2022/10/17 by Alberto Olmo, Ahmed S. Zamzam, Olmo, Alberto +5 · 1 citation
Computer Science · Engineering · Physics and Astronomy · #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn) #Generative Adversarial Networks and Image Synthesis #Lattice Boltzmann Simulation Studies #Model Reduction and Neural Networks
paper · pdf · doi:10.48550/arxiv.2210.09262
openalex publication_date 2022/10/17 · openalex created_date 2022/10/20 · openalex updated_date 2026/07/28
With the growing size and complexity of turbulent flow models, data compression approaches are of the utmost importance to analyze, visualize, or restart the simulations. Recently, in-situ autoencoder-based compression approaches have been proposed and shown to be effective at producing reduced representations of turbulent flow data. However, these approaches focus solely on training the model using point-wise sample reconstruction losses that do not take advantage of the physical properties of turbulent flows. In this paper, we show that training autoencoders with additional physics-informed regularizations, e.g., enforcing incompressibility and preserving enstrophy, improves the compression model in three ways: (i) the compressed data better conform to known physics for homogeneous isotropic turbulence without negatively impacting point-wise reconstruction quality, (ii) inspection of the gradients of the trained model uncovers changes to the learned compression mapping that can facilitate the use of explainability techniques, and (iii) as a performance byproduct, training losses are shown to converge up to 12x faster than the baseline model.