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
• ISSN: 1070-6631; 1089-7666
• DOI: 10.1063/5.0199175

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 data-driven turbulence modeling due to its merit of non-derivativeness. However, the training accuracy of the ensemble method can be affected by the linearization assumption and sample collapse issue. Given these difficulties, we introduce the hybrid ensemble variational method, which inherits the merits of the ensemble method in non-derivativeness and the variational method in nonlinear analysis. Moreover, a covariance inflation scheme is proposed based on convergence states to alleviate the detrimental effects of sample collapse. The capability of the ensemble variational method in model learning is tested for flows in a square duct, flows over periodic hills, and flows around the S809 airfoil, with increasing complexity in the training data from direct observation to sparse indirect observation. Our results show that the ensemble variational method can learn relatively accurate neural network-based turbulence models in scenarios of small ensemble size and sample variances, compared to the ensemble Kalman method. It highlights the superiority of the ensemble variational method in practical applications, since small ensemble sizes can reduce computational costs, and small sample variance can ensure the training robustness by avoiding nonphysical samples of Reynolds stresses.