• 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
TLDR
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 Coarse Models for Efficient Turbulence Simulation
TLDR
The proposed model can simulate turbulent dynamics more accurately than classical numerical solvers at the same low resolutions across various scientifically relevant metrics, and it is concluded that simple design choices can offer stability and robust generalization.
Machine learning accelerated particle-in-cell plasma simulations
Particle-In-Cell (PIC) methods are frequently used for kinetic, high-fidelity simulations of plasmas. Implicit formulations of PIC algorithms feature strong conservation properties, up to numerical
Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
There is a growing interest in developing data-driven subgrid-scale (SGS) models for largeeddy simulation (LES) using machine learning (ML). In a priori (offline) tests, some recent studies have
Error-Correcting Neural Networks for Semi-Lagrangian Advection in the Level-Set Method
TLDR
A novel machine-learning-augmented transport algorithm that operates alongside selective redistancing and alternates with conventional advection to keep the adjusted interface trajectory smooth is presented, which believes all the above assets make the framework attractive to parallel level-set algorithms.
Graph neural networks for laminar flow prediction around random two-dimensional shapes
In the recent years, the domain of fast flow field prediction has been vastly dominated by pixel-based convolutional neural networks. Yet, the recent advent of graph convolutional neural networks
Accelerating GMRES with Deep Learning in Real-Time
TLDR
A real-time machine learning algorithm that can be used to accelerate the time-to-solution for GMRES and develops networks which are capable of learning non-local relationships perform well, without needing to be scaled with the input problem size, making them good candidates for the extremely large problems encountered in high-performance computing.
Predicting Mechanically Driven Full-Field Quantities of Interest with Deep Learning-Based Metamodels
TLDR
The work presented in this paper made a significant extension to the Mechanical MNIST dataset designed to enable the investigation of full field QoI prediction, and investigated multiple Deep Neural Network architectures and subsequently established strong baseline performance for predicting full-field QOI.
Learning Transport Processes with Machine Intelligence
TLDR
A machine learning model is built using simple components and following a few well established practices and is capable of learning latent representations of the transport process substantially closer to the ground truth than expected from the nominal error characterising the data, leading to sound generalisation properties.
Closed-form discovery of structural errors in models of chaotic systems by integrating Bayesian sparse regression and data assimilation
TLDR
This work introduces a framework named MEDIDA: Model Error Discovery with Interpretability and Data Assimilation, and demonstrates the excellent performance of MEDIDA in discovering different types of structural/parametric model errors, representing different type of missing physics, using noise-free and noisy observations.
...
1
2
...

References

SHOWING 1-10 OF 33 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
{m
TLDR
The master programme in Applied Geology aims to provide comprehensive knowledge based on various branches of Geology, with special focus on Applied geology subjects in the areas of Geomorphology, Structural geology, Hydrogeology, Petroleum Geologists, Mining Geology), Remote Sensing and Environmental geology.
Proceedings of the National Academy of Sciences, USA
TLDR
The song below is a talking blues in the style of Woody Guthrie, written by Joel Herskowitz, a pediatric neurologist working in Boston, and sung by Joel and his brother Ira.
I and i
TLDR
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
‘A’
  • P. Alam
  • Composites Engineering: An A–Z Guide
  • 2021
Annual Review of Fluid Mechanics 52
  • 477
  • 2020
Experiment tracking with weights and biases,
  • wandb.com
  • 2020
...
1
2
3
4
...