Latent-space Physics: Towards Learning the Temporal Evolution of Fluid Flow
This addresses the challenge of high-dimensional fluid flow simulation for computational physics applications, representing a novel method for a known bottleneck.
The authors tackled the problem of predicting temporal evolution of fluid flows (Navier-Stokes problems) by proposing an LSTM-based method that operates in latent spaces, achieving more than two orders of magnitude speed-up compared to traditional pressure solvers.
We propose a method for the data-driven inference of temporal evolutions of physical functions with deep learning. More specifically, we target fluid flows, i.e. Navier-Stokes problems, and we propose a novel LSTM-based approach to predict the changes of pressure fields over time. The central challenge in this context is the high dimensionality of Eulerian space-time data sets. We demonstrate for the first time that dense 3D+time functions of physics system can be predicted within the latent spaces of neural networks, and we arrive at a neural-network based simulation algorithm with significant practical speed-ups. We highlight the capabilities of our method with a series of complex liquid simulations, and with a set of single-phase buoyancy simulations. With a set of trained networks, our method is more than two orders of magnitudes faster than a traditional pressure solver. Additionally, we present and discuss a series of detailed evaluations for the different components of our algorithm.