EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Variational Graph Neural Networks for Uncertainty Quantification in Inverse Problems

David González, Alba Muixí, Beatriz Moya, Elías Cueto

International Journal for Numerical Methods in Engineering · 30.11.2026 · 127 (22)

DOI: 10.1002/nme.70465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal for Numerical Methods in Engineering, online erschienen am 13.11.2026. Verfasst von David González und 3 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Ministerio de Ciencia, Innovación y Universidades, Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España, European Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increasingly wide use of deep machine learning techniques in computational mechanics has significantly accelerated simulations of problems that were considered unapproachable just a few years ago. However, in critical applications such as Digital Twins for engineering or medicine, fast responses are not enough; reliable results must also be provided. In certain cases, traditional deterministic methods may not be optimal as they do not provide a measure of confidence in their predictions or results, especially in inverse problems where the solution may not be unique or the initial data may not be entirely reliable due to the presence of noise, for instance. Classic deep neural networks also lack a clear measure to quantify the uncertainty of their predictions. In this work, we present a variational graph neural network (VGNN) architecture that integrates variational layers into its architecture to model the probability distribution of weights. Unlike computationally expensive full Bayesian networks, our approach strategically introduces variational layers exclusively in the decoder, allowing us to estimate cognitive uncertainty and statistical uncertainty at a relatively lower cost. In this work, we validate the proposed methodology in two cases of solid mechanics: the identification of the value of the elastic modulus with nonlinear distribution in a 2D elastic problem and the location and quantification of the loads applied to a 3D hyperelastic beam, in both cases using only the displacement field of each test as input data. The results show that the model not only recovers the physical parameters with high precision, but also provides confidence intervals consistent with the physics of the problem, as well as being able to locate the position of the applied load and estimate its value, giving a confidence interval for that experiment.

Förderung

  • Ministerio de Ciencia, Innovación y Universidades
  • Ministerio de Asuntos Económicos y Transformación Digital, Gobierno de España
  • European Research Council

Zitieren

APA

González, D., Muixí, A., Moya, B., & Cueto, E. (2026). Variational Graph Neural Networks for Uncertainty Quantification in Inverse Problems. International Journal for Numerical Methods in Engineering, 127(22). https://doi.org/10.1002/nme.70465

Vancouver

González D, Muixí A, Moya B, Cueto E. Variational Graph Neural Networks for Uncertainty Quantification in Inverse Problems. International Journal for Numerical Methods in Engineering. 2026;127(22). doi:10.1002/nme.70465

BibTeX
@article{Gonzlez2026,
  author = {González, David and Muixí, Alba and Moya, Beatriz and Cueto, Elías},
  title = {Variational Graph Neural Networks for Uncertainty Quantification in Inverse Problems},
  journal = {International Journal for Numerical Methods in Engineering},
  year = {2026},
  volume = {127},
  number = {22},
  doi = {10.1002/nme.70465}
}
Kostenlos starten →