Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks
This addresses a critical bottleneck in computational fluid dynamics for engineering applications, though it is an incremental improvement using existing deep learning techniques.
The paper tackles the computational and memory demands of Lattice Boltzmann flow simulations by introducing Lat-Net, a deep neural network method that compresses both time and memory usage, achieving generalization to large grids and complex geometries while maintaining accuracy.
Computational Fluid Dynamics (CFD) is a hugely important subject with applications in almost every engineering field, however, fluid simulations are extremely computationally and memory demanding. Towards this end, we present Lat-Net, a method for compressing both the computation time and memory usage of Lattice Boltzmann flow simulations using deep neural networks. Lat-Net employs convolutional autoencoders and residual connections in a fully differentiable scheme to compress the state size of a simulation and learn the dynamics on this compressed form. The result is a computationally and memory efficient neural network that can be iterated and queried to reproduce a fluid simulation. We show that once Lat-Net is trained, it can generalize to large grid sizes and complex geometries while maintaining accuracy. We also show that Lat-Net is a general method for compressing other Lattice Boltzmann based simulations such as Electromagnetism.