Articles | Volume 16, issue 6
https://doi.org/10.5194/se-16-477-2025
https://doi.org/10.5194/se-16-477-2025
Research article
 | 
23 Jun 2025
Research article |  | 23 Jun 2025

About the trustworthiness of physics-based machine learning – considerations for geomechanical applications

Denise Degen, Moritz Ziegler, Oliver Heidbach, Andreas Henk, Karsten Reiter, and Florian Wellmann

Related authors

Exploiting Physics-Based Machine Learning to Quantify Geodynamic Effects – Insights from the Alpine Region
Denise Degen, Ajay Kumar, Magdalena Scheck-Wenderoth, and Mauro Cacace
EGUsphere, https://doi.org/10.5194/egusphere-2025-1925,https://doi.org/10.5194/egusphere-2025-1925, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Perspectives of physics-based machine learning strategies for geoscientific applications governed by partial differential equations
Denise Degen, Daniel Caviedes Voullième, Susanne Buiter, Harrie-Jan Hendricks Franssen, Harry Vereecken, Ana González-Nicolás, and Florian Wellmann
Geosci. Model Dev., 16, 7375–7409, https://doi.org/10.5194/gmd-16-7375-2023,https://doi.org/10.5194/gmd-16-7375-2023, 2023
Short summary
How biased are our models? – a case study of the alpine region
Denise Degen, Cameron Spooner, Magdalena Scheck-Wenderoth, and Mauro Cacace
Geosci. Model Dev., 14, 7133–7153, https://doi.org/10.5194/gmd-14-7133-2021,https://doi.org/10.5194/gmd-14-7133-2021, 2021
Short summary
Effects of transient processes for thermal simulations of the Central European Basin
Denise Degen and Mauro Cacace
Geosci. Model Dev., 14, 1699–1719, https://doi.org/10.5194/gmd-14-1699-2021,https://doi.org/10.5194/gmd-14-1699-2021, 2021
Short summary

Related subject area

Subject area: Tectonic plate interactions, magma genesis, and lithosphere deformation at all scales | Editorial team: Structural geology and tectonics, paleoseismology, rock physics, experimental deformation | Discipline: Tectonics
Relict landscape evolution and fault reactivation in the eastern Tian Shan: insights from the Harlik Mountains
Zihao Zhao, Tianyi Shen, Guocan Wang, Peter van der Beek, Yabo Zhou, and Cheng Ma
Solid Earth, 16, 503–530, https://doi.org/10.5194/se-16-503-2025,https://doi.org/10.5194/se-16-503-2025, 2025
Short summary
Switching extensional and contractional tectonics in the West Kunlun Mountains during the Jurassic period: responses to the Neo-Tethyan geodynamics along the Eurasian margin
Hong-Xiang Wu, Han-Lin Chen, Andrew V. Zuza, Yildirim Dilek, Du-Wei Qiu, Qi-Ye Lu, Feng-Qi Zhang, Xiao-Gan Cheng, and Xiu-Bin Lin
Solid Earth, 16, 155–177, https://doi.org/10.5194/se-16-155-2025,https://doi.org/10.5194/se-16-155-2025, 2025
Short summary
Influence of lateral heterogeneities on strike-slip fault behaviour: insights from analogue models
Sandra González-Muñoz, Guido Schreurs, Timothy C. Schmid, and Fidel Martín-González
Solid Earth, 15, 1509–1523, https://doi.org/10.5194/se-15-1509-2024,https://doi.org/10.5194/se-15-1509-2024, 2024
Short summary
Importance of basement faulting and salt decoupling for the structural evolution of the Fars Arc (Zagros fold-and-thrust belt): a numerical modeling approach
Fatemeh Gomar, Jonas B. Ruh, Mahdi Najafi, and Farhad Sobouti
Solid Earth, 15, 1479–1507, https://doi.org/10.5194/se-15-1479-2024,https://doi.org/10.5194/se-15-1479-2024, 2024
Short summary
Topographic stresses affect stress changes caused by megathrust earthquakes and condition aftershock seismicity in forearcs: Insights from mechanical models and the Tohoku-Oki and Maule earthquakes
Armin Dielforder, Gian Maria Bocchini, and Andrea Hampel
EGUsphere, https://doi.org/10.5194/egusphere-2024-3592,https://doi.org/10.5194/egusphere-2024-3592, 2024
Short summary

Cited articles

Ahlers, S., Henk, A., Hergert, T., Reiter, K., Müller, B., Röckel, L., Heidbach, O., Morawietz, S., Scheck-Wenderoth, M., and Anikiev, D.: 3D crustal stress state of Germany according to a data-calibrated geomechanical model, Solid Earth, 12, 1777–1799, https://doi.org/10.5194/se-12-1777-2021, 2021. a
Amadei, B. and Stephansson, O.: Rock Stress and its Measurement, Springer Science and Business Media, ISBN 10 0412447002, ISBN 13 978-0412447006, 1997. a
Bär, K., Reinsch, T., and Bott, J.: The PetroPhysical Property Database (P3) – a global compilation of lab-measured rock properties, Earth Syst. Sci. Data, 12, 2485–2515, https://doi.org/10.5194/essd-12-2485-2020, 2020. a
Benner, P., Gugercin, S., and Willcox, K.: A survey of projection-based model reduction methods for parametric dynamical systems, SIAM Rev., 57, 483–531, https://doi.org/10.1137/130932715, 2015. a, b, c, d, e, f
Download
Short summary
Obtaining reliable estimates of the subsurface state distributions is essential to determine the location of, e.g., potential nuclear waste disposal sites. However, providing these is challenging since it requires solving the problem numerous times, yielding high computational cost. To overcome this, we use a physics-based machine learning method to construct surrogate models. We demonstrate how it produces physics-preserving predictions, which differentiates it from purely data-driven approaches.
Share