Deep Learning for Subgrid‐Scale Turbulence Modeling in Large‐Eddy Simulations of the Convective Atmospheric Boundary Layer
Deep Learning for Subgrid‐Scale Turbulence Modeling in Large‐Eddy Simulations of the Convective Atmospheric Boundary Layer
复制标题
DOI：
10.1029/2021ms002847
复制
发表时间：
2022-05
影响因子：
6.8
通讯作者：
Yu Cheng;M. Giometto;Pit Kauffmann;Ling Lin;Chengyu Cao;Cody Zupnick;Harold Li;Qi Li;Y. Huang;R. Abernathey;P. Gentine
中科院分区：
文献类型：
--
作者：
Yu Cheng;M. Giometto;Pit Kauffmann;Ling Lin;Chengyu Cao;Cody Zupnick;Harold Li;Qi Li;Y. Huang;R. Abernathey;P. Gentine
在大涡模拟中，亚网格尺度（SGS）过程被参数化为过滤网格尺度变量的函数。一阶代数SGS模型基于涡粘性假设，这并不总是适用于湍流。在这里，我们应用有监督的深度神经网络（DNN）从摩擦雷诺数Re τ高达1243的对流边界层直接数值模拟中的一组相邻粗粒速度中学习SGS应力，而无需调用涡粘性假设。与Smagorinsky模型和Smagorinsky-Bardina混合模型相比，DNN模型在表面和混合层中的SGS应力之间产生更高的相关性，并且可以应用于不同的网格分辨率和从接近中性到非常不稳定的各种稳定性条件。DNN模型在应用于大气边界层的大涡模拟时，可以在后验（在线）测试中捕获湍流的关键统计数据。
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 Reτ 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.