EUVIMEDEUVIMED entdecken
Crossref

Integrating neural operators with diffusion models improves spectral representation in turbulence modelling

Vivek Oommen, Aniruddha Bora, Zhen Zhang, George Em Karniadakis

Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences · 2025-03 · 481 (2309)

DOI: 10.1098/rspa.2024.0819 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, online erschienen am 12.03.2025. Verfasst von Vivek Oommen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: SEA-CROGS, ONR Vannevar Bush Faculty Fellowship, MURI grant.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We integrate neural operators with diffusion models to address the spectral limitations of neural operators in surrogate modelling of turbulent flows. While neural operators offer computational efficiency, they exhibit deficiencies in capturing high-frequency flow dynamics, resulting in overly smooth approximations. To overcome this, we condition diffusion models on neural operators to enhance the resolution of turbulent structures. Our approach is validated for different neural operators on diverse datasets, including a high-Reynolds-number jet-flow simulation and experimental Schlieren velocimetry. The proposed method significantly improves the alignment of predicted energy spectra with true distributions compared to neural operators alone. This enables the diffusion models to stabilize longer forecasts through diffusion-corrected autoregressive (AR) rollouts, as we demonstrate in this work. In addition, proper orthogonal decomposition (POD) analysis demonstrates enhanced spectral fidelity in space–time. This work establishes a new paradigm for combining generative models with neural operators to advance surrogate modelling of turbulent systems, and it can be used in other scientific applications that involve microstructure and high-frequency content. See our project page: vivekoommen.github.io/NO_DM .

Förderung

  • SEA-CROGS
  • ONR Vannevar Bush Faculty Fellowship
  • MURI grant

Zitieren

APA

Oommen, V., Bora, A., Zhang, Z., & Karniadakis, G. E. (2025). Integrating neural operators with diffusion models improves spectral representation in turbulence modelling. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 481(2309). https://doi.org/10.1098/rspa.2024.0819

Vancouver

Oommen V, Bora A, Zhang Z, Karniadakis GE. Integrating neural operators with diffusion models improves spectral representation in turbulence modelling. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2025;481(2309). doi:10.1098/rspa.2024.0819

BibTeX
@article{Oommen2025,
  author = {Oommen, Vivek and Bora, Aniruddha and Zhang, Zhen and Karniadakis, George Em},
  title = {Integrating neural operators with diffusion models improves spectral representation in turbulence modelling},
  journal = {Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences},
  year = {2025},
  volume = {481},
  number = {2309},
  doi = {10.1098/rspa.2024.0819}
}
Kostenlos starten →