Machine learning for fluid mechanics
From MaRDI portal
Abstract: The field of fluid mechanics is rapidly advancing, driven by unprecedented volumes of data from field measurements, experiments and large-scale simulations at multiple spatiotemporal scales. Machine learning offers a wealth of techniques to extract information from data that could be translated into knowledge about the underlying fluid mechanics. Moreover, machine learning algorithms can augment domain knowledge and automate tasks related to flow control and optimization. This article presents an overview of past history, current developments, and emerging opportunities of machine learning for fluid mechanics. It outlines fundamental machine learning methodologies and discusses their uses for understanding, modeling, optimizing, and controlling fluid flows. The strengths and limitations of these methods are addressed from the perspective of scientific inquiry that considers data as an inherent part of modeling, experimentation, and simulation. Machine learning provides a powerful information processing framework that can enrich, and possibly even transform, current lines of fluid mechanics research and industrial applications.
Recommendations
- Data-driven fluid mechanics. Combining first principles and machine learning. Based on a von Karman Institute Lecture Series
- A review on deep reinforcement learning for fluid mechanics
- Data-driven, physics-based feature extraction from fluid flow fields using convolutional neural networks
- Multi-Fidelity Machine Learning Applied to Steady Fluid Flows
- Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
Cited in
(only showing first 100 items - show all)- Application of physics-constrained data-driven reduced-order models to shape optimization
- GSA for machine learning problems: a comprehensive overview
- Coupled and uncoupled dynamic mode decomposition in multi-compartmental systems with applications to epidemiological and additive manufacturing problems
- Leveraging reduced-order models for state estimation using deep learning
- Modern Koopman theory for dynamical systems
- Residual-Guided Dictionary Learning for Spectrally Accurate Koopman Approximation
- Data-driven wall modeling for turbulent separated flows
- JAX-FVM: A differentiable, entropy-stable finite volume solver on unstructured meshes for compressible flows
- Physics-based self-learning spiking neural network enhanced time-integration scheme for computing viscoplastic structural finite element response
- Enhancement of RANS models by means of the tensor basis random forest for turbulent flows in two-dimensional channels with bumps
- A probabilistic, data-driven closure model for RANS simulations with aleatoric, model uncertainty
- A global eigenvalue reassignment method for the stabilization of nonlinear reduced-order models
- Multi-fidelity parametric sensitivity estimation for large eddy simulation with the Spalart–Allmaras model
- Bayesian conditional diffusion models for versatile spatiotemporal turbulence generation
- Neural ODE to model and prognose thermoacoustic instability
- Turbulence theories and statistical closure approaches
- Forecasting macroscopic dynamics in adaptive Kuramoto network using reservoir computing
- SciANN: a Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks
- Neural ordinary differential equations for model order reduction of stiff systems
- Uncovering wall-shear stress dynamics from neural-network enhanced fluid flow measurements
- Theory-guided physics-informed neural networks for boundary layer problems with singular perturbation
- Reinforcement-learning-assisted control of four-roll Mills: geometric symmetry and inertial effect
- Airfoil-based convolutional autoencoder and long short-term memory neural network for predicting coherent structures evolution around an airfoil
- A predictive physics-aware hybrid reduced order model for reacting flows
- DeepM\&Mnet: inferring the electroconvection multiphysics fields based on operator approximation by neural networks
- Recurrent neural networks (RNNs) learn the constitutive law of viscoelasticity
- Adaptive deep density approximation for fractional Fokker-Planck equations
- Approximating partial differential equations without boundary conditions
- Solving time dependent Fokker-Planck equations via temporal normalizing flow
- Parsimony as the ultimate regularizer for physics-informed machine learning
- Synchronization and chimeras in a network of four ring-coupled thermoacoustic oscillators
- Multiresolution convolutional autoencoders
- A deep-learning super-resolution reconstruction model of turbulent reacting flow
- Revisiting tensor basis neural network for Reynolds stress modeling: application to plane channel and square duct flows
- Evaluation of physics constrained data-driven methods for turbulence model uncertainty quantification
- Spatio-temporal microstructure of sprays: data science-based analysis and modelling
- Four-dimensional variational data assimilation of a turbulent jet for super-temporal-resolution reconstruction
- Robust flow control and optimal sensor placement using deep reinforcement learning
- Multi-hierarchical surrogate learning for explicit structural dynamical systems using graph convolutional neural networks
- Tensor decomposition-based neural operator with dynamic mode decomposition for parameterized time-dependent problems
- Complex-network modeling of reversal events in two-dimensional turbulent thermal convection
- Data-driven resolvent analysis
- A coupled smoothed finite element method and Lagrangian particle tracking model for three-dimensional dilute particle-laden flows
- Learning about structural errors in models of complex dynamical systems
- Three dimensional interface normal prediction for volume-of-fluid method using artificial neural network
- A (2+1)-dimensional evolution model of Rossby waves and its resonance Y-type soliton and interaction solutions
- Multiscale model reduction for incompressible flows
- Short- and long-term predictions of chaotic flows and extreme events: a physics-constrained reservoir computing approach
- MC-Nonlocal-PINNs: Handling Nonlocal Operators in PINNs Via Monte Carlo Sampling
- Deep learning-based reduced order model for three-dimensional unsteady flow using mesh transformation and stitching
- Data-enabled reduction of the time complexity of iterative solvers
- Leveraging initial conditions memory for modelling Rayleigh-Taylor turbulence
- Numerical Assessment of a Nonintrusive Surrogate Model Based on Recurrent Neural Networks and Proper Orthogonal Decomposition: Rayleigh–Bénard Convection
- Multi-Fidelity Machine Learning Applied to Steady Fluid Flows
- Elasticity-based morphing technique and application to reduced-order modeling
- A projection-based, semi-implicit time-stepping approach for the Cahn-Hilliard Navier-Stokes equations on adaptive octree meshes
- DPM: a deep learning PDE augmentation method with application to large-eddy simulation
- A data-driven physics-informed finite-volume scheme for nonclassical undercompressive shocks
- Symplectic neural networks in Taylor series form for Hamiltonian systems
- Integration of neural networks with numerical solution of PDEs for closure models development
- Dynamics-augmented cluster-based network model
- Stochastic characterisation of unstable lean hydrogen–air annular premixed flames
- A data-driven scale-invariant weighted compact nonlinear scheme for hyperbolic conservation laws
- Domain decomposition learning methods for solving elliptic problems
- Mixing artificial and natural intelligence: from statistical mechanics to AI and back to turbulence
- Real-time computing for a parameterized feedback control problem of Boussinesq equations by POD and deep learning
- \(\text{PIN}^{\mathcal L}\) : Preconditioned Inexact Newton with Learning Capability for Nonlinear System of Equations
- Numerical study and parameter prediction of a full-free flexible flament in wakes of flapping wing
- Reduced basis methods for time-dependent problems
- On the accuracy of two-temperature models for hypersonic nonequilibrium flow
- Data-driven Bayesian inference of turbulence model closure coefficients incorporating epistemic uncertainty
- Bayesian optimization for active flow control
- Genetic-algorithm-based artificial intelligence control of a turbulent boundary layer
- Machine learning for adjoint vector in aerodynamic shape optimization
- Robust optimization and validation of echo state networks for learning chaotic dynamics
- On the improvement of the extrapolation capability of an iterative machine-learning based RANS framework
- VPVnet: a velocity-pressure-vorticity neural network method for the Stokes' equations under reduced regularity
- A sparse optimal closure for a reduced-order model of wall-bounded turbulence
- Neural-network-based fluid-structure interaction applied to vortex-induced vibration
- Direct shape optimization through deep reinforcement learning
- Physically interpretable machine learning algorithm on multidimensional non-linear fields
- Physics-inspired architecture for neural network modeling of forces and torques in particle-laden flows
- Deep reinforcement learning for the control of conjugate heat transfer
- Enhancing CFD Solver with machine learning techniques
- A deep learning -- genetic algorithm approach for aerodynamic inverse design via optimization of pressure distribution
- Machine learning predictive model for dynamic response of rising bubbles impacting on a horizontal wall
- A few-shot identification method for stochastic dynamical systems based on residual multipeaks adaptive sampling
- CGNSDE: conditional Gaussian neural stochastic differential equation for modeling complex systems and data assimilation
- Nonintrusive Reduced Order Modelling of Convective Boussinesq Flows
- Machine learning strategies for systems with invariance properties
- Diffusion maps-aided neural networks for the solution of parametrized PDEs
- Data driven modeling for self-similar dynamics
- Gaussian process regression + deep neural network autoencoder for probabilistic surrogate modeling in nonlinear mechanics of solids
- Variational physics-informed neural operator (VINO) for solving partial differential equations
- The \(l_1\)-based sparsification of energy interactions in unsteady lid-driven cavity flow
- Interactions among the rogue waves and solitons for a \((2 + 1)\)-dimensional Maccari system in fluid mechanics and nonlinear optics
- Active control of compressible channel flow up to Mab=3 using direct numerical simulations with spanwise velocity modulation at the walls
- Reinforcement-learning-based actuator selection method for active flow control
- Layer-parallel training of residual networks with auxiliary variable networks
- Data-driven fractional subgrid-scale modeling for scalar turbulence: a nonlocal LES approach
This page was built for publication: Machine learning for fluid mechanics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3296524)
