Saved in:
Bibliographic Details
Main Authors: Sardar, Mohammed, Skillen, Alex, Zimoń, Małgorzata J., Draycott, Samuel, Revell, Alistair
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