Physics-Constrained Diffusion Model for Synthesis of 3D Turbulent Data

TL;DR

This paper introduces a physics-constrained diffusion model that effectively synthesizes realistic 3D turbulent velocity fields, maintaining physical laws and statistical properties better than unconstrained models.

Contribution

The paper presents a novel diffusion-based generative model that incorporates physical constraints directly, enabling stable and accurate synthesis of complex turbulent flows.

Findings

Successfully synthesizes inertial-range turbulence data with physical fidelity

Outperforms standard diffusion models in statistical accuracy and physical consistency

Achieves stable training and realistic turbulence features at medium resolution

Abstract

Synthesizing fully developed three-dimensional turbulent velocity fields remains a long-standing problem in fluid mechanics and an open challenge for generative modeling. The difficulty arises from the coexistence of extreme dimensionality, multiscale rough fluctuations and strong intermittency, together with exact physical constraints such as incompressibility and zero-mean momentum. We propose a physics-constrained diffusion model (PCDM) in which these \emph{a priori} constraints are incorporated directly into the generative dynamics. Using rotating turbulence as a stringent benchmark, we show that the proposed framework enables stable and statistically faithful synthesis of inertial-range three-dimensional turbulent velocity fields at medium resolution, accurately reproducing anisotropic energy spectra, intermittency statistics, and physical constraints. By contrast, standard denoising diffusion probabilistic models without such constraints exhibit multiscale statistical deviations, violations of physical consistency, and substantially slower training convergence. These findings point to broader implications for generative modeling of high-dimensional complex systems under physical constraints.