Convolutional neural network models and interpretability for the anisotropic reynolds stress tensor in turbulent one-dimensional flows

• Published in: Journal of turbulence 2022-02, Vol.23 (1-2), p.1-28
• Main Authors: Sáez de Ocáriz Borde, Haitz, Sondak, David, Protopapas, Pavlos
• Format: Article
• Language: English
• Subjects: convolutional neural networks; deep learning; interpretability; Reynolds-averaged Navier-Stokes; Turbulence modelling
• ISSN: 1468-5248; 1468-5248
• DOI: 10.1080/14685248.2021.1999459

The Reynolds-averaged Navier-Stokes (RANS) equations are widely used in turbulence applications. They require accurately modelling the anisotropic Reynolds stress tensor, for which traditional Reynolds stress closure models only yield reliable results in some flow configurations. In the last few years, there has been a surge of work aiming at using data-driven approaches to tackle this problem. The majority of previous work has focused on the development of fully connected networks for modelling the anisotropic Reynolds stress tensor. In this paper, we expand upon recent work for turbulent channel flow and develop new convolutional neural network (CNN) models that are able to accurately predict the normalised anisotropic Reynolds stress tensor. We apply the new CNN model to a number of one-dimensional turbulent flows. Additionally, we present interpretability techniques that help drive the model design and provide guidance on the model behaviour in relation to the underlying physics.