Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
arXiv:2312.15029 · doi:10.1063/5.0231664
Abstract
We investigate the statistical recovery of missing physics and turbulent phenomena in fluid flows using generative machine learning. Here we develop a two-stage super-resolution method using spectral filtering to restore the high-wavenumber components of a Kolmogorov flow. We include a rigorous examination of generated samples through the lens of statistical turbulence. By extending the prior methods to a combined super-resolution and conditional high-wavenumber generation, we demonstrate turbulence recovery on a 8x upsampling task, effectively doubling the range of recovered wavenumbers.
28 pages, 15 figures
References in corpus (11)
- Diffusion Models Beat GANs on Image Synthesis
- Classifier-Free Diffusion Guidance
- A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction
- Tackling the Generative Learning Trilemma with Denoising Diffusion GANs
- Super-resolution reconstruction of turbulent flow at various Reynolds numbers based on generative adversarial networks
- Synthetic Lagrangian Turbulence by Generative Diffusion Models
- Generative Modeling of Turbulence
- Learning to correct spectral methods for simulating turbulent flows
- From Zero to Turbulence: Generative Modeling for 3D Flow Simulation
- Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection
- Physics-Informed CNNs for Super-Resolution of Sparse Observations on Dynamical Systems