Machine learning–accelerated computational fluid dynamics
Dmitrii Kochkov, Jamie Smith, Ayya Alieva et al. · Proceedings of the National Academy of Sciences · 2021
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 to 10× finer resolution in each spatial dimension, resulting in 40- to 80-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.
Cited by 1,042 works. doi:10.1073/pnas.2101784118
Authors
References
- Deep Residual Learning for Image Recognition
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
- GENERAL CIRCULATION EXPERIMENTS WITH THE PRIMITIVE EQUATIONS
- The Local Structure of Turbulence in Incompressible Viscous Fluid for Very Large Reynolds' Numbers
- High Resolution Schemes Using Flux Limiters for Hyperbolic Conservation Laws
- Turbulent Flows
- Turbulence
- Direct solution of partial difference equations by tensor product methods
- Two-dimensional turbulence
- The local structure of turbulence in incompressible viscous fluid for very large Reynolds numbers