Robust deep learning for emulating turbulent viscosities

@article{Patil2021RobustDL,
  title={Robust deep learning for emulating turbulent viscosities},
  author={Aakash Patil and Jonathan Viquerat and Aur{\'e}lien Larcher and George El Haber and Elie Hachem},
  journal={Physics of Fluids},
  year={2021}
}
From the simplest models to complex deep neural networks, modeling turbulence with machine learning techniques still offers multiple challenges. In this context, the present contribution proposes a robust strategy using patch-based training to learn turbulent viscosity from flow velocities, and demonstrates its efficient use on the Spalart-Allmaras turbulence model. Training datasets are generated for flow past twodimensional obstacles at high Reynolds numbers and used to train an auto-encoder… Expand
1 Citations
Graph neural networks for laminar flow prediction around random 2D 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 networksExpand

References

SHOWING 1-10 OF 64 REFERENCES
Development of Deep Learning Methods for Inflow Turbulence Generation.
TLDR
Though instantaneous snapshots of the target flow are required for training, these a priori simulations suggest that the deep learning methods for generating inflow turbulence are one of the possible alternatives to existing methods. Expand
Compressed Convolutional LSTM: An Efficient Deep Learning framework to Model High Fidelity 3D Turbulence
High-fidelity modeling of turbulent flows is one of the major challenges in computational physics, with diverse applications in engineering, earth sciences and astrophysics, among many others. TheExpand
Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
There exists significant demand for improved Reynolds-averaged Navier–Stokes (RANS) turbulence models that are informed by and can represent a richer set of turbulence physics. This paper presents aExpand
Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
TLDR
A novel model is developed that could generate time-varying fully developed flow for a long time and is in good agreement with those of the DNS, proving the usefulness of unsupervised learning in the generation of synthetic turbulence fields. Expand
Deep Neural Networks for Data-Driven Turbulence Models
TLDR
This work defines the perfect LES formulation including the discretization operators and derive the associated perfect closure terms and designs and trains artificial neural networks based on local convolution filters to predict the underlying unknown non-linear mapping from the coarse grid quantities to the closure terms without a priori assumptions. Expand
Synthetic turbulent inflow generator using machine learning
TLDR
It is shown that the present machine-learned turbulent inflow generator is free from the spurious periodicity, unlike the conventional driver DNS in a periodic domain, and can maintain the turbulent channel flow for a long time period sufficient to accumulate turbulent statistics, with much lower computational cost than the corresponding driver simulation. Expand
A neural network approach for the blind deconvolution of turbulent flows
TLDR
The proposed blind deconvolution network performs exceptionally well in the a priori testing of two-dimensional Kraichnan, three-dimensional Kolmogorov and compressible stratified turbulence test cases, and shows promise in forming the backbone of a physics-augmented data-driven closure for the Navier–Stokes equations. Expand
Recent progress in augmenting turbulence models with physics-informed machine learning
In view of the long stagnation in traditional turbulence modeling, researchers have attempted using machine learning to augment turbulence models. This paper presents some of the recent progresses inExpand
Super-resolution reconstruction of turbulent flows with machine learning
We use machine learning to perform super-resolution analysis of grossly under-resolved turbulent flow field data to reconstruct the high-resolution flow field. Two machine learning models areExpand
Machine Learning-augmented Predictive Modeling of Turbulent Separated Flows over Airfoils
TLDR
By incorporating data that can reveal the form of the innate model discrepancy, the applicability of data-driven turbulence models can be extended to more general flows. Expand
...
1
2
3
4
5
...