Recent Advances on Machine Learning for Computational Fluid Dynamics: A Survey
read the original abstract
This paper explores the recent advancements in enhancing Computational Fluid Dynamics (CFD) tasks through Machine Learning (ML) techniques. We begin by introducing fundamental concepts, traditional methods, and benchmark datasets, then examine the various roles ML plays in improving CFD. The literature systematically reviews papers in recent five years and introduces a novel classification for forward modeling: Data-driven Surrogates, Physics-Informed Surrogates, and ML-assisted Numerical Solutions. Furthermore, we also review the latest ML methods in inverse design and control, offering a novel classification and providing an in-depth discussion. Then we highlight real-world applications of ML for CFD in critical scientific and engineering disciplines, including aerodynamics, combustion, atmosphere & ocean science, biology fluid, plasma, symbolic regression, and reduced order modeling. Besides, we identify key challenges and advocate for future research directions to address these challenges, such as multi-scale representation, physical knowledge encoding, scientific foundation model and automatic scientific discovery. This review serves as a guide for the rapidly expanding ML for CFD community, aiming to inspire insights for future advancements. We draw the conclusion that ML is poised to significantly transform CFD research by enhancing simulation accuracy, reducing computational time, and enabling more complex analyses of fluid dynamics. The paper resources can be viewed at https://github.com/WillDreamer/Awesome-AI4CFD.
This paper has not been read by Pith yet.
Forward citations
Cited by 15 Pith papers
-
Is Zero-Shot Super-Resolution Possible in Operator Learning?
Zero-shot super-resolution is information-theoretically impossible for some simple operators but possible under Hölder smoothness of outputs, accompanied by generalization bounds.
-
FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulation
FD-Bench supplies the first modular, reproducible benchmark and leaderboard for comparing neural PDE solvers on fluid dynamics tasks with direct numerical solver baselines.
-
PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport
PINS combines an outer proximal-point loop over shifted entropic OT problems with inner Sinkhorn warm-up and sparse-Newton refinement to reach unregularized OT solutions with global convergence and lower error than Si...
-
A Physics-Informed Fourier-Wavelet Transformer for Multiscale Computational Fluid Dynamics Surrogate Modeling
A physics-informed Fourier-wavelet transformer model reports the lowest normalized mean-squared error on cylinder-wake and fluid-structure interaction velocity-field benchmarks compared with spectral, transformer, ope...
-
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting
PnP-Corrector decouples physics simulation from error correction via a plug-and-play agent, cutting error by 29% in 300-day global ocean-atmosphere forecasts.
-
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting
PnP-Corrector decouples physics simulation from error correction to counter reciprocal error amplification in coupled spatiotemporal forecasting, cutting error by 29% in a 300-day ocean-atmosphere test.
-
Deep Wave Network for Modeling Multi-Scale Physical Dynamics
DW-Net improves the accuracy versus computational cost Pareto front over standard U-Nets for 2D and 3D multi-scale flow benchmarks by stacking multiple waves while keeping training settings identical.
-
Spectral-inspired Operator Learning with Limited Data and Unknown Physics
SINO learns PDE operators from limited data using spectral features from frequency indices, a Pi-block for nonlinearities, and a low-pass filter, achieving 1-2 orders of magnitude better accuracy than prior methods on...
-
DeepPropNet: an operator learning-based predictor for thermal plasma properties
DeepPropNet predicts thermal plasma properties with relative L2 errors of 10^{-3} to 10^{-2} for SF6-N2 and C4F7N-CO2-O2 mixtures using single-property and mixture-of-experts architectures trained on high-fidelity data.
-
Incomplete Data, Complete Dynamics: A Diffusion Approach
A conditional diffusion model trained on partitioned incomplete samples for physical dynamics achieves asymptotic convergence to the true generative process under mild conditions and outperforms baselines in imputation.
-
Solution of the Newtonian plane Couette flow with dynamic wall slip using machine-learning methods
PINNs and DeepONets solve Newtonian plane Couette flow with dynamic wall slip; DeepONet achieves 0.36% mean relative error on unseen cases and 540X speedup over numerical methods.
-
Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospects
A survey organizing AI methods for inverse PDE problems into inverse problems, inverse design, and control categories, covering applications and future challenges like physics-informed models and uncertainty quantification.
-
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting
PnP-Corrector decouples pre-trained physics engines from a correction agent to mitigate reciprocal error amplification in coupled spatiotemporal forecasting, cutting error by 28% on a 300-day ocean-atmosphere task.
-
Encoding strategies for quantum enhanced fluid simulations: opportunities and challenges
Encoding strategies for quantum fluid simulations trade off compactness against practicality in state preparation, measurement, boundary conditions, and nonlinear operations, with no single approach being universally optimal.
-
A review of quantum machine learning and quantum-inspired applied methods to computational fluid dynamics
A survey of variational quantum algorithms, quantum neural networks, and tensor networks for addressing scalability challenges in computational fluid dynamics.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.