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

arXiv: https://arxiv.org/abs/1705.09036 · HTML: https://mlsanity.com/paper/1705.09036/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2017.

## Built on by (most cited first, 11 of 11)

- [XLB: A differentiable massively parallel lattice Boltzmann library in Python](https://mlsanity.com/paper/2311.16080/) (2023)
- [Lettuce: PyTorch-based Lattice Boltzmann Framework](https://mlsanity.com/paper/2106.12929/) (2021)
- [Physics Informed RNN-DCT Networks for Time-Dependent Partial Differential Equations](https://mlsanity.com/paper/2202.12358/) (2022)
- [RANS-PINN based Simulation Surrogates for Predicting Turbulent Flows](https://mlsanity.com/paper/2306.06034/) (2023)
- [Demystifying the Data Need of ML-surrogates for CFD Simulations](https://mlsanity.com/paper/2205.08355/) (2022)
- [Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks](https://mlsanity.com/paper/2405.13850/) (2024)
- [Using Parametric PINNs for Predicting Internal and External Turbulent Flows](https://mlsanity.com/paper/2410.18917/) (2024)
- [A panoramic aerodynamic performance prediction method for turbomachinery cascades using transformer-enhanced neural operator](https://mlsanity.com/paper/2609.16066/) (2026)
- [Geometric Deep Learning for the Assessment of Thrombosis Risk in the Left Atrial Appendage](https://mlsanity.com/paper/2210.10563/) (2022)
- [Geometry-aware PINNs for Turbulent Flow Prediction](https://mlsanity.com/paper/2412.01954/) (2024)
- [Fast-Forward Lattice Boltzmann: Learning Kinetic Behaviour with Physics-Informed Neural Operators](https://mlsanity.com/paper/2509.22411/) (2025)

## Abstract (arXiv)

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.