Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard
<p>The ice thickness of the world's glaciers is mostly unmeasured, and physics-based models to reconstruct ice thickness cannot always deliver accurate estimates. In this study, we use deep learning paired with physical knowledge to generate ice thickness estimates for all glaciers of Spi...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-02-01
|
| Series: | The Cryosphere |
| Online Access: | https://tc.copernicus.org/articles/19/645/2025/tc-19-645-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206617471188992 |
|---|---|
| author | V. Steidl J. L. Bamber J. L. Bamber X. X. Zhu X. X. Zhu |
| author_facet | V. Steidl J. L. Bamber J. L. Bamber X. X. Zhu X. X. Zhu |
| author_sort | V. Steidl |
| collection | DOAJ |
| description | <p>The ice thickness of the world's glaciers is mostly unmeasured, and physics-based models to reconstruct ice thickness cannot always deliver accurate estimates. In this study, we use deep learning paired with physical knowledge to generate ice thickness estimates for all glaciers of Spitsbergen, Barentsøya, and Edgeøya in Svalbard. We incorporate mass conservation and other physically derived conditions into a neural network to predict plausible ice thicknesses even for glaciers without any in situ ice thickness measurements. With a glacier-wise cross-validation scheme, we evaluate the performance of the physics-informed neural network. The results of these proof-of-concept experiments let us identify several challenges and opportunities that affect the model's performance in a real-world setting.</p> |
| format | Article |
| id | doaj-art-40ff9f8d442f4b9788ab099f8b523381 |
| institution | Kabale University |
| issn | 1994-0416 1994-0424 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The Cryosphere |
| spelling | doaj-art-40ff9f8d442f4b9788ab099f8b5233812025-02-07T07:59:13ZengCopernicus PublicationsThe Cryosphere1994-04161994-04242025-02-011964566110.5194/tc-19-645-2025Physics-aware machine learning for glacier ice thickness estimation: a case study for SvalbardV. Steidl0J. L. Bamber1J. L. Bamber2X. X. Zhu3X. X. Zhu4Chair of Data Science in Earth Observation, Department of Aerospace and Geodesy, Technical University of Munich, 80333 Munich, GermanyChair of Data Science in Earth Observation, Department of Aerospace and Geodesy, Technical University of Munich, 80333 Munich, GermanyBristol Glaciology Centre, School of Geographical Sciences, University of Bristol, Bristol, BS8 1SS, UKChair of Data Science in Earth Observation, Department of Aerospace and Geodesy, Technical University of Munich, 80333 Munich, GermanyMunich Center for Machine Learning, 80538 Munich, Germany<p>The ice thickness of the world's glaciers is mostly unmeasured, and physics-based models to reconstruct ice thickness cannot always deliver accurate estimates. In this study, we use deep learning paired with physical knowledge to generate ice thickness estimates for all glaciers of Spitsbergen, Barentsøya, and Edgeøya in Svalbard. We incorporate mass conservation and other physically derived conditions into a neural network to predict plausible ice thicknesses even for glaciers without any in situ ice thickness measurements. With a glacier-wise cross-validation scheme, we evaluate the performance of the physics-informed neural network. The results of these proof-of-concept experiments let us identify several challenges and opportunities that affect the model's performance in a real-world setting.</p>https://tc.copernicus.org/articles/19/645/2025/tc-19-645-2025.pdf |
| spellingShingle | V. Steidl J. L. Bamber J. L. Bamber X. X. Zhu X. X. Zhu Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard The Cryosphere |
| title | Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard |
| title_full | Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard |
| title_fullStr | Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard |
| title_full_unstemmed | Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard |
| title_short | Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard |
| title_sort | physics aware machine learning for glacier ice thickness estimation a case study for svalbard |
| url | https://tc.copernicus.org/articles/19/645/2025/tc-19-645-2025.pdf |
| work_keys_str_mv | AT vsteidl physicsawaremachinelearningforglaciericethicknessestimationacasestudyforsvalbard AT jlbamber physicsawaremachinelearningforglaciericethicknessestimationacasestudyforsvalbard AT jlbamber physicsawaremachinelearningforglaciericethicknessestimationacasestudyforsvalbard AT xxzhu physicsawaremachinelearningforglaciericethicknessestimationacasestudyforsvalbard AT xxzhu physicsawaremachinelearningforglaciericethicknessestimationacasestudyforsvalbard |