The new paradigm of computational fluid dynamics: Empowering computational fluid dynamics with machine learning

Computational fluid dynamics (CFD) integrated with machine learning (ML) is an emerging and rapidly growing research field. ML's ability to process data and extract patterns enables the extraction of valuable insights from large, fluid datasets. Compared to traditional CFD, ML-enhanced CFD not only significantly reduces simulation costs and improves efficiency but also enhances generalization capabilities, enabling the solution of complex fluid dynamics problems, such as nonlinear and high-dimensional issues. This paper offers a comprehensive overview of ML advancements in theoretical modeling, numerical computation, and experimental validation, structured around the three main areas of CFD research. It also highlights recent fusion applications and algorithms used for training over the past 5 years. Additionally, the future prospects of ML-enabled CFD are explored, along with potential challenges that may arise during its development.

• Publication year

  2025

• Venue

  The Physics of Fluids

• Publication date

  2025-08-01

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1063/5.0280743
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Hemodynamics modeling with physics-informed neural networks: A progressive boundary complexity approach

  2025cited by this paper
• AutoTurb: Using large language models for automatic algebraic turbulence model discovery

  2025cited by this paper
• Using Physics-Informed neural networks for solving Navier-Stokes equations in fluid dynamic complex scenarios

  2025cited by this paper
• Three-dimensional spatiotemporal wind field reconstruction based on LiDAR and multi-scale PINN

  2025cited by this paper
• Modeling the discharge coefficient of labyrinth sluice gates using hybrid support vector regression and metaheuristic algorithms

  2025cited by this paper
• Preconditioned FEM-based neural networks for solving incompressible fluid flows and related inverse problems

  2024cited by this paper
• Physics-informed recurrent super-resolution generative reconstruction in rotating detonation combustor

  2024cited by this paper
• Accurate machine-learning-based prediction of aerodynamic and heat transfer coefficients for cylindrical biomass particles

  2024cited by this paper
• Unsupervised physics-informed deep learning for assessing pulmonary artery hemodynamics

  2024cited by this paper
• Gridder-HO: Rapid and efficient parallel software for high-order curvilinear mesh generation

  2024cited by this paper
• PDENNEval: A Comprehensive Evaluation of Neural Network Methods for Solving PDEs

  2024cited by this paper
• Machine learning-based reduced-order reconstruction method for flow fields

  2024cited by this paper
• Neural differentiable modeling with diffusion-based super-resolution for two-dimensional spatiotemporal turbulence

  2024cited by this paper
• Three-Dimensional Physics-Informed Neural Network Simulation in Coronary Artery Trees

  2024cited by this paper
• On Some Limitations of Current Machine Learning Weather Prediction Models

  2024cited by this paper
• Evolution of CFD as an engineering science. A personal perspective with emphasis on the finite volume method

  2024cited by this paper
• RANS wake surrogate: Impact of Physics Information in Neural Networks

  2024cited by this paper
• A novel discretized physics-informed neural network model applied to the Navier–Stokes equations

  2024cited by this paper
• Machine-learning wall-model large-eddy simulation accounting for isotropic roughness under local equilibrium

  2024cited by this paper
• Flow reconstruction over a SUBOFF model based on LBM-generated data and physics-informed neural networks

  2024cited by this paper
• Vascular flow design and predicting evolution

  2024cited by this paper
• Developing machine learning models with metaheuristic algorithms for droplet size prediction in a microfluidic microchannel

  2024cited by this paper
• Fourier neural operator for large eddy simulation of compressible Rayleigh–Taylor turbulence

  2024cited by this paper
• Simulation of Supersonic Axisymmetric Base Flow with a Data-Driven Turbulence Model

  2024cited by this paper
• Data-driven turbulence modeling for fluid flow and heat transfer in peripheral subchannels of a rod bundle

  2024cited by this paper
• Machine learning-based vorticity evolution and super-resolution of homogeneous isotropic turbulence using wavelet projection

  2024cited by this paper
• On the Hard Boundary Constraint Method for Fluid Flow Prediction based on the Physics-Informed Neural Network

  2024cited by this paper
• Physics-informed neural network combined with characteristic-based split for solving forward and inverse problems involving Navier-Stokes equations

  2024cited by this paper
• Data-Driven Acceleration of Statistical Convergence in Turbulent Flows

  2024cited by this paper
• Using Machine-Learning-Aided Computational Fluid Dynamics to Facilitate Design of Experiments

  2024cited by this paper
• High precision aerodynamic heat prediction method based on data augmentation and transfer learning

  2024cited by this paper
• LESnets (large-eddy simulation nets): Physics-informed neural operator for large-eddy simulation of turbulence

  2024cited by this paper
• Comparison of hybrid deep learning models for estimation of the time-dependent scour depth downstream of river training structures

  2024cited by this paper
• A Data-Driven Machine Learning Approach for Turbulent Flow Field Prediction Based on Direct Computational Fluid Dynamics Database

  2024cited by this paper
• Automated adaptive chemistry for Large Eddy Simulations of turbulent reacting flows

  2024cited by this paper
• Immersed Boundary Wall-Modelled Large Eddy Simulations of Subsonic Jet Flows and Acoustics

  2024cited by this paper
• ML and CFD Simulation of Flow Structure around Tandem Bridge Piers in Pressurized Flow

  2023cited by this paper
• Mean flow reconstruction of unsteady flows using physics-informed neural networks

  2023cited by this paper
• Development of a Machine Learning Wall Model for Large-Eddy Simulation of Gas Turbine Film Cooling Flows

  2023cited by this paper
• Discovering explicit Reynolds-averaged turbulence closures for turbulent separated flows through deep learning-based symbolic regression with non-linear corrections

  2023cited by this paper
• Reconstruction of hydrofoil cavitation flow based on the chain-style physics-informed neural network

  2023cited by this paper
• An End-to-End Physics-Informed Neural Network for Defect Identification and 3-D Reconstruction Using Rotating Alternating Current Field Measurement

  2023cited by this paper
• Physics-informed machine learning based RANS turbulence modeling convection heat transfer of supercritical pressure fluid

  2023cited by this paper
• Accurate medium-range global weather forecasting with 3D neural networks

  2023cited by this paper
• 200 years of the Navier–Stokes equation

  2023cited by this paper
• An integrated framework for accelerating reactive flow simulation using GPU and machine learning models

  2023cited by this paper
• Rethinking materials simulations: Blending direct numerical simulations with neural operators

  2023cited by this paper
• Enhancing turbulence modeling: Machine learning for pressure-strain correlation and uncertainty quantification in the Reynolds stress model

  2023cited by this paper
• Peristaltic flow of a bioconvective sutterby nanofluid in a flexible microchannel with compliant walls: Application to hemodynamic instability

  2023cited by this paper
• Do AI models produce better weather forecasts than physics-based models? A quantitative evaluation case study of Storm Ciarán

  2023cited by this paper
• Heterogeneous data-driven aerodynamic modeling based on physical feature embedding

  2023cited by this paper
• Time-averaged flow field reconstruction based on a multifidelity model using physics-informed neural network (PINN) and nonlinear information fusion

  2023cited by this paper
• Investigation of Physics-Informed Neural Networks to Reconstruct a Flow Field with High Resolution

  2023cited by this paper
• Peristaltic flow of bioconvective Ree–Eyring nanofluid through an inclined elastic channel with partial slip effects

  2023cited by this paper
• Variational assimilation of sparse time-averaged data for efficient adjoint-based optimization of unsteady RANS simulations

  2023cited by this paper
• A variational data assimilation approach for sparse velocity reference data in coarse RANS simulations through a corrective forcing term

  2023cited by this paper
• Applying Physics-Informed Neural Networks to Solve Navier–Stokes Equations for Laminar Flow around a Particle

  2023cited by this paper
• On the unsteady wake flow behind a sphere with large transverse-rotating speeds

  2023cited by this paper
• Generative ensemble deep learning severe weather prediction from a deterministic convection-allowing model

  2023cited by this paper
• Neural operators for accelerating scientific simulations and design

  2023cited by this paper
• Developing a novel structured mesh generation method based on deep neural networks

  2023cited by this paper
• Machine learning prediction of BLEVE loading with graph neural networks

  2023cited by this paper
• PHYSICS-INFORMED NEURAL NETWORKS FOR MODELING OF 3D FLOW THERMAL PROBLEMS WITH SPARSE DOMAIN DATA

  2023cited by this paper
• Investigation on the abilities of different artificial intelligence methods to predict the aerodynamic coefficients

  2023cited by this paper
• Equation discovery of dynamized coefficients in the ໿k-ε model for urban airflow and ໿airborne contaminant dispersion

  2023cited by this paper
• Wavelet Transforms and Machine Learning Methods for the Study of Turbulence

  2023cited by this paper
• Reconstruction of 3D flow field around a building model in wind tunnel: a novel physics-informed neural network framework adopting dynamic prioritization self-adaptive loss balance strategy

  2023cited by this paper
• Peristaltic transport of MHD Ree–Eyring fluid through a flexible channel under the influence of activation energy

  2023cited by this paper
• Neural Operator: Learning Maps Between Function Spaces With Applications to PDEs

  2023cited by this paper
• A hybrid CFD-RMD multiscale coupling framework for interfacial heat and mass simulation under hyperthermal ablative conditions

  2023cited by this paper
• Convolutional Neural Operators for robust and accurate learning of PDEs

  2023cited by this paper
• Machine learning enhanced real-time aerodynamic forces prediction based on sparse pressure sensor inputs

  2023cited by this paper
• Data-driven prediction of the performance of enhanced surfaces from an extensive CFD-generated parametric search space

  2023cited by this paper
• Deep Neural Network Modeling for CFD Simulations: Benchmarking the Fourier Neural Operator on the Lid-Driven Cavity Case

  2023cited by this paper
• Learning stiff chemical kinetics using extended deep neural operators

  2023cited by this paper
• Benchmarking sparse system identification with low-dimensional chaos

  2023cited by this paper
• Diffusion effects on mixed convective peristaltic flow of a bi-viscous Bingham nanofluid through a flexible porous channel with convective boundary conditions

  2023cited by this paper
• Physics-informed neural entangled-ladder network for inhalation impedance of the respiratory system

  2023cited by this paper
• Physics-informed deep-learning applications to experimental fluid mechanics

  2022cited by this paper
• JAX-FLUIDS: A fully-differentiable high-order computational fluid dynamics solver for compressible two-phase flows

  2022cited by this paper
• Multi-objective optimization of cyclone separators using mathematical modelling and large-eddy simulation for a fixed total height condition

  2022cited by this paper
• Reconstruction of nearshore wave fields based on physics-informed neural networks

  2022cited by this paper
• Deep Learning and Symbolic Regression for Discovering Parametric Equations

  2022cited by this paper
• Lagrangian large eddy simulations via physics-informed machine learning

  2022cited by this paper
• Transfer Learning for Flow Reconstruction Based on Multifidelity Data

  2022cited by this paper
• Gradient-based shape optimization for unsteady turbulent simulations using field inversion and machine learning

  2022cited by this paper
• Scientific machine learning for modeling and simulating complex fluids

  2022cited by this paper
• PDEBENCH: An Extensive Benchmark for Scientific Machine Learning

  2022cited by this paper
• Fourier neural operator approach to large eddy simulation of three-dimensional turbulence

  2022cited by this paper
• SIKIŞTIRILAMAZ ISIL TAŞINIM PROBLEMLERİNİN FİZİKLE ÖĞRENEN YAPAY SİNİR AĞLARI İLE ÇÖZÜMÜ

  2022cited by this paper
• Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constants

  2022cited by this paper
• A practical approach to flow field reconstruction with sparse or incomplete data through physics informed neural network

  2022cited by this paper
• High Fidelity Cfd-Trained Machine Learning To Inform Rans-Modelled Interfacial Turbulence

  2022cited by this paper
• Machine learning enables design automation of microfluidic flow-focusing droplet generation

  2021cited by this paper
• Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning

  2021cited by this paper
• Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and control

  2021cited by this paper
• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method

  2021cited by this paper
• Unsteady aerodynamic reduced-order modeling based on machine learning across multiple airfoils

  2021cited by this paper
• Impact of wall heat transfer in Large Eddy Simulation of flame dynamics in a swirled combustion chamber

  2021cited by this paper
• Exploiting machine learning for bestowing intelligence to microfluidics.

  2021cited by this paper

• Quantum-Enhanced Computational Fluid Dynamics: Hybrid Quantum–Classical Solvers for High-Fidelity Simulation of Turbulence and Multiphase Flow in Mechanical System Design

  2026cites this paper
• Low-cost and generalizable optimization for the centrifugal pump using deep reinforcement learning

  2025cites this paper
• Development of Part Cooling in 3D Printer through the Design of a Custom Cooling Duct Using Generative Design

  2025cites this paper
• Scientific software development in the AI era: reproducibility, MLOps, and applications in soft matter physics

  2025cites this paper
• Interpretable surrogate modeling of extrusion flows with deep learning

  2025cites this paper
• A Fast Calculation Method for Equivalent Transformer Windings Based on Thermal Parameter Equivalence

  2025cites this paper