Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks

TL;DR

Lat-Net introduces a neural network-based approach that significantly reduces the computational and memory requirements of Lattice Boltzmann fluid simulations, enabling efficient and scalable CFD modeling.

Contribution

The paper presents Lat-Net, a novel deep learning method employing autoencoders and residual connections to compress and accelerate Lattice Boltzmann simulations.

Findings

Lat-Net generalizes to larger grids and complex geometries.

It maintains accuracy while reducing resource usage.

Applicable to other Lattice Boltzmann simulations like Electromagnetism.

Abstract

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.