Multi-Task Learning based Convolutional Models with Curriculum Learning for the Anisotropic Reynolds Stress Tensor in Turbulent Duct Flow

The Reynolds-averaged Navier-Stokes (RANS) equations require accurate modeling of the anisotropic Reynolds stress tensor, for which traditional closure models only give good results in certain flow configurations. Researchers have started using machine learning approaches to address this problem. In this work we build upon recent convolutional neural network architectures used for turbulence modeling and propose a multi-task learning based fully convolutional neural network that is able to accurately predict the normalized anisotropic Reynolds stress tensor for turbulent duct flow. Furthermore, we also explore the application of curriculum learning to data-driven turbulence modeling.