• Corpus ID: 222090391

Using Machine Learning to Augment Coarse-Grid Computational Fluid Dynamics Simulations

@article{Pathak2020UsingML,
  title={Using Machine Learning to Augment Coarse-Grid Computational Fluid Dynamics Simulations},
  author={Jaideep Pathak and Mustafa Mustafa and Karthik Kashinath and Emmanuel Motheau and Thorsten Kurth and Marcus S. Day},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.00072}
}
Simulation of turbulent flows at high Reynolds number is a computationally challenging task relevant to a large number of engineering and scientific applications in diverse fields such as climate science, aerodynamics, and combustion. Turbulent flows are typically modeled by the Navier-Stokes equations. Direct Numerical Simulation (DNS) of the Navier-Stokes equations with sufficient numerical resolution to capture all the relevant scales of the turbulent motions can be prohibitively expensive… 

Figures and Tables from this paper

Machine learning–accelerated computational fluid dynamics

It is shown that using machine learning inside traditional fluid simulations can improve both accuracy and speed, even on examples very different from the training data, which opens the door to applying machine learning to large-scale physical modeling tasks like airplane design and climate prediction.

Learned discretizations for passive scalar advection in a two-dimensional turbulent flow

A machine learning approach is used to learn a numerical discretization that retains high accuracy even when the solution is under-resolved with classical methods to solve passive scalar advection in a two-dimensional turbulent flow.

Learned Coarse Models for Efficient Turbulence Simulation

Broadly, the proposed model can simulate turbulent dynamics more accurately than classical numerical solvers at the comparably low resolutions across various scientifically relevant metrics.

Multiscale Neural Operator: Learning Fast and Grid-independent PDE Solvers

This work proposes a hybrid, flexible surrogate model that exploits known physics for simulating large-scale dynamics and limits learning to the hard-to-model term, which is called parametrization or closure and captures the effect of fine- onto large- scale dynamics.

Machine learning accelerated particle-in-cell plasma simulations

This work investigates how amortized solvers can be incorporated with PIC methods for simulations of plasmas and finds that this approach reduces the average number of required solver iterations by about 25% when simulating electron plasma oscillations.

L EARNING GENERAL - PURPOSE CNN- BASED SIMULA TORS FOR ASTROPHYSICAL TURBULENCE

It is found that the learned models outperform coarsened solvers on certain metrics, particularly in their ability to preserve high-frequency information at low resolution, and describe ways to improve generalization beyond the training distribution.

Meta-PDE: Learning to Solve PDEs Quickly Without a Mesh

A meta-learning based method which learns to rapidly solve problems from a distribution of related PDEs, which can be trained without supervision from expensive ground-truth data, does not require a mesh, and can even be used when the geometry and topology varies between tasks.

TNT: Vision Transformer for Turbulence Simulations

The Turbulence Neural Transformer (TNT), which is a learned simulator based on the transformer architecture, to predict turbulent dynamics on coarsened grids, and it is shown that TNT outperforms the state-of-the-art U-net simulator on several metrics.

References

SHOWING 1-10 OF 31 REFERENCES

Journal of Fluid Mechanics创刊50周年

流体力学杂志“Journal of Fluid Mechanics”由剑桥大学教授George

I and i

There is, I think, something ethereal about i —the square root of minus one, which seems an odd beast at that time—an intruder hovering on the edge of reality.

Physical Review Research 2

  • 023068
  • 2020

and T

  • Brox, in International Conference on Medical image computing and computer-assisted intervention
  • 2015

In Advances in Neural Information Processing Systems 15

and s

Geophysical Research Letters 47

  • e2020GL087776
  • 2020

Physics of Fluids 32

  • 025105
  • 2020

Geoscientific Model Development 11

  • 3999
  • 2018