Learning Temporally Consistent Turbulence Between Sparse Snapshots via Diffusion Models
On the map: Diffusion models → Flow matching, time series and science
Abstract (arXiv)
We investigate the statistical accuracy of temporally interpolated spatiotemporal flow sequences between sparse, decorrelated snapshots of turbulent flow fields using conditional Denoising Diffusion Probabilistic Models (DDPMs). The developed method is presented as a proof-of-concept generative surrogate for reconstructing coherent turbulent dynamics between sparse snapshots, demonstrated on a 2D Kolmogorov Flow, and a 3D Kelvin-Helmholtz Instability (KHI). We analyse the generated flow sequences through the lens of statistical turbulence, examining the time-averaged turbulent kinetic energy spectra over generated sequences, and temporal decay of turbulent structures. For the non-stationary Kelvin-Helmholtz Instability, we assess the ability of the proposed method to capture evolving flow statistics across the most strongly time-varying flow regime. We additionally examine instantaneous fields and physically motivated metrics at key stages of the KHI flow evolution.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 11 of its 23 references that are in the map. First posted on arXiv 31 Dec 2025.
Builds on
11 of 23 references.
Closest ancestors · 5
Same direction, newest first
- 2024CoNFiLD-inlet: Synthetic Turbulence Inflow Using Generative Latent Diffusion Models with Neural Fields21 Nov
- 2024Stochastic Reconstruction of Gappy Lagrangian Turbulent Signals by Conditional Diffusion Models31 Oct
- 2023Bayesian Conditional Diffusion Models for Versatile Spatiotemporal Turbulence Generation14 Nov
- 2023Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation4 Sep
- 2023Synthetic Lagrangian Turbulence by Generative Diffusion Models17 Jul
Other references · 6
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
- 2022Classifier-Free Diffusion Guidancecited by 5,717
- 2022Video Diffusion Modelscited by 2,280
- 2023Preserve Your Own Correlation: A Noise Prior for Video Diffusion Modelscited by 284
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Physics-aware generative models for turbulent fluid flows through energy-consistent stochastic interpolants
- 2025Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
- 2024Unfolding Time: Generative Modeling for Turbulent Flows in 4D
- 2025Guiding diffusion models to reconstruct flow fields from sparse data
- 2026Optimal-Transport-Guided Functional Flow Matching for Turbulent Field Generation in Hilbert Space
- 2026PerFlow: Physics-Embedded Rectified Flow for Efficient Reconstruction and Uncertainty Quantification of Spatiotemporal Dynamics
- 2025Lazy Diffusion: Mitigating spectral collapse in generative diffusion-based stable autoregressive emulation of turbulent flows
- 2025Rectified Flows for Fast Multiscale Fluid Flow Modeling