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

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.

References in corpus (1)

• Generating Videos with Scene Dynamics

Cited by in corpus (6)

• Embedding Hard Physical Constraints in Neural Network Coarse-Graining of 3D Turbulence
• NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework
• ML-LBM: Machine Learning Aided Flow Simulation in Porous Media
• Frequency-compensated PINNs for Fluid-dynamic Design Problems
• Connecting implicit and explicit large eddy simulations of two-dimensional turbulence through machine learning
• A Method for Tumor Treating Fields Fast Estimation