Addressing A Posteriori Performance Degradation in Neural Network Subgrid Stress Models
This addresses a critical reliability issue for researchers and engineers using neural network models in fluid dynamics simulations, though it is incremental as it builds on existing methods.
The paper tackled the performance gap between a priori and a posteriori evaluations in neural network subgrid stress models for Large Eddy Simulations, showing that combining training data augmentation with reduced input complexity significantly improves a posteriori robustness and alignment with a priori results.
Neural network subgrid stress models often have a priori performance that is far better than the a posteriori performance, leading to neural network models that look very promising a priori completely failing in a posteriori Large Eddy Simulations (LES). This performance gap can be decreased by combining two different methods, training data augmentation and reducing input complexity to the neural network. Augmenting the training data with two different filters before training the neural networks has no performance degradation a priori as compared to a neural network trained with one filter. A posteriori, neural networks trained with two different filters are far more robust across two different LES codes with different numerical schemes. In addition, by ablating away the higher order terms input into the neural network, the a priori versus a posteriori performance changes become less apparent. When combined, neural networks that use both training data augmentation and a less complex set of inputs have a posteriori performance far more reflective of their a priori evaluation.