Lat-Net: Compressing Lattice Boltzmann Flow Simulations using Deep Neural Networks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Efficient Neural NetworkSimilar Papers 제목 키워드 기반
A data-driven proxy to Stoke's flow in porous media
The objective for this work is to develop a data-driven proxy to high-fidelity numerical flow simulations using digital images. The proposed model can capture the flow field and permeability in a large verity of digital …
Simulating the Hubbard Model with Equivariant Normalizing Flows
Generative models, particularly normalizing flows, have shown exceptional performance in learning probability distributions across various domains of physics, including statistical mechanics, collider physics, and lattic…
Optimal Lattice Boltzmann Closures through Multi-Agent Reinforcement Learning
The Lattice Boltzmann method (LBM) offers a powerful and versatile approach to simulating diverse hydrodynamic phenomena, spanning microfluidics to aerodynamics. The vast range of spatiotemporal scales inherent in these …
Computational EfficiencyMulti-agent Reinforcement Learningreinforcement-learningReinforcement LearningToward Scalable Normalizing Flows for the Hubbard Model
Normalizing flows have recently demonstrated the ability to learn the Boltzmann distribution of the Hubbard model, opening new avenues for generative modeling in condensed matter physics. In this work, we investigate the…
Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks
We present a new class of equivariant neural networks, hereby dubbed Lattice-Equivariant Neural Networks (LENNs), designed to satisfy local symmetries of a lattice structure. Our approach develops within a recently intro…