EUVIMEDEUVIMED entdecken
Crossref

Physically-Informed Flow Matching with Graph Neural Networks for Complex Fluid Dynamics

Xiaozhuang Song, Tianshu Yu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (2) · 1024-1032

DOI: 10.1609/aaai.v40i2.37072 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xiaozhuang Song und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computational fluid dynamics (CFD) simulations traditionally require extensive computational resources, limiting their utility in many scientific and engineering applications at scale. We introduce Physically-Informed Flow Matching Graph Networks (PIFM-GN), a novel generative framework that directly samples fluid states under specified physical conditions without requiring expensive time-stepping simulations. The key innovation of our approach is the incorporation of incompressibility constraints directly into the flow matching transport process by parameterizing velocity fields through vector potentials, with graph-based curl operators ensuring divergence-free predictions without requiring global pressure-Poisson solves. Experiments on diverse fluid dynamics problems -- ranging from two-dimensional surface pressure distributions and complete flow fields, to complex three-dimensional airflow fields -- demonstrate that PIFM-GN generates high-fidelity samples with significantly fewer sampling steps than diffusion-based alternatives. Most notably, our model maintains competitive performance even with a single sampling step, a regime where diffusion models completely fail. Our generated samples accurately reproduce the statistical characteristics of target flows, successfully capturing multi-modal pressure distributions across various flow conditions, while achieving significant computational speedups compared to diffusion-based methods. PIFM-GN thus enables efficient generation of fluid states for downstream analysis and design tasks in scientific and engineering applications.

Zitieren

APA

Song, X., & Yu, T. (2026). Physically-Informed Flow Matching with Graph Neural Networks for Complex Fluid Dynamics. Proceedings of the AAAI Conference on Artificial Intelligence, 40(2), 1024-1032. https://doi.org/10.1609/aaai.v40i2.37072

Vancouver

Song X, Yu T. Physically-Informed Flow Matching with Graph Neural Networks for Complex Fluid Dynamics. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(2):1024-1032. doi:10.1609/aaai.v40i2.37072

BibTeX
@article{Song2026,
  author = {Song, Xiaozhuang and Yu, Tianshu},
  title = {Physically-Informed Flow Matching with Graph Neural Networks for Complex Fluid Dynamics},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {2},
  pages = {1024--1032},
  doi = {10.1609/aaai.v40i2.37072}
}
Kostenlos starten →