Articles | Volume 14, issue 6
Geosci. Model Dev., 14, 3769–3788, 2021
https://doi.org/10.5194/gmd-14-3769-2021
Geosci. Model Dev., 14, 3769–3788, 2021
https://doi.org/10.5194/gmd-14-3769-2021

Development and technical paper 24 Jun 2021

Development and technical paper | 24 Jun 2021

Development of a large-eddy simulation subgrid model based on artificial neural networks: a case study of turbulent channel flow

Robin Stoffer et al.

Model code and software

Used scripts and model code Robin Stoffer https://doi.org/10.5281/zenodo.4767902

microhh/microhh: 1.0.0 (Version 1.0.0) C. C. van Heerwaarden, B. J. H. van Stratum, and T. Heus https://doi.org/10.5281/zenodo.822842

Download
Short summary
Turbulent flows are often simulated with the large-eddy simulation (LES) technique, which requires subgrid models to account for the smallest scales. Current subgrid models often require strong simplifying assumptions. We therefore developed a subgrid model based on artificial neural networks, which requires fewer assumptions. Our data-driven SGS model showed high potential in accurately representing the smallest scales but still introduced instability when incorporated into an actual LES.