Work

Physics-aware machine learning for glacier ice thickness estimation: a case study for Svalbard

Year: 2025

Type: article

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.

Source: The cryosphere

DOI: 10.5194/tc-19-645-2025

Authors: Viola Steidl, Jonathan L. Bamber, Xiao Xiang Zhu

Institutions: Technical University of Munich, University of Bristol, Munich Center for Machine Learning

Language: English

Topic: Cryospheric studies and observations

Subfield: Atmospheric Science

Field: Earth and Planetary Sciences

Domain: Physical Sciences

SDG: Climate action

Open Access status: gold

Estimated APC paid: $1,574