PICL: Physics informed contrastive learning for partial differential equations
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.
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}
}
EUVIMED