EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FE-PINNs: Finite-element-based physics-informed neural networks for surrogate modeling

Pranav Sunil, Ryan B. Sills

APL Machine Learning · 01.03.2026 · 4 (1)

DOI: 10.1063/5.0299671 ↗

Kurz gefasst

Fachartikel in der Zeitschrift APL Machine Learning, online erschienen am 13.02.2026. Verfasst von Pranav Sunil und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, Army Research Office.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a method whereby the finite element (FE) method is used to train physics-informed neural networks that are suitable for surrogate modeling. The method is based on a new class of mesh-based neural network operators called stenciled operators, which leverage the inverse isoparametric map of the FE method. In contrast with graph-based methods, stenciled operators can incorporate non-local information over arbitrary spatial domains with computational costs that are length-scale invariant. Using stenciled convolutional operations as an exemplar, we demonstrate the performance of the method in several training and testing scenarios with linear-elastic boundary-value problems of varying geometries. The resulting neural networks show reasonable accuracy when tested on unseen geometries that are similar to those used for training. Furthermore, when the number of training geometries is increased, the testing errors systematically decrease, demonstrating that the neural networks learn how to generalize as the training set becomes larger. Further extending the method to allow for variable boundary conditions, properties, and body forces will lead to a general-purpose surrogate modeling framework that can leverage existing FE codes for training.

Förderung

  • National Science Foundation
  • Army Research Office

Zitieren

APA

Sunil, P., & Sills, R. B. (2026). FE-PINNs: Finite-element-based physics-informed neural networks for surrogate modeling. APL Machine Learning, 4(1). https://doi.org/10.1063/5.0299671

Vancouver

Sunil P, Sills RB. FE-PINNs: Finite-element-based physics-informed neural networks for surrogate modeling. APL Machine Learning. 2026;4(1). doi:10.1063/5.0299671

BibTeX
@article{Sunil2026,
  author = {Sunil, Pranav and Sills, Ryan B.},
  title = {FE-PINNs: Finite-element-based physics-informed neural networks for surrogate modeling},
  journal = {APL Machine Learning},
  year = {2026},
  volume = {4},
  number = {1},
  doi = {10.1063/5.0299671}
}
Kostenlos starten →