Semantic segmentation of glaciological features across multiple remote sensing platforms with the Segment Anything Model (SAM)
Semantic segmentation is a critical part of observation-driven research in glaciology. Using remote sensing to quantify how features change (e.g. glacier termini, supraglacial lakes, icebergs, crevasses) is particularly important in polar regions, where glaciological features may be spatially small...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Cambridge University Press
2024-01-01
|
| Series: | Journal of Glaciology |
| Subjects: | |
| Online Access: | https://www.cambridge.org/core/product/identifier/S0022143023000953/type/journal_article |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526524160770048 |
|---|---|
| author | Siddharth Shankar Leigh A. Stearns C. J. van der Veen |
| author_facet | Siddharth Shankar Leigh A. Stearns C. J. van der Veen |
| author_sort | Siddharth Shankar |
| collection | DOAJ |
| description | Semantic segmentation is a critical part of observation-driven research in glaciology. Using remote sensing to quantify how features change (e.g. glacier termini, supraglacial lakes, icebergs, crevasses) is particularly important in polar regions, where glaciological features may be spatially small but reflect important shifts in boundary conditions. In this study, we assess the utility of the Segment Anything Model (SAM), released by Meta AI Research, for cryosphere research. SAM is a foundational AI model that generates segmentation masks without additional training data. This is highly beneficial in polar science because pre-existing training data rarely exist. Widely-used conventional deep learning models such as UNet require tens of thousands of training labels to perform effectively. We show that the Segment Anything Model performs well for different features (icebergs, glacier termini, supra-glacial lakes, crevasses), in different environmental settings (open water, mélange, and sea ice), with different sensors (Sentinel-1, Sentinel-2, Planet, timelapse photographs) and different spatial resolutions. Due to the performance, versatility, and cross-platform adaptability of SAM, we conclude that it is a powerful and robust model for cryosphere research. |
| format | Article |
| id | doaj-art-c61a8d7cbbc2436e8c242bab2832f368 |
| institution | Kabale University |
| issn | 0022-1430 1727-5652 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Cambridge University Press |
| record_format | Article |
| series | Journal of Glaciology |
| spelling | doaj-art-c61a8d7cbbc2436e8c242bab2832f3682025-01-16T21:48:07ZengCambridge University PressJournal of Glaciology0022-14301727-56522024-01-017010.1017/jog.2023.95Semantic segmentation of glaciological features across multiple remote sensing platforms with the Segment Anything Model (SAM)Siddharth Shankar0https://orcid.org/0000-0001-5977-2898Leigh A. Stearns1C. J. van der Veen2Center for Remote Sensing and Integrated Systems, The University of Kansas, Lawrence, KS, USACenter for Remote Sensing and Integrated Systems, The University of Kansas, Lawrence, KS, USA Department of Geology, The University of Kansas, Lawrence, KS, USADepartment of Geography & Atmospheric Science, The University of Kansas, Lawrence, KS, USASemantic segmentation is a critical part of observation-driven research in glaciology. Using remote sensing to quantify how features change (e.g. glacier termini, supraglacial lakes, icebergs, crevasses) is particularly important in polar regions, where glaciological features may be spatially small but reflect important shifts in boundary conditions. In this study, we assess the utility of the Segment Anything Model (SAM), released by Meta AI Research, for cryosphere research. SAM is a foundational AI model that generates segmentation masks without additional training data. This is highly beneficial in polar science because pre-existing training data rarely exist. Widely-used conventional deep learning models such as UNet require tens of thousands of training labels to perform effectively. We show that the Segment Anything Model performs well for different features (icebergs, glacier termini, supra-glacial lakes, crevasses), in different environmental settings (open water, mélange, and sea ice), with different sensors (Sentinel-1, Sentinel-2, Planet, timelapse photographs) and different spatial resolutions. Due to the performance, versatility, and cross-platform adaptability of SAM, we conclude that it is a powerful and robust model for cryosphere research.https://www.cambridge.org/core/product/identifier/S0022143023000953/type/journal_articleCrevassesglacier mappingiceberg calvingremote sensingsea ice |
| spellingShingle | Siddharth Shankar Leigh A. Stearns C. J. van der Veen Semantic segmentation of glaciological features across multiple remote sensing platforms with the Segment Anything Model (SAM) Journal of Glaciology Crevasses glacier mapping iceberg calving remote sensing sea ice |
| title | Semantic segmentation of glaciological features across multiple remote sensing platforms with the Segment Anything Model (SAM) |
| title_full | Semantic segmentation of glaciological features across multiple remote sensing platforms with the Segment Anything Model (SAM) |
| title_fullStr | Semantic segmentation of glaciological features across multiple remote sensing platforms with the Segment Anything Model (SAM) |
| title_full_unstemmed | Semantic segmentation of glaciological features across multiple remote sensing platforms with the Segment Anything Model (SAM) |
| title_short | Semantic segmentation of glaciological features across multiple remote sensing platforms with the Segment Anything Model (SAM) |
| title_sort | semantic segmentation of glaciological features across multiple remote sensing platforms with the segment anything model sam |
| topic | Crevasses glacier mapping iceberg calving remote sensing sea ice |
| url | https://www.cambridge.org/core/product/identifier/S0022143023000953/type/journal_article |
| work_keys_str_mv | AT siddharthshankar semanticsegmentationofglaciologicalfeaturesacrossmultipleremotesensingplatformswiththesegmentanythingmodelsam AT leighastearns semanticsegmentationofglaciologicalfeaturesacrossmultipleremotesensingplatformswiththesegmentanythingmodelsam AT cjvanderveen semanticsegmentationofglaciologicalfeaturesacrossmultipleremotesensingplatformswiththesegmentanythingmodelsam |