Machine learning accelerated computational fluid dynamics

TL;DR

This paper introduces a deep learning approach that accelerates computational fluid dynamics simulations of turbulent flows, achieving comparable accuracy to high-resolution models with significantly reduced computational costs.

Contribution

The authors develop an end-to-end deep learning method that enhances fluid simulation accuracy and speed, outperforming traditional solvers in turbulence modeling and generalizing across different conditions.

Findings

Achieves 40-80x speedup over baseline solvers.

Maintains stability during long simulations.

Generalizes to unseen forcing functions and Reynolds numbers.

Abstract

Numerical simulation of fluids plays an essential role in modeling many physical phenomena, such as weather, climate, aerodynamics and plasma physics. Fluids are well described by the Navier-Stokes equations, but solving these equations at scale remains daunting, limited by the computational cost of resolving the smallest spatiotemporal features. This leads to unfavorable trade-offs between accuracy and tractability. Here we use end-to-end deep learning to improve approximations inside computational fluid dynamics for modeling two-dimensional turbulent flows. For both direct numerical simulation of turbulence and large eddy simulation, our results are as accurate as baseline solvers with 8-10x finer resolution in each spatial dimension, resulting in 40-80x fold computational speedups. Our method remains stable during long simulations, and generalizes to forcing functions and Reynolds numbers outside of the flows where it is trained, in contrast to black box machine learning approaches. Our approach exemplifies how scientific computing can leverage machine learning and hardware accelerators to improve simulations without sacrificing accuracy or generalization.