From Zero to Turbulence: Generative Modeling for 3D Flow Simulation
This work addresses the high computational cost of 3D turbulent flow simulations in computational fluid dynamics, offering a novel generative approach that could accelerate simulations, though it is incremental in the context of existing surrogate models.
The paper tackles the problem of expensive 3D turbulent flow simulations by proposing a generative model that directly learns the manifold of all possible turbulent flow states, eliminating the need for initial flow states; it introduces a high-resolution 3D turbulence dataset and shows that the model captures the distribution of turbulent flows from unseen objects, generating realistic samples for downstream applications.
Simulations of turbulent flows in 3D are one of the most expensive simulations in computational fluid dynamics (CFD). Many works have been written on surrogate models to replace numerical solvers for fluid flows with faster, learned, autoregressive models. However, the intricacies of turbulence in three dimensions necessitate training these models with very small time steps, while generating realistic flow states requires either long roll-outs with many steps and significant error accumulation or starting from a known, realistic flow state - something we aimed to avoid in the first place. Instead, we propose to approach turbulent flow simulation as a generative task directly learning the manifold of all possible turbulent flow states without relying on any initial flow state. For our experiments, we introduce a challenging 3D turbulence dataset of high-resolution flows and detailed vortex structures caused by various objects and derive two novel sample evaluation metrics for turbulent flows. On this dataset, we show that our generative model captures the distribution of turbulent flows caused by unseen objects and generates high-quality, realistic samples amenable for downstream applications without access to any initial state.