Machine learning accelerated computational fluid dynamics
This addresses the accuracy-tractability trade-off in computational fluid dynamics for applications like weather and aerodynamics, representing a novel integration rather than an incremental improvement.
The paper tackles the high computational cost of solving Navier-Stokes equations for fluid dynamics by using end-to-end deep learning to accelerate simulations, achieving 40-80x speedups while maintaining accuracy comparable to baseline solvers with 8-10x finer resolution.
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.