The Cryosphere
The Cryosphere
TC
Articles | Volume 19, issue 2
Articles | Volume 19, issue 2
https://doi.org/10.5194/tc-19-805-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/tc-19-805-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 19, issue 2
Research article
 | 
21 Feb 2025
Research article |  | 21 Feb 2025

A minimal machine-learning glacier mass balance model

Marijn van der Meer, Harry Zekollari, Matthias Huss, Jordi Bolibar, Kamilla Hauknes Sjursen, and Daniel Farinotti

Viewed

Total article views: 3,701 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
3,006 426 269 3,701 61 119
  • HTML: 3,006
  • PDF: 426
  • XML: 269
  • Total: 3,701
  • BibTeX: 61
  • EndNote: 119
Views and downloads (calculated since 06 Sep 2024)
Cumulative views and downloads (calculated since 06 Sep 2024)

Viewed (geographical distribution)

Total article views: 3,701 (including HTML, PDF, and XML) Thereof 3,585 with geography defined and 116 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 12 Feb 2026
Download
Short summary
Glacier retreat poses big challenges, making understanding how climate affects glaciers vital. But glacier measurements worldwide are limited. We created a simple machine-learning model called miniML-MB, which estimates annual changes in glacier mass in the Swiss Alps. As input, miniML-MB uses two climate variables: average temperature (May–Aug) and total precipitation (Oct–Feb). Our model can accurately predict glacier mass from 1961 to 2021 but struggles for extreme years (2022 and 2023).
Read more
Share