# CFDNet: a deep learning-based accelerator for fluid simulations

arXiv: https://arxiv.org/abs/2005.04485 · HTML: https://mlsanity.com/paper/2005.04485/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2020.

## Built on by (most cited first, 30 of 40)

- [Machine learning accelerated computational fluid dynamics](https://mlsanity.com/paper/2102.01010/) (2021)
- [Factorized Fourier Neural Operators](https://mlsanity.com/paper/2111.13802/) (2021)
- [Enhancing Computational Fluid Dynamics with Machine Learning](https://mlsanity.com/paper/2110.02085/) (2021)
- [AirfRANS: High Fidelity Computational Fluid Dynamics Dataset for Approximating Reynolds-Averaged Navier-Stokes Solutions](https://mlsanity.com/paper/2212.07564/) (2022)
- [From Zero to Turbulence: Generative Modeling for 3D Flow Simulation](https://mlsanity.com/paper/2306.01776/) (2023)
- [Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNN](https://mlsanity.com/paper/2210.02573/) (2022)
- [Mosaic Flows: A Transferable Deep Learning Framework for Solving PDEs on Unseen Domains](https://mlsanity.com/paper/2104.10873/) (2021)
- [MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations](https://mlsanity.com/paper/2211.00713/) (2022)
- [Multigrid-augmented deep learning preconditioners for the Helmholtz equation](https://mlsanity.com/paper/2203.11025/) (2022)
- [How to Avoid Trivial Solutions in Physics-Informed Neural Networks](https://mlsanity.com/paper/2112.05620/) (2021)
- [Finite volume method network for acceleration of unsteady computational fluid dynamics: non-reacting and reacting flows](https://mlsanity.com/paper/2105.03332/) (2021)
- [Multigrid-Augmented Deep Learning Preconditioners for the Helmholtz Equation using Compact Implicit Layers](https://mlsanity.com/paper/2306.17486/) (2023)
- [SURFNet: Super-resolution of Turbulent Flows with Transfer Learning using Small Datasets](https://mlsanity.com/paper/2108.07667/) (2021)
- [An extensible Benchmarking Graph-Mesh dataset for studying Steady-State Incompressible Navier-Stokes Equations](https://mlsanity.com/paper/2206.14709/) (2022)
- [INFINITY: Neural Field Modeling for Reynolds-Averaged Navier-Stokes Equations](https://mlsanity.com/paper/2307.13538/) (2023)
- [Reference Neural Operators: Learning the Smooth Dependence of Solutions of PDEs on Geometric Deformations](https://mlsanity.com/paper/2405.17509/) (2024)
- [Towards high-accuracy deep learning inference of compressible turbulent flows over aerofoils](https://mlsanity.com/paper/2109.02183/) (2021)
- [An Improved Structured Mesh Generation Method Based on Physics-informed Neural Networks](https://mlsanity.com/paper/2210.09546/) (2022)
- [Learning to Predict Structural Vibrations](https://mlsanity.com/paper/2310.05469/) (2023)
- [Surrogate-data-enriched Physics-Aware Neural Networks](https://mlsanity.com/paper/2112.05489/) (2021)
- [An Implicit GNN Solver for Poisson-like problems](https://mlsanity.com/paper/2302.10891/) (2023)
- [Breaking Boundaries: Distributed Domain Decomposition with Scalable Physics-Informed Neural PDE Solvers](https://mlsanity.com/paper/2308.14258/) (2023)
- [3DMeshNet: A Three-Dimensional Differential Neural Network for Structured Mesh Generation](https://mlsanity.com/paper/2407.01560/) (2024)
- [Comparison of CNN-based deep learning architectures for unsteady CFD acceleration on small datasets](https://mlsanity.com/paper/2502.06837/) (2025)
- [Graph network for learning bi-directional physics](https://mlsanity.com/paper/2112.07054/) (2021)
- [Positional Encoding Augmented GAN for the Assessment of Wind Flow for Pedestrian Comfort in Urban Areas](https://mlsanity.com/paper/2112.08447/) (2021)
- [NUNet: Deep Learning for Non-Uniform Super-Resolution of Turbulent Flows](https://mlsanity.com/paper/2203.14154/) (2022)
- [Hierarchical-embedding autoencoder with a predictor (HEAP) as efficient architecture for learning long-term evolution of complex multi-scale physical systems](https://mlsanity.com/paper/2505.18857/) (2025)
- [A Deep Learning Approach for Thermal Plume Prediction of Groundwater Heat Pumps](https://mlsanity.com/paper/2203.14961/) (2022)
- [Meta-Learning for Airflow Simulations with Graph Neural Networks](https://mlsanity.com/paper/2306.10624/) (2023)

## Abstract (arXiv)

CFD is widely used in physical system design and optimization, where it is used to predict engineering quantities of interest, such as the lift on a plane wing or the drag on a motor vehicle. However, many systems of interest are prohibitively expensive for design optimization, due to the expense of evaluating CFD simulations. To render the computation tractable, reduced-order or surrogate models are used to accelerate simulations while respecting the convergence constraints provided by the higher-fidelity solution. This paper introduces CFDNet -- a physical simulation and deep learning coupled framework, for accelerating the convergence of Reynolds Averaged Navier-Stokes simulations. CFDNet is designed to predict the primary physical properties of the fluid including velocity, pressure, and eddy viscosity using a single convolutional neural network at its core. We evaluate CFDNet on a variety of use-cases, both extrapolative and interpolative, where test geometries are observed/not-observed during training. Our results show that CFDNet meets the convergence constraints of the domain-specific physics solver while outperforming it by 1.9 - 7.4x on both steady laminar and turbulent flows. Moreover, we demonstrate the generalization capacity of CFDNet by testing its prediction on new geometries unseen during training. In this case, the approach meets the CFD convergence criterion while still providing significant speedups over traditional domain-only models.