The University of Southampton
University of Southampton Institutional Repository

The influence of adversarial training on turbulence closure modeling

The influence of adversarial training on turbulence closure modeling
The influence of adversarial training on turbulence closure modeling
Over the last years, fundamental advancements in deep learning frameworks combined with the availability of large highly-resolved datasets, as well as the exponential improvement in computer hardware performance have shown great promise to move beyond classical equation-based models for the turbulence closure. Deep convolutional neural networks (CNN) can be used to super-resolve low-resolution simulations, thus they become attractive for large eddy simulation subfilter-scale modeling. However, these models often lack generalization capabilities and cannot guarantee fields with high-wavenumber details. To tackle those problems, the use of generative adversarial networks (GAN), which are composed of two competing neural networks (a generator and a discriminator) has been proposed. Despite the remarkable performance of GAN in single-image super-reconstruction, its application in turbulence modeling applications is relatively unexplored. In this work, the contribution of adversarial training is assessed by comparing two types of deep neural networks: a supervised CNN-type model and a semi-supervised GAN-based model. This study demonstrates the ability of the GAN architecture to produce high-quality super-reconstructed fields compared to standard deep convolutional networks, enhancing subgrid physical structures. The prolonged adversarial training leads to extracting underlying small-dimensional features in a semi-supervised manner and, consequently, improved turbulence statistics. Finally, it is shown that the propensity of the GAN training to run into convergence oscillations can be limited by a proper selection of the learning rate for both generator and discriminator.
American Institute of Aeronautics and Astronautics
Nista, L.
3c47ceab-cf95-418e-a8b3-b1926403faf1
Schumann, C.
9246a4bc-a8df-4663-a033-2468bfe0db59
Scialabba, G.
3e339b54-1898-4900-8643-7038115dbdcb
Grenga, T.
be0eba30-74b5-4134-87e7-3a2d6dd3836f
Pitsch, H.
3dc0eb6e-deca-4742-98a1-f0cdd62ff8b8
Attili, A.
359dfd2e-9503-4a12-88ee-a8f16579a107
Nista, L.
3c47ceab-cf95-418e-a8b3-b1926403faf1
Schumann, C.
9246a4bc-a8df-4663-a033-2468bfe0db59
Scialabba, G.
3e339b54-1898-4900-8643-7038115dbdcb
Grenga, T.
be0eba30-74b5-4134-87e7-3a2d6dd3836f
Pitsch, H.
3dc0eb6e-deca-4742-98a1-f0cdd62ff8b8
Attili, A.
359dfd2e-9503-4a12-88ee-a8f16579a107

Nista, L., Schumann, C., Scialabba, G., Grenga, T., Pitsch, H. and Attili, A. (2022) The influence of adversarial training on turbulence closure modeling. In AIAA SciTech Forum 2022. American Institute of Aeronautics and Astronautics.. (doi:10.2514/6.2022-0185).

Record type: Conference or Workshop Item (Paper)

Abstract

Over the last years, fundamental advancements in deep learning frameworks combined with the availability of large highly-resolved datasets, as well as the exponential improvement in computer hardware performance have shown great promise to move beyond classical equation-based models for the turbulence closure. Deep convolutional neural networks (CNN) can be used to super-resolve low-resolution simulations, thus they become attractive for large eddy simulation subfilter-scale modeling. However, these models often lack generalization capabilities and cannot guarantee fields with high-wavenumber details. To tackle those problems, the use of generative adversarial networks (GAN), which are composed of two competing neural networks (a generator and a discriminator) has been proposed. Despite the remarkable performance of GAN in single-image super-reconstruction, its application in turbulence modeling applications is relatively unexplored. In this work, the contribution of adversarial training is assessed by comparing two types of deep neural networks: a supervised CNN-type model and a semi-supervised GAN-based model. This study demonstrates the ability of the GAN architecture to produce high-quality super-reconstructed fields compared to standard deep convolutional networks, enhancing subgrid physical structures. The prolonged adversarial training leads to extracting underlying small-dimensional features in a semi-supervised manner and, consequently, improved turbulence statistics. Finally, it is shown that the propensity of the GAN training to run into convergence oscillations can be limited by a proper selection of the learning rate for both generator and discriminator.

This record has no associated files available for download.

More information

e-pub ahead of print date: 29 December 2021
Published date: 3 January 2022
Additional Information: Funding Information: The research leading to these results has received funding from the European Union’s Horizon 2020 research and innovation program under the Center of Excellence in Combustion (CoEC) project, grant agreement no. 952181. The authors gratefully acknowledge the computing resources from the DEEP-EST project, which received funding from the European Union’s Horizon 2020 research and innovation programme under the grant agreement no. 754304 and the computing resources granted by RWTH Aachen University under project rwth0658. We thank Mr. Rocco Sedona for the support in the porting of the application to DEEP-EST. Publisher Copyright: © 2022, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.
Venue - Dates: AIAA Science and Technology Forum and Exposition (AIAA SciTech Forum 2022), , San Diego, United States, 2022-01-03 - 2022-01-07

Identifiers

Local EPrints ID: 478561
URI: http://eprints.soton.ac.uk/id/eprint/478561
PURE UUID: ef413104-8dff-41e2-b371-ac1856fd7f57
ORCID for T. Grenga: ORCID iD orcid.org/0000-0002-9465-9505

Catalogue record

Date deposited: 04 Jul 2023 18:02
Last modified: 18 Mar 2024 04:10

Export record

Altmetrics

Contributors

Author: L. Nista
Author: C. Schumann
Author: G. Scialabba
Author: T. Grenga ORCID iD
Author: H. Pitsch
Author: A. Attili

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×