EUVIMEDEUVIMED entdecken
Crossref

wPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation Laws

Tim De Ryck, Siddhartha Mishra, Roberto Molinaro

SIAM Journal on Numerical Analysis · 30.04.2024 · 62 (2) · 811-841

DOI: 10.1137/22m1522504 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Numerical Analysis, online erschienen am 14.03.2024. Verfasst von Tim De Ryck und 2 weiteren Autor:innen. Die Arbeit wurde bisher 74-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: H2020 European Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Physics informed neural networks (PINNs) require regularity of solutions of the underlying PDE to guarantee accurate approximation. Consequently, they may fail at approximating discontinuous solutions of PDEs such as nonlinear hyperbolic equations. To ameliorate this, we propose a novel variant of PINNs, termed as weak PINNs (wPINNs) for accurate approximation of entropy solutions of scalar conservation laws. wPINNs are based on approximating the solution of a min-max optimization problem for a residual, defined in terms of Kruzkhov entropies, to determine parameters for the neural networks approximating the entropy solution as well as test functions. We prove rigorous bounds on the error incurred by wPINNs and illustrate their performance through numerical experiments to demonstrate that wPINNs can approximate entropy solutions accurately.

Förderung

  • H2020 European Research Council

Zitieren

APA

Ryck, T. D., Mishra, S., & Molinaro, R. (2024). wPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation Laws. SIAM Journal on Numerical Analysis, 62(2), 811-841. https://doi.org/10.1137/22m1522504

Vancouver

Ryck TD, Mishra S, Molinaro R. wPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation Laws. SIAM Journal on Numerical Analysis. 2024;62(2):811-841. doi:10.1137/22m1522504

BibTeX
@article{Ryck2024,
  author = {Ryck, Tim De and Mishra, Siddhartha and Molinaro, Roberto},
  title = {wPINNs: Weak Physics Informed Neural Networks for Approximating Entropy Solutions of Hyperbolic Conservation Laws},
  journal = {SIAM Journal on Numerical Analysis},
  year = {2024},
  volume = {62},
  number = {2},
  pages = {811--841},
  doi = {10.1137/22m1522504}
}
Kostenlos starten →