Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.15029 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908427791368192 |
|---|---|
| author | Sardar, Mohammed Skillen, Alex Zimoń, Małgorzata J. Draycott, Samuel Revell, Alistair |
| author_facet | Sardar, Mohammed Skillen, Alex Zimoń, Małgorzata J. Draycott, Samuel Revell, Alistair |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_15029 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery Sardar, Mohammed Skillen, Alex Zimoń, Małgorzata J. Draycott, Samuel Revell, Alistair Fluid Dynamics Computational Physics 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. |
| title | Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery |
| topic | Fluid Dynamics Computational Physics |
| url | https://arxiv.org/abs/2312.15029 |