EUVIMEDEUVIMED entdecken
Crossref

A unified scalable framework for causal sweeping strategies for Physics-Informed Neural Networks (PINNs) and their temporal decompositions

Michael Penwarden, Ameya D. Jagtap, Shandian Zhe, George Em Karniadakis, Robert M. Kirby

Journal of Computational Physics · 2023-11 · 493 · 112464

DOI: 10.1016/j.jcp.2023.112464 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computational Physics, 2023-11. Verfasst von Michael Penwarden und 4 weiteren Autor:innen. Die Arbeit wurde bisher 109-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: Air Force Office of Scientific Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Physics-informed neural networks (PINNs) as a means of solving partial differential equations (PDE) have garnered much attention in the Computational Science and Engineering (CS&E) world. However, a recent topic of interest is exploring various training (i.e., optimization) challenges - in particular, arriving at poor local minima in the optimization landscape results in a PINN approximation giving an inferior, and sometimes trivial, solution when solving forward time-dependent PDEs with no data. This problem is also found in, and in some sense more difficult, with domain decomposition strategies such as temporal decomposition using XPINNs. We furnish examples and explanations for different training challenges, their cause, and how they relate to information propagation and temporal decomposition. We then propose a new stacked-decomposition method that bridges the gap between time-marching PINNs and XPINNs. We also introduce significant computational speed-ups by using transfer learning concepts to initialize subnetworks in the domain and loss tolerance-based propagation for the subdomains. Finally, we formulate a new time-sweeping collocation point algorithm inspired by the previous PINNs causality literature, which our framework can still describe, and provides a significant computational speed-up via reduced-cost collocation point segmentation. The proposed methods form our unified framework, which overcomes training challenges in PINNs and XPINNs for time-dependent PDEs by respecting the causality in multiple forms and improving scalability by limiting the computation required per optimization iteration. Finally, we provide numerical results for these methods on baseline PDE problems for which unmodified PINNs and XPINNs struggle to train.

Förderung

  • Air Force Office of Scientific Research

Zitieren

APA

Penwarden, M., Jagtap, A. D., Zhe, S., Karniadakis, G. E., & Kirby, R. M. (2023). A unified scalable framework for causal sweeping strategies for Physics-Informed Neural Networks (PINNs) and their temporal decompositions. Journal of Computational Physics, 493, 112464. https://doi.org/10.1016/j.jcp.2023.112464

Vancouver

Penwarden M, Jagtap AD, Zhe S, Karniadakis GE, Kirby RM. A unified scalable framework for causal sweeping strategies for Physics-Informed Neural Networks (PINNs) and their temporal decompositions. Journal of Computational Physics. 2023;493:112464. doi:10.1016/j.jcp.2023.112464

BibTeX
@article{Penwarden2023,
  author = {Penwarden, Michael and Jagtap, Ameya D. and Zhe, Shandian and Karniadakis, George Em and Kirby, Robert M.},
  title = {A unified scalable framework for causal sweeping strategies for Physics-Informed Neural Networks (PINNs) and their temporal decompositions},
  journal = {Journal of Computational Physics},
  year = {2023},
  volume = {493},
  pages = {112464},
  doi = {10.1016/j.jcp.2023.112464}
}
Kostenlos starten →