Enhancing Computational Fluid Dynamics with Machine Learning

Abstract

Machine learning is rapidly becoming a core technology for scientific computing, with numerous opportunities to advance the field of computational fluid dynamics. In this Perspective, we highlight some of the areas of highest potential impact, including to accelerate direct numerical simulations, to improve turbulence closure modeling, and to develop enhanced reduced-order models. We also discuss emerging areas of machine learning that are promising for computational fluid dynamics, as well as some potential limitations that should be taken into account.

15 pages, 4 figures

References in corpus (9)

• Machine learning for molecular simulation
• A neural network approach for the blind deconvolution of turbulent flows
• Data-Driven Modeling and Prediction of Non-Linearizable Dynamics via Spectral Submanifolds
• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• CFDNet: a deep learning-based accelerator for fluid simulations
• Data-Driven Multi-Grid Solver for Accelerated Pressure Projection
• Convolutional-network models to predict wall-bounded turbulence from wall quantities
• Inserting machine-learned virtual wall velocity for large-eddy simulation of turbulent channel flows
• Predicting the near-wall region of turbulence through convolutional neural networks

Cited by in corpus (45)

• Improving aircraft performance using machine learning: a review
• Recent advances in applying deep reinforcement learning for flow control: perspectives and future directions
• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• A transformer-based synthetic-inflow generator for spatially-developing turbulent boundary layers
• Machine learning building-block-flow wall model for large-eddy simulation
• Residual-based physics-informed transfer learning: A hybrid method for accelerating long-term CFD simulations via deep learning
• OpenFOAMGPT: a RAG-Augmented LLM Agent for OpenFOAM-Based Computational Fluid Dynamics
• Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models
• XLB: A differentiable massively parallel lattice Boltzmann library in Python
• Log-law recovery through reinforcement-learning wall model for large-eddy simulation
• Three-dimensional generative adversarial networks for turbulent flow estimation from wall measurements
• Physics-informed neural networks modeling for systems with moving immersed boundaries: application to an unsteady flow past a plunging foil
• Accelerating high order discontinuous Galerkin solvers using neural networks: 3D compressible Navier-Stokes equations
• Compressing fluid flows with nonlinear machine learning: mode decomposition, latent modeling, and flow control
• Reduced-order modeling of unsteady fluid flow using neural network ensembles
• A Deep Learning algorithm to accelerate Algebraic Multigrid methods in Finite Element solvers of 3D elliptic PDEs
• High-flexibility reconstruction of small-scale motions in wall turbulence using a generalized zero-shot learning
• Predicting the wall-shear stress and wall pressure through convolutional neural networks
• A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek
• Local neural operator for solving transient partial differential equations on varied domains
• Machine Learning Changes the Rules for Flux Limiters
• Generative prediction of flow fields around an obstacle using the diffusion model
• When Energy and Information Revolutions Meet 2D Janus
• Neural Quantum Propagators for Driven-Dissipative Quantum Dynamics
• Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow
• Flow control by a hybrid use of machine learning and control theory
• Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection
• Optimized Flow Control based on Automatic Differentiation in Compressible Turbulent Channel Flows
• Learning the Latent dynamics of Fluid flows from High-Fidelity Numerical Simulations using Parsimonious Diffusion Maps
• A deep learning approach to wall-shear stress quantification: From numerical training to zero-shot experimental application
• Hierarchical deep learning-based adaptive time-stepping scheme for multiscale simulations
• Reducing Spatial Discretization Error on Coarse CFD Simulations Using an OpenFOAM-Embedded Deep Learning Framework
• Kinetic data-driven approach to turbulence subgrid modeling
• FlexPINN: Modeling Fluid Dynamics and Mass Transfer in 3D Micromixer Geometries Using a Flexible Physics-Informed Neural Network
• Deep learning surrogate models of JULES-INFERNO for wildfire prediction on a global scale
• Defiltering turbulent flow fields for Lagrangian particle tracking using machine learning techniques
• Quantum Iterative Methods for Solving Differential Equations with Application to Computational Fluid Dynamics
• On Deep-Learning-Based Closures for Algebraic Surrogate Models of Turbulent Flows
• Electron neural closure for turbulent magnetosheath simulations: energy channels
• Prediction of flow and elastic stresses in a viscoelastic turbulent channel flow using convolutional neural networks
• Uncertainty quantification and stability of neural operators for prediction of three-dimensional turbulence
• Time-inversion of spatiotemporal beam dynamics using uncertainty-aware latent evolution reversal
• VIVALDy: A Hybrid Generative Reduced-Order Model for Turbulent Flows, Applied to Vortex-Induced Vibrations
• Data-driven quantification of model-form uncertainty in Reynolds-averaged simulations of wind farms
• The Machine Learning Approach to Moment Closure Relations for Plasma: A Review