Universal differential equations for glacier ice flow modelling

Bolibar, Jordi; Sapienza, Facundo; Maussion, Fabien; Lguensat, Redouane; Wouters, Bert; Pérez, Fernando

doi:https://doi.org/10.5194/gmd-16-6671-2023

Articles | Volume 16, issue 22

https://doi.org/10.5194/gmd-16-6671-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/gmd-16-6671-2023

© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 16, issue 22

Development and technical paper

| Highlight paper

|

16 Nov 2023

Development and technical paper | Highlight paper |

| 16 Nov 2023

Universal differential equations for glacier ice flow modelling

Jordi Bolibar, Facundo Sapienza, Fabien Maussion, Redouane Lguensat, Bert Wouters, and Fernando Pérez

Model code and software

ODINN.jl Jordi Bolibar and Facundo Sapienza https://doi.org/10.5281/zenodo.8033313

OGGM/oggm: v1.6.0 (v1.6.0) Fabien Maussion, Timo Rothenpieler, Matthias Dusch, Patrick Schmitt, Anouk Vlug, Lilian Schuster, Nicolas Champollion, Fei Li, Ben Marzeion, Moritz Oberrauch, Julia Eis, Johannes Landmann, Alex Jarosch, Alexander Fischer, luzpaz, Sarah Hanus, David Rounce, Matteo Castellani, Sadie L. Bartholomew, and zhaohongyu https://doi.org/10.5281/zenodo.7718476

Executive editor

The integration of neural networks into PDE solvers to simulate systems for which the PDE models are incomplete is a key advance at the cutting edge of geoscientific modelling. The approach presented here is applicable far beyond the realm of ice modelling, and will be of interest to model developers and users across geoscience and beyond.