Synthetic Lagrangian Turbulence by Generative Diffusion Models

Abstract

Lagrangian turbulence lies at the core of numerous applied and fundamental problems related to the physics of dispersion and mixing in engineering, bio-fluids, atmosphere, oceans, and astrophysics. Despite exceptional theoretical, numerical, and experimental efforts conducted over the past thirty years, no existing models are capable of faithfully reproducing statistical and topological properties exhibited by particle trajectories in turbulence. We propose a machine learning approach, based on a state-of-the-art diffusion model, to generate single-particle trajectories in three-dimensional turbulence at high Reynolds numbers, thereby bypassing the need for direct numerical simulations or experiments to obtain reliable Lagrangian data. Our model demonstrates the ability to reproduce most statistical benchmarks across time scales, including the fat-tail distribution for velocity increments, the anomalous power law, and the increased intermittency around the dissipative scale. Slight deviations are observed below the dissipative scale, particularly in the acceleration and flatness statistics. Surprisingly, the model exhibits strong generalizability for extreme events, producing events of higher intensity and rarity that still match the realistic statistics. This paves the way for producing synthetic high-quality datasets for pre-training various downstream applications of Lagrangian turbulence.

We include Supplementary Information as a separate PDF file available in the Tex Source download area

References in corpus (29)

• WaveNet: A Generative Model for Raw Audio
• Machine Learning for Fluid Mechanics
• Turbulence Modeling in the Age of Data
• Particles and fields in fluid turbulence
• Fluid Particle Accelerations in Fully Developed Turbulence
• Measurement of Lagrangian velocity in fully developed turbulence
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Introduction to quantum turbulence
• DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps
• Multifractal statistics of Lagrangian velocity and acceleration in turbulence
• Universal intermittent properties of particle trajectories in highly turbulent flows
• A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction
• Log-infinitely divisible multifractal processes
• Long time correlations in Lagrangian dynamics: a key to intermittency in turbulence
• Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
• Lagrangian Velocity Statistics in Turbulent Flows: Effects of Dissipation
• Guidelines for the formulation of Lagrangian stochastic models for particle simulations of single-phase and dispersed two-phase turbulent flows
• Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database
• Multi-particle dispersion in fully developed turbulence
• Synthetic Lagrangian Turbulence by Generative Diffusion Models
• Mimicking a turbulent signal: sequential multiaffine processes
• Extreme events in the dispersions of two neighboring particles under the influence of fluid turbulence
• Lagrangian Statistics of Navier-Stokes- and MHD-Turbulence
• The Varieties of Dynamic Multiscaling in Fluid Turbulence
• Modelling Lagrangian velocity and acceleration in turbulent flows as infinitely differentiable stochastic processes
• Persistent accelerations disentangle Lagrangian turbulence
• Optimal tracking strategies in a turbulent flow
• Multi-level stochastic refinement for complex time series and fields: A Data-Driven Approach
• TURB-Lagr. A database of 3d Lagrangian trajectories in homogeneous and isotropic turbulence

Cited by in corpus (15)

• Synthetic Lagrangian Turbulence by Generative Diffusion Models
• Turbulence Scaling from Deep Learning Diffusion Generative Models
• Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
• Towards Synthetic Magnetic Turbulence with Coherent Structures
• Generative prediction of flow fields around an obstacle using the diffusion model
• Understanding complex crowd dynamics with generative neural simulators
• Machine-learning-based simulation of turbulent flows over periodic hills using a hybrid U-Net and Fourier neural operator framework
• A Very Effective and Simple Diffusion Reconstruction for the Diluted Ising Model
• A multiscale and multicriteria Generative Adversarial Network to synthesize 1-dimensional turbulent fields
• Data-driven Mori-Zwanzig modeling of Lagrangian particle dynamics in turbulent flows
• Effective Energy, Interactions And Out Of Equilibrium Nature Of Scalar Active Matter
• Modelling cosmic-ray transport: magnetised versus unmagnetised motion in astrophysical magnetic turbulence
• Synthetic Turbulence via an Instanton Gas Approximation
• Resolving Turbulent Magnetohydrodynamics: A Hybrid Operator-Diffusion Framework
• Quantum-assisted tracer dispersion in turbulent shear flow