Preprints
https://doi.org/10.5194/egusphere-2024-1732
https://doi.org/10.5194/egusphere-2024-1732
14 Jun 2024
 | 14 Jun 2024
Status: this preprint is open for discussion.

Physics-aware Machine Learning for Glacier Ice Thickness Estimation: A Case Study for Svalbard

Viola Steidl, Jonathan L. Bamber, and Xiao Xiang Zhu

Abstract. The ice thickness of the world’s glaciers is mostly unmeasured and physics-based models to reconstruct ice thickness can not 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 the experiments let us identify several challenges and opportunities that affect the model’s performance in a real-world setting.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Viola Steidl, Jonathan L. Bamber, and Xiao Xiang Zhu

Status: open (until 31 Jul 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Viola Steidl, Jonathan L. Bamber, and Xiao Xiang Zhu

Data sets

GlacierPINN: Case Study Svalbard Viola Steidl https://doi.org/10.5281/zenodo.11474955

Model code and software

Glacier_PINN Viola Steidl https://github.com/viola1593/glacier_pinn

Viola Steidl, Jonathan L. Bamber, and Xiao Xiang Zhu

Viewed

Total article views: 357 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
244 94 19 357 13 12
  • HTML: 244
  • PDF: 94
  • XML: 19
  • Total: 357
  • BibTeX: 13
  • EndNote: 12
Views and downloads (calculated since 14 Jun 2024)
Cumulative views and downloads (calculated since 14 Jun 2024)

Viewed (geographical distribution)

Total article views: 327 (including HTML, PDF, and XML) Thereof 327 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 24 Jul 2024
Download
Short summary
Glacier ice thickness is difficult to measure directly but is essential for glacier evolution modelling. In this work, we employ a novel approach combining physical knowledge and data-driven machine learning to estimate the ice thickness of multiple glaciers in Spitsbergen, Barentsøya, and Edgeøya in Svalbard. We identify challenges for the physics-aware machine learning model and opportunities for improving the accuracy and physical consistency that would also apply to other geophysical tasks.