Sustainable Energy and Artificial Intelligence

A numerical investigation of subgrid-scale stresses in turbulent channel flow using artificial intelligence techniques

Document Type : Original Article

Authors

Mohammad Reza Azarshab
Zeinab Pouransari

Department of Mechanical Engineering, Iran University of Science and Technology, Tehran, Iran.

https://doi.org/10.66224/seai.2510-1035
Abstract
This study presents a data-driven approach for modeling subgrid-scale (SGS) stresses in turbulent channel flow using a fully connected neural network (FCNN), also known as a multilayer perceptron (MLP). Our data-driven closure model is based on localized learning, and the FCNN architecture has a point-to-point mapping framework. The MLP-based SGS model is trained using direct numerical simulation (DNS) data of a turbulent channel flow at the bulk Reynolds number Re=4400, corresponding to the friction Reynolds number 〖 Re〗_τ=180. Performance of the FCCN model is assessed using a priori analysis in comparison with the filtered DNS (fDNS) data of the turbulent channel flow. Resolved flow statistics, including filtered velocity gradients and wall distance, are employed as input parameters for training the FCNN. To evaluate the significance of the feature inputs, we utilize random forest regression, which reveals that y^+ is a critical factor in predicting the output, which can reduce the compactional costs. In an a priori test, the model achieved a correlation coefficient exceeding 95% for the components of the SGS stress tensor, which have non-zero mean values. Finally, potential strategies for improving prediction accuracy and overall performance are explored. The findings demonstrate that the proposed FCNN can accurately reproduce key turbulence characteristics, offering a promising step toward efficient, AI-based turbulence modeling.

Keywords

Turbulent channel flow
FCNN
SGS modeling
a priori analysis
Random Forest regression
Subjects

  1. Frisch, U., & Kolmogorov, A. N. (1995). Turbulence: the legacy of AN Kolmogorov. Cambridge university press.

  2. Germano, M., Piomelli, U., Moin, P., & Cabot, W. H. (1991). A dynamic subgrid‐scale eddy viscosity model. Physics of fluids a: Fluid dynamics, 3(7), 1760-1765.

  3. Rasam, A., Pouransari, Z., Vervisch, L., & Johansson, A. V. (2016). Assessment of subgrid-scale stress statistics in non-premixed turbulent wall-jet flames. Journal of Turbulence, 17(5), 471-490.

  4. Pouransari, Z., & Rasam, A. (2023). Non-equilibrium extension of the explicit algebraic subgrid-scale stress model with application to turbulent channel flow at low Reynolds numbers. Physics of Fluids, 35(3).

  5. Smagorinsky, J. (1963). General circulation experiments with the primitive equations: I. The basic experiment. Monthly weather review, 91(3), 99-164.

  6. Deardorff, J. W. (1970). A numerical study of three-dimensional turbulent channel flow at large Reynolds numbers. Journal of Fluid Mechanics, 41(2), 453-480.

  7. Ghosal, S., Lund, T. S., Moin, P., & Akselvoll, K. (1995). A dynamic localization model for large-eddy simulation of turbulent flows. Journal of fluid mechanics, 286, 229-255.

  8. Meneveau, C., Lund, T. S., & Cabot, W. H. (1996). A Lagrangian dynamic subgrid-scale model of turbulence. Journal of fluid mechanics, 319, 353-385.

  9. Park, N., & Mahesh, K. (2009). Reduction of the Germano-identity error in the dynamic Smagorinsky model. Physics of Fluids, 21(6).

  10. Brunton, S. L., Noack, B. R., & Koumoutsakos, P. (2020). Machine learning for fluid mechanics. Annual review of fluid mechanics, 52(1), 477-508.

  11. Milano, M., & Koumoutsakos, P. (2002). Neural network modeling for near wall turbulent flow. Journal of Computational Physics, 182(1), 1-26.

  12. Erichson, N. B., Mathelin, L., Yao, Z., Brunton, S. L., Mahoney, M. W., & Kutz, J. N. (2020). Shallow neural networks for fluid flow reconstruction with limited sensors. Proceedings of the Royal Society A, 476(2238), 20200097.

  13. Fukami, K., Fukagata, K., & Taira, K. (2019). Super-resolution reconstruction of turbulent flows with machine learning. Journal of Fluid Mechanics, 870, 106-120.

  14. Maulik, R., & San, O. (2017). A neural network approach for the blind deconvolution of turbulent flows. Journal of Fluid Mechanics, 831, 151-181.

  15. Maulik, R., San, O., Rasheed, A., & Vedula, P. (2019). Subgrid modelling for two-dimensional turbulence using neural networks. Journal of Fluid Mechanics, 858, 122-144.

  16. Zhou, Z., He, G., Wang, S., & Jin, G. (2019). Subgrid-scale model for large-eddy simulation of isotropic turbulent flows using an artificial neural network. Computers & Fluids, 195, 104319.

  17. Sarghini, F., de Felice, G., & Santini, S. (2003). Neural networks based subgrid scale modeling in large eddy simulations. Computers & fluids, 32(1), 97-108.

  18. Gamahara, M., & Hattori, Y. (2017). Searching for turbulence models by artificial neural network. Physical Review Fluids, 2(5), 054604.

  19. Park, J., & Choi, H. (2021). Toward neural-network-based large eddy simulation: Application to turbulent channel flow. Journal of Fluid Mechanics, 914, A16.

  20. Pouransari, Z. (2023). Passive scalar small-scale anisotropy and mixing characteristics in magnetohydrodynamic turbulent channel flow. Physics of Fluids, 35(10).

  21. Cant, S. (2001). SB Pope, Turbulent Flows, Cambridge University Press, Cambridge, UK, 2000, 771 pp. Combustion and Flame, 125(4), 1361-1362.

  22. Sagaut, P., & Grohens, R. (1999). Discrete filters for large eddy simulation. International Journal for Numerical Methods in Fluids, 31(8), 1195-1220.

  23. Majd, B. K., & Pouransari, Z. (2024). Reynolds number effect on the Lagrangian evolution of hairpin vortices in turbulent channel flow. Journal of Turbulence, 25(7), 207-224.

  24. Sanhueza, R. D., Smit, S. H., Peeters, J. W., & Pecnik, R. (2023). Machine learning for RANS turbulence modeling of variable property flows. Computers & Fluids, 255, 105835.

  25. Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. Peerj computer science, 7, e623.

  26. Montesinos López, O. A., Montesinos López, A., & Crossa, J. (2022). Overfitting, model tuning, and evaluation of prediction performance. In Multivariate statistical machine learning methods for genomic prediction (pp. 109-139). Cham: Springer International Publishing.

  27. Mandler, H., & Weigand, B. (2023). Feature importance in neural networks as a means of interpretation for data-driven turbulence models. Computers & Fluids, 265, 105993.

  28. Rasam, A., & Najarian, A. (2024). Modeling the subgrid-scale kinetic energy in a turbulent channel flow using artificial neural network. AUT Journal of Mechanical Engineering, 8(1), 19-30.

Sustainable Energy and Artificial Intelligence
Volume 2, Issue 1
Winter 2026
Pages 37-45

  • Receive Date 01 October 2025
  • Revise Date 14 November 2025
  • Accept Date 24 November 2025
  • First Publish Date 24 November 2025

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us