气候变化领域集成服务门户(CCPortal): Machine learning–accelerated computational fluid dynamics

CCPortal

DOI	10.1073/pnas.2101784118
	Machine learning–accelerated computational fluid dynamics
	Kochkov D.; Smith J.A.; Alieva A.; Wang Q.; Brenner M.P.; Hoyer S.
发表日期	2021
ISSN	0027-8424
卷号	118 期号:21
英文摘要	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 tradeoffs 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. © 2021 National Academy of Sciences. All rights reserved.
英文关键词	Computational physics; Differential equations; Machine learning; Nonlinear partial; Turbulence
语种	英语
scopus关键词	article; computational fluid dynamics; computer simulation; deep learning; human tissue; physics; turbulent flow
来源期刊	Proceedings of the National Academy of Sciences of the United States of America
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/238733
作者单位	Google Research, Mountain View, CA 94043, United States; School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, United States
推荐引用方式 GB/T 7714	Kochkov D.,Smith J.A.,Alieva A.,等. Machine learning–accelerated computational fluid dynamics[J],2021,118(21).
APA	Kochkov D.,Smith J.A.,Alieva A.,Wang Q.,Brenner M.P.,&Hoyer S..(2021).Machine learning–accelerated computational fluid dynamics.Proceedings of the National Academy of Sciences of the United States of America,118(21).
MLA	Kochkov D.,et al."Machine learning–accelerated computational fluid dynamics".Proceedings of the National Academy of Sciences of the United States of America 118.21(2021).