Department of Earth and Environmental Engineering Columbia University New York NY USA
Department of Civil Engineering and Engineering Mechanics Columbia University New York NY USA
Capstone Project at Data Science Institute Columbia University New York NY USA
School of Civil and Environmental Engineering Cornell University Ithaca NY USA
Department of Earth and Environmental Sciences Columbia University Palisades NY USA
Department of Earth and Environmental Engineering Columbia University New York NY USA, Department of Earth and Environmental Sciences Columbia University Palisades NY USA
In large‐eddy simulations, subgrid‐scale (SGS) processes are parameterized as a function of filtered grid‐scale variables. First‐order, algebraic SGS models are based on the eddy‐viscosity assumption, which does not always hold for turbulence. Here we apply supervised deep neural networks (DNNs) to learn SGS stresses from a set of neighboring coarse‐grained velocity from direct numerical simulations of the convective boundary layer at friction Reynolds numbers Re τ up to 1243 without invoking the eddy‐viscosity assumption. The DNN model was found to produce higher correlation between SGS stresses compared to the Smagorinsky model and the Smagorinsky‐Bardina mixed model in the surface and mixed layers and can be applied to different grid resolutions and various stability conditions ranging from near neutral to very unstable. The DNN model can capture key statistics of turbulence in a posteriori (online) tests when applied to large‐eddy simulations of the atmospheric boundary layer.
Cheng, Yu, et al. "Deep Learning for Subgrid‐Scale Turbulence Modeling in Large‐Eddy Simulations of the Convective Atmospheric Boundary Layer." Journal of Advances in Modeling Earth Systems, vol. 14, no. 5, May. 2022. https://doi.org/10.1029/2021MS002847
Cheng, Yu, Giometto, Marco G., Kauffmann, Pit, et al., "Deep Learning for Subgrid‐Scale Turbulence Modeling in Large‐Eddy Simulations of the Convective Atmospheric Boundary Layer," Journal of Advances in Modeling Earth Systems 14, no. 5 (2022), https://doi.org/10.1029/2021MS002847
@article{osti_1869503,
author = {Cheng, Yu and Giometto, Marco G. and Kauffmann, Pit and Lin, Ling and Cao, Chen and Zupnick, Cody and Li, Harold and Li, Qi and Huang, Yu and Abernathey, Ryan and others},
title = {Deep Learning for Subgrid‐Scale Turbulence Modeling in Large‐Eddy Simulations of the Convective Atmospheric Boundary Layer},
annote = {Abstract In large‐eddy simulations, subgrid‐scale (SGS) processes are parameterized as a function of filtered grid‐scale variables. First‐order, algebraic SGS models are based on the eddy‐viscosity assumption, which does not always hold for turbulence. Here we apply supervised deep neural networks (DNNs) to learn SGS stresses from a set of neighboring coarse‐grained velocity from direct numerical simulations of the convective boundary layer at friction Reynolds numbers Re τ up to 1243 without invoking the eddy‐viscosity assumption. The DNN model was found to produce higher correlation between SGS stresses compared to the Smagorinsky model and the Smagorinsky‐Bardina mixed model in the surface and mixed layers and can be applied to different grid resolutions and various stability conditions ranging from near neutral to very unstable. The DNN model can capture key statistics of turbulence in a posteriori (online) tests when applied to large‐eddy simulations of the atmospheric boundary layer. },
doi = {10.1029/2021MS002847},
url = {https://www.osti.gov/biblio/1869503},
journal = {Journal of Advances in Modeling Earth Systems},
issn = {ISSN 1942-2466},
number = {5},
volume = {14},
place = {United States},
publisher = {American Geophysical Union (AGU)},
year = {2022},
month = {05}}