Ensemble variational method with adaptive covariance inflation for learning neural network-based turbulence models

• Published in: Physics of fluids (1994) Vol. 36; no. 3
• Main Authors: Luo, Qingyong, Zhang, Xin-Lei, He, Guowei
• Format: Journal Article
• Language: English
• Published: Melville American Institute of Physics 01.03.2024
• Subjects: Anisotropy; Covariance; Eddy viscosity; Learning; Neural networks; Nonlinear analysis; Reynolds stress; Robustness (mathematics); Sample variance; Tensors; Training; Turbulence models

This work introduces an ensemble variational method with adaptive covariance inflation for learning nonlinear eddy viscosity turbulence models where the Reynolds stress anisotropy is represented with tensor-basis neural networks. The ensemble-based method has emerged as an important alternative to d...