Turbulence Scaling from Deep Learning Diffusion Generative Models
arXiv:2311.06112 · doi:10.1016/j.jcp.2024.113239
Abstract
Complex spatial and temporal structures are inherent characteristics of turbulent fluid flows and comprehending them poses a major challenge. This comprehesion necessitates an understanding of the space of turbulent fluid flow configurations. We employ a diffusion-based generative model to learn the distribution of turbulent vorticity profiles and generate snapshots of turbulent solutions to the incompressible Navier-Stokes equations. We consider the inverse cascade in two spatial dimensions and generate diverse turbulent solutions that differ from those in the training dataset. We analyze the statistical scaling properties of the new turbulent profiles, calculate their structure functions, energy power spectrum, velocity probability distribution function and moments of local energy dissipation. All the learnt scaling exponents are consistent with the expected Kolmogorov scaling. This agreement with established turbulence characteristics provides strong evidence of the model's capability to capture essential features of real-world turbulence.
References in corpus (13)
- Denoising Diffusion Probabilistic Models
- Super-resolution reconstruction of turbulent flows with machine learning
- A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction
- An update on the double cascade scenario in two-dimensional turbulence
- Mean- Field Approximation and a Small Parameter in Turbulence Theory
- Inferring flow parameters and turbulent configuration with physics-informed data-assimilation and spectral nudging
- Synthetic Lagrangian Turbulence by Generative Diffusion Models
- Generative Modeling of Turbulence
- Interpreted machine learning in fluid dynamics: Explaining relaminarisation events in wall-bounded shear flows
- Self-similar Subgrid-scale Models for Inertial Range Turbulence and Accurate Measurements of Intermittency
- Spontaneous Symmetry Breaking, Conformal Anomaly and Incompressible Fluid Turbulence
- Generative Adversarial Networks to infer velocity components in rotating turbulent flows
- Neural Network Complexity of Chaos and Turbulence