EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PICL: Physics informed contrastive learning for partial differential equations

Cooper Lorsung, Amir Barati Farimani

APL Machine Learning · 01.12.2024 · 2 (4)

DOI: 10.1063/5.0223651 ↗

Kurz gefasst

Fachartikel in der Zeitschrift APL Machine Learning, online erschienen am 14.11.2024. Verfasst von Cooper Lorsung und 1 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural operators have recently grown in popularity as Partial Differential Equation (PDE) surrogate models. Learning solution functionals, rather than functions, has proven to be a powerful approach to calculate fast, accurate solutions to complex PDEs. While much work has been performed evaluating neural operator performance on a wide variety of surrogate modeling tasks, these works normally evaluate performance on a single equation at a time. In this work, we develop a novel contrastive pretraining framework utilizing generalized contrastive loss that improves neural operator generalization across multiple governing equations simultaneously. Governing equation coefficients are used to measure ground-truth similarity between systems. A combination of physics-informed system evolution and latent-space model output is anchored to input data and used in our distance function. We find that physics-informed contrastive pretraining improves accuracy for the Fourier neural operator in fixed-future and autoregressive rollout tasks for the 1D and 2D heat, Burgers’, and linear advection equations.

Förderung

  • National Science Foundation

Zitieren

APA

Lorsung, C., & Farimani, A. B. (2024). PICL: Physics informed contrastive learning for partial differential equations. APL Machine Learning, 2(4). https://doi.org/10.1063/5.0223651

Vancouver

Lorsung C, Farimani AB. PICL: Physics informed contrastive learning for partial differential equations. APL Machine Learning. 2024;2(4). doi:10.1063/5.0223651

BibTeX
@article{Lorsung2024,
  author = {Lorsung, Cooper and Farimani, Amir Barati},
  title = {PICL: Physics informed contrastive learning for partial differential equations},
  journal = {APL Machine Learning},
  year = {2024},
  volume = {2},
  number = {4},
  doi = {10.1063/5.0223651}
}
Kostenlos starten →