References

In this page we provide the main references used in the ODINN project, grouped by themes.

Papers using ODINN.jl

• Universal differential equations for glacier ice flow modelling, Bolibar and Sapienza et al. (2023), Geoscientific Model Development [2].

Papers about Universal Differential Equations and the SciML ecosystem

• Universal Differential Equations for Scientific Machine Learning, Rackauckas et al. (2020) [1].
• Stiff neural ordinary differential equations, Kim et al. (2021) [9].
• Spherical Path Regression through Universal Differential Equations with Applications to Paleomagnetism, Sapienza et al. (preprint) [10].
• On Neural Differential Equations, Kidger (2022) [11].
• Physics-Based Deep Learning, Thuerey et al. (2021) [12].

Papers about differentiable programming

• Differentiable programming for differential equations: a review, Sapienza et al. (preprint) [7].
• Differentiable programming for Earth System modelling, Gelbrecht et al. (2023), Geoscientific Model Development [13].

Papers about Julia packages

• Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl, Cranmer (2023), arXiV [14].

Papers about glacier (ice flow) modelling

• Inversion of basal friction in Antarctica using exact and incomplete adjoints of a higher-order model, Morlighem et al. (2013), JGR Earth Surface [3].
• What is glacier sliding?, Law et al. (2025), arXiV [15].
• Deep learning the flow law of Antarctic ice shelves, Wang et al. (2025), Science [16].
• The Physics of Glaciers, Cuffey and Paterson (2010) [8].
• Ice-Dynamical Glacier Evolution Modeling - A Review, Zekollari et al. (2022) [17].
• Do existing theories explain seasonal to multi-decadal changes in glacier basal sliding speed?, Gimbert et al. (2021) [18].

Papers about the MassBalanceMachine

• Machine learning improves seasonal mass balance prediction for unmonitored glaciers, Sjursen et al. (preprint) [19].

Datasets

• GlaThiDa: Glacier ice thickness database, Welty et al. (2020), ESSD [4].
• Ice velocity and thickness of the world’s glaciers, Millan et al. (2022), Nature Geoscience [5].
• Satellite-Derived Annual Glacier Surface Flow Velocity Products for the European Alps, 2015–2021, Rabatel et al. (2023) [6]

Full bibliography