Unfolding Time: Generative Modeling for Turbulent Flows in 4D

TL;DR

This paper introduces a 4D generative diffusion model with physics-informed guidance to produce realistic sequences of turbulent flow states, advancing the analysis of dynamic phenomena in turbulence modeling.

Contribution

It extends previous 3D generative models by enabling sequence generation of turbulent flows using a novel 4D approach and physics-informed techniques.

Findings

Successfully samples entire subsequences of turbulent flows

Demonstrates potential for analyzing temporal evolution of turbulence

Highlights challenges in generalizing from frames to sequences

Abstract

A recent study in turbulent flow simulation demonstrated the potential of generative diffusion models for fast 3D surrogate modeling. This approach eliminates the need for specifying initial states or performing lengthy simulations, significantly accelerating the process. While adept at sampling individual frames from the learned manifold of turbulent flow states, the previous model lacks the capability to generate sequences, hindering analysis of dynamic phenomena. This work addresses this limitation by introducing a 4D generative diffusion model and a physics-informed guidance technique that enables the generation of realistic sequences of flow states. Our findings indicate that the proposed method can successfully sample entire subsequences from the turbulent manifold, even though generalizing from individual frames to sequences remains a challenging task. This advancement opens doors for the application of generative modeling in analyzing the temporal evolution of turbulent flows, providing valuable insights into their complex dynamics.