Abstract
We examine the application of neural network-based methods to improve the accuracy of large eddy simulations of incompressible turbulent flows. The networks are trained to learn a mapping between flow features and the subgrid scales, and applied locally and instantaneously—in the same way as traditional physics-based subgrid closures. Models that use only the local resolved strain rate are poorly correlated with the actual subgrid forces obtained from filtering direct numerical simulation data. We see that highly accurate models in a priori testing are inaccurate in forward calculations, owing to the preponderance of numerical errors in implicitly filtered large eddy simulations. A network that accounts for the discretization errors is trained and found to be unstable in a posteriori testing. We identify a number of challenges that the approach faces, including a distribution shift that affects networks that fail to account for numerical errors.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
References
K. Duraisamy, G. Iaccarino, H. Xiao, Turbulence modeling in the age of data. Annu. Rev. Fluid Mech. 51, 357–377 (2019)
S.L. Brunton, B.R. Noack, P. Koumoutsakos, Machine learning for fluid mechanics. Annu. Rev. Fluid Mech. 52, 477–508 (2020)
M. Germano, U. Piomelli, P. Moin, W.H. Cabot, A dynamic subgrid-scale eddy viscosity model. Phys. Fluids A Fluid Dyn. 3(7), 1760–1765 (1991). https://doi.org/10.1063/1.857955
C. Xie, J. Wang, H. Li, M. Wan, S. Chen, Artificial neural network mixed model for large eddy simulation of compressible isotropic turbulence. Phys. Fluids (2019). https://doi.org/10.1063/1.5110788
Z. Zhou, G. He, S. Wang, G. Jin, Subgrid-scale model for large-eddy simulation of isotropic turbulent flows using an artificial neural network. Comput. Fluids 195, 104319 (2019)
J. Park, H. Choi, Toward neural-network-based large eddy simulation: application to turbulent channel flow. J. Fluid Mech. 914, A16 (2021). https://doi.org/10.1017/jfm.2020.931
R. Stoffer, C.M. van Leeuwen, D. Podareanu, V. Codreanu, M.A. Veerman, M. Janssens, O.K. Hartogensis, C.C. van Heerwaarden, Development of a large-eddy simulation subgrid model based on artificial neural networks: a case study of turbulent channel flow. Geosci. Model Dev. 14(6), 3769–3788 (2021). https://doi.org/10.5194/gmd-14-3769-2021
M. Gamahara, Y. Hattori, Searching for turbulence models by artificial neural network. Phys. Rev. Fluids (2017). https://doi.org/10.1103/PhysRevFluids.2.054604
M. Kang, Y. Jeon, D. You, Neural-network-based mixed subgrid-scale model for turbulent flow (2022). arXiv preprint arXiv:2205.10181
J. Bardina, J. Ferziger, W.C. Reynolds, Improved subgrid-scale models for large-eddy simulation. in 13th Fluid and Plasmadynamics Conference, p. 1357 (1980)
J. Ling, A. Kurzawski, J. Templeton, Reynolds averaged turbulence modelling using deep neural networks with embedded invariance. J. Fluid Mech. 807, 155–166 (2016). https://doi.org/10.1017/jfm.2016.615
O.V. Vasilyev, T.S. Lund, P. Moin, A general class of commutative filters for les in complex geometries. J. Comput. Phys. 146(1), 82–104 (1998). https://doi.org/10.1006/jcph.1998.6060
T.S. Lund, The use of explicit filters in large eddy simulation. Comput. Math. Appl. 46(4), 603–616 (2003). https://doi.org/10.1016/S0898-1221(03)90019-8
X.I.A. Yang, K.P. Griffin, Grid-point and time-step requirements for direct numerical simulation and large-eddy simulation. Phys. Fluids 33(1), 015108 (2021)
X. Glorot, A. Bordes, Y. Bengio, Deep sparse rectifier neural networks. in G. Gordon, D. Dunson, M. Dudík, editors, Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, volume 15 of Proceedings of Machine Learning Research, pp. 315–323, Fort Lauderdale, FL, USA, 11–13 Apr. PMLR (2011). https://proceedings.mlr.press/v15/glorot11a.html
B. Vreman, B. Geurts, H. Kuerten, Comparision of numerical schemes in large-eddy simulation of the temporal mixing layer. Int. J. Numer. Methods Fluids 22(4), 297–311 (1996)
S.P. Domino, Sierra low mach module: Nalu theory manual 1.0. SAND2015-3107W, Sandia National Laboratories Unclassified Unlimited Release (2015). https://github.com/NaluCFD/Nalu
J.H. Ferziger, M. Perić, R.L. Street, Computational Methods for Fluid Dynamics, vol. 3 (Springer, 2002)
S. Ghosal, An analysis of numerical errors in large-eddy simulations of turbulence. J. Comput. Phys. 125(1), 187–206 (1996)
R.S. Rogallo, P. Moin, Numerical simulation of turbulent flows. Annu. Rev. Fluid Mech. 16(1), 99–137 (1984)
J. Quinonero-Candela, M. Sugiyama, A. Schwaighofer, N.D. Lawrence, Dataset Shift in Machine Learning (MIT Press, 2008)
H.J. Bae, A. Lozano-Durán, Numerical and modeling error assessment of large-eddy simulation using direct-numerical-simulation-aided large-eddy simulation (2022). arXiv preprint arXiv:2208.02354
C. Geng, G. He, Y. Wang, C. Xu, A. Lozano-Durán, J.M. Wallace, Taylor’s hypothesis in turbulent channel flow considered using a transport equation analysis. Phys. Fluids (2015). https://doi.org/10.1063/1.4908070
A. Lozano-Durán, H.J. Bae, Building-block-flow wall model for large-eddy simulation (2022). arXiv preprint arXiv:2211.07879
Acknowledgements
The authors gratefully acknowledge discussions with Adrian Lozano-Durán, Tim Flint, Michael Patrick Whitmore and Sanjeeb Bose. This article has been authored by an employee of National Technology & Engineering Solutions of Sandia, LLC under contract no. DE-NA0003525 with the US Department of Energy (DOE). The employee owns all right, title and interest in and to the article and is solely responsible for its contents. The US Government retains and the publisher, by accepting the article for publication, acknowledges that the US Government retains a non-exclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this article or allow others to do so, for US Government purposes. The DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan SAND2022-16617 B (https://www.energy.gov/downloads/doe-public-access-plan).
Author information
Authors and Affiliations
Contributions
MB and GI did conceptualization; MB, SPD, GI did the data curation; MB and GI performed formal analysis; GI did the funding acquisition; MB, SPD, GI were involved in investigation and methodology; GI supervised the study; MB did writing—original draft; SPD and GI performed writing—review & editing.
Corresponding author
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Benjamin, M., Domino, S.P. & Iaccarino, G. Neural networks for large eddy simulations of wall-bounded turbulence: numerical experiments and challenges. Eur. Phys. J. E 46, 55 (2023). https://doi.org/10.1140/epje/s10189-023-00314-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1140/epje/s10189-023-00314-6