Invited Talk: Generative Learning for Turbulence: Conditional Diffusion and Flow Matching Models for Spatiotemporal Flow Synthesis and Reconstruction

INVITED · P01 · ID: 3586499

Presentations

  • Generative Learning for Turbulence: Conditional Diffusion and Flow Matching Models for Spatiotemporal Flow Synthesis and Reconstruction

    ORAL · Invited

    –

    Publication: 1. CoNFiLD-inlet: Synthetic Turbulence Inflow Using Generative Latent Diffusion Models with Neural Fields, Physical Review Fluids, 054901, 2025
    2. Conditional neural field latent diffusion model for generating spatiotemporal turbulence, Nature Communications, 1, 15, 10416, 2024.
    3. Bayesian conditional diffusion model for versatile spatiotemporal turbulence generation, Computer Methods in Applied Mechanics and Engineering, 117023, 2024
    4. Conditional flow matching for generative modeling of near-wall turbulence with quantified uncertainty, under review in Journal of Fluid Mechanics. 2025

    Presenters

    • Jian-Xun Wang

      Cornell University, University of Notre Dame

    Authors

    • Jian-Xun Wang

      Cornell University, University of Notre Dame

    View abstract →