EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine-learning emulation of the modeled basal thermal state for Totten Glacier

Junshun Wang, Liyun Zhao, Jin Dong, John C. Moore

Journal of Glaciology · 2026 · 72

DOI: 10.1017/jog.2026.10170 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Glaciology, online erschienen am 08.06.2026. Verfasst von Junshun Wang und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The basal thermal state of the Antarctic ice sheet strongly influences ice dynamics and mass balance. Although basal thermal states can be simulated using ice-sheet models, significant uncertainties persist, with poorly constrained geothermal heat flux being one important source of uncertainty. The substantial computational cost of ice-sheet models restricts large ensemble simulations essential for uncertainty quantification and sensitivity analyses. To address this limitation, we develop machine-learning emulators for rapidly simulating the basal temperature and melt rate of Totten Glacier. Three distinct machine-learning emulators were trained using outputs of full-Stokes model simulations with different geothermal heat flux fields, achieving accurate replication ( R 2 up to 0.92). At least five simulations are needed to train a reliable emulator for basal ice temperature. Model interpretability reveals complementary physics learning: Random forest and XGBoost prioritize local dynamic drivers (basal topography, ice velocity), while neural network captures lower-complexity statistical mapping that is more strongly influenced by globally predictive variables (surface temperature, ice thickness). For basal melt rate, surface velocity emerges as the primary driver. These findings highlight substantial potential for integrating machine learning with ice-sheet modeling to efficiently and better predict basal thermal states.

Zitieren

APA

Wang, J., Zhao, L., Dong, J., & Moore, J. C. (2026). Machine-learning emulation of the modeled basal thermal state for Totten Glacier. Journal of Glaciology, 72. https://doi.org/10.1017/jog.2026.10170

Vancouver

Wang J, Zhao L, Dong J, Moore JC. Machine-learning emulation of the modeled basal thermal state for Totten Glacier. Journal of Glaciology. 2026;72. doi:10.1017/jog.2026.10170

BibTeX
@article{Wang2026,
  author = {Wang, Junshun and Zhao, Liyun and Dong, Jin and Moore, John C.},
  title = {Machine-learning emulation of the modeled basal thermal state for Totten Glacier},
  journal = {Journal of Glaciology},
  year = {2026},
  volume = {72},
  doi = {10.1017/jog.2026.10170}
}
Kostenlos starten →