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

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

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.
Short summary
We developed a new modelling framework combining numerical methods with machine learning. Using this approach, we focused on understanding how ice moves within glaciers, and we successfully learnt a prescribed law describing ice movement for 17 glaciers worldwide as a proof of concept. Our framework has the potential to discover important laws governing glacier processes, aiding our understanding of glacier physics and their contribution to water resources and sea-level rise.