p. 197.
[2]
Saurabh Kaushik, Tejpal Singh, Anshuman Bhardwaj, Pawan K Joshi, and Andreas J Dietz. "Automated Delineation of Supraglacial Debris Cover Using Deep Learning and Multisource Remote Sensing Data". In: Remote Sensing 14.6 (2022), p. 1352.
[3]
Mike MacFerrin, Horst Machguth, D van As, Charalampos Charalampidis, C Max Stevens, Achim Heilig, Baptiste Vandecrux, Peter L Langen, R Mottram, Xavier Fettweis, et al. "Rapid expansion of Greenland's low-permeability ice slabs". In: Nature 573.7774 (2019), pp. 403--407.
[4]
Paul Morin, Claire Porter, Michael Cloutier, Ian Howat, Myoung-Jong Noh, Michael Willis, Brian Bates, Cathleen Willamson, and Kennith Peterman. "ArcticDEM; a publically available, high resolution elevation model of the Arctic". In: Egu general assembly conference abstracts. 2016, EPSC2016--8396.
[5]
Olaf Ronneberger, Philipp Fischer, and Thomas Brox. "U-net: Convolutional networks for biomedical image segmentation". In: Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5--9, 2015, Proceedings, Part III 18. Springer. 2015, pp. 234--241.
[6]
Kang Yang and Laurence C Smith. "Supraglacial streams on the Greenland Ice Sheet delineated from combined spectral-shape information in high-resolution satellite imagery". In: IEEE Geoscience and Remote Sensing Letters 10.4 (2012), pp. 801--805.
Index Terms
- Geo-knowledge-informed Deep Learning for Auto-identification of Supraglacial Lakes on the Greenland Ice Sheet from Satellite Imagery
Recommendations
Exploring GeoAI Methods for Supraglacial Lake Mapping on Greenland Ice Sheet
SIGSPATIAL '23: Proceedings of the 31st ACM International Conference on Advances in Geographic Information SystemsThe ACM SIGSPATIAL Cup 2023 proposed the challenge to identify and map supraglacial lakes in Greenland in satellite imagery. The peculiarities of supraglacial lakes pose a hard problem for semantic segmentation and object detection tasks because the ...
Enhanced Mapping of Supraglacial Lakes Through Dual-attention Deep Neural Network
SIGSPATIAL '23: Proceedings of the 31st ACM International Conference on Advances in Geographic Information SystemsSupraglacial lakes in the Arctic undergo seasonal and glacial-activity-induced changes, providing profound insights into ice dynamics and climate changes in these sensitive regions. However, the morphological complexity of these lakes, compounded by the ...
A novel application of DUCK-Net for extracting supraglacial lakes in Greenland
SIGSPATIAL '23: Proceedings of the 31st ACM International Conference on Advances in Geographic Information SystemsThis paper presents a new application of the DUCK-Net convolutional neural network for image segmentation to identify supraglacial lakes on the Greenland ice sheet. The model presented was created as part of the 12th SIGSPATIAL Cup Competition and ...
Comments
Information & Contributors
Information
Published In
November 2023
686 pages
ISBN:9798400701689
DOI:10.1145/3589132
- General Chairs:
- Maria Luisa Damiani,
- Matthias Renz,
- Program Chairs:
- Ahmed Eldawy,
- Peer Kröger,
- Mario A Nascimento
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 22 December 2023
Check for updates
Author Tags
Qualifiers
- Short-paper
Conference
SIGSPATIAL '23
Sponsor:
SIGSPATIAL '23: 31st ACM International Conference on Advances in Geographic Information Systems
November 13 - 16, 2023
Hamburg, Germany
Acceptance Rates
Overall Acceptance Rate 220 of 1,116 submissions, 20%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 50Total Downloads
- Downloads (Last 12 months)50
- Downloads (Last 6 weeks)10
Reflects downloads up to 26 Sep 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in