Parameterized Physics-informed Neural Networks for Parameterized PDEs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916361305849856 |
|---|---|
| author | Cho, Woojin Jo, Minju Lim, Haksoo Lee, Kookjin Lee, Dongeun Hong, Sanghyun Park, Noseong |
| author_facet | Cho, Woojin Jo, Minju Lim, Haksoo Lee, Kookjin Lee, Dongeun Hong, Sanghyun Park, Noseong |
| contents | Complex physical systems are often described by partial differential equations (PDEs) that depend on parameters such as the Reynolds number in fluid mechanics. In applications such as design optimization or uncertainty quantification, solutions of those PDEs need to be evaluated at numerous points in the parameter space. While physics-informed neural networks (PINNs) have emerged as a new strong competitor as a surrogate, their usage in this scenario remains underexplored due to the inherent need for repetitive and time-consuming training. In this paper, we address this problem by proposing a novel extension, parameterized physics-informed neural networks (P$^2$INNs). P$^2$INNs enable modeling the solutions of parameterized PDEs via explicitly encoding a latent representation of PDE parameters. With the extensive empirical evaluation, we demonstrate that P$^2$INNs outperform the baselines both in accuracy and parameter efficiency on benchmark 1D and 2D parameterized PDEs and are also effective in overcoming the known "failure modes". |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09446 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Parameterized Physics-informed Neural Networks for Parameterized PDEs Cho, Woojin Jo, Minju Lim, Haksoo Lee, Kookjin Lee, Dongeun Hong, Sanghyun Park, Noseong Machine Learning Numerical Analysis Computational Physics Complex physical systems are often described by partial differential equations (PDEs) that depend on parameters such as the Reynolds number in fluid mechanics. In applications such as design optimization or uncertainty quantification, solutions of those PDEs need to be evaluated at numerous points in the parameter space. While physics-informed neural networks (PINNs) have emerged as a new strong competitor as a surrogate, their usage in this scenario remains underexplored due to the inherent need for repetitive and time-consuming training. In this paper, we address this problem by proposing a novel extension, parameterized physics-informed neural networks (P$^2$INNs). P$^2$INNs enable modeling the solutions of parameterized PDEs via explicitly encoding a latent representation of PDE parameters. With the extensive empirical evaluation, we demonstrate that P$^2$INNs outperform the baselines both in accuracy and parameter efficiency on benchmark 1D and 2D parameterized PDEs and are also effective in overcoming the known "failure modes". |
| title | Parameterized Physics-informed Neural Networks for Parameterized PDEs |
| topic | Machine Learning Numerical Analysis Computational Physics |
| url | https://arxiv.org/abs/2408.09446 |