.png){kind=icon}
.png){kind=icon}
Return
Bayesian conditional diffusion models for versatile spatiotemporal turbulence generation
.png){kind=icon}
OA
AI
DOI：10.1016/j.cma.2024.117023.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Turbulent flows, characterized by their chaotic and stochastic nature, have historically presented formidable challenges to predictive computational modeling. Traditional eddy -resolved numerical simulations often require vast computational resources, making them impractical or infeasible for numerous engineering applications. As an alternative, deep learning -based surrogate models have emerged, offering data -drive solutions. However, these are typically constructed within deterministic settings, leading to shortfall in capturing the innate chaotic and stochastic behaviors of turbulent dynamics. In this study, we introduce a novel generative framework grounded in probabilistic diffusion models for versatile generation of spatiotemporal turbulence under various conditions. Our method unifies both unconditional and conditional sampling strategies within a Bayesian framework, which can accommodate diverse conditioning scenarios, including those with a direct differentiable link between specified conditions and generated unsteady flow outcomes, as well as scenarios lacking such explicit correlations. A notable feature of our approach is the method proposed for long -span flow sequence generation, which is based on autoregressive gradient -based conditional sampling, eliminating the need for cumbersome retraining processes. We evaluate and showcase the versatile turbulence generation capability of our framework through a suite of numerical experiments, including: (1) the synthesis of Large Eddy Simulations (LES) simulated instantaneous flow sequences from unsteady Reynolds -Averaged Navier-Stokes (URANS) inputs; (2) holistic generation of inhomogeneous, anisotropic wall -bounded turbulence, whether from given initial conditions, prescribed turbulence statistics, or entirely from scratch; (3) super -resolved generation of high-speed turbulent boundary layer flows from low -resolution data across a range of input resolutions. Collectively, our numerical experiments highlight the merit and transformative potential of the proposed methods, making a significant advance in the field of turbulence generation.
Keywords:
Turbulent flow
Generative modeling
Bayesian statistics
Surrogate modeling
Wall-bounded turbulence
Chaotic dynamics
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.3
Papers:
1.3W
Citations:
5.6W
Organization
View more organizations