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)- A data-driven smoothed particle hydrodynamics method for fluids
- SciANN: a Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks
- Development of an algorithm for reconstruction of droplet history based on deposition pattern using computational fluid dynamics and convolutional neural network
- The neural particle method - an updated Lagrangian physics informed neural network for computational fluid dynamics
- A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics
- Diffusion maps-aided neural networks for the solution of parametrized PDEs
- Embedding data analytics and CFD into the digital twin concept
- Efficient computations for linear feedback control problems for target velocity matching of Navier-Stokes flows via POD and LSTM-ROM
- PhyCRNet: physics-informed convolutional-recurrent network for solving spatiotemporal PDEs
- Deep learning of conjugate mappings
- Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
- Stabilized reduced-order models for unsteady incompressible flows in three-dimensional parametrized domains
- Three-dimensional realizations of flood flow in large-scale rivers using the neural fuzzy-based machine-learning algorithms
- Mapping of coherent structures in parameterized flows by learning optimal transportation with Gaussian models
- Physics-based self-learning recurrent neural network enhanced time integration scheme for computing viscoplastic structural finite element response
- Theory-guided physics-informed neural networks for boundary layer problems with singular perturbation
- Multiresolution convolutional autoencoders
- DPM: a deep learning PDE augmentation method with application to large-eddy simulation
- Deep learning of the spanwise-averaged Navier-Stokes equations
- A data-driven physics-informed finite-volume scheme for nonclassical undercompressive shocks
- Symplectic neural networks in Taylor series form for Hamiltonian systems
- A long short-term memory embedding for hybrid uplifted reduced order models
- NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations
- Physically interpretable machine learning algorithm on multidimensional non-linear fields
- PhyGeoNet: physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain
- Direct shape optimization through deep reinforcement learning
- Physics-inspired architecture for neural network modeling of forces and torques in particle-laden flows
- DeepM\&Mnet: inferring the electroconvection multiphysics fields based on operator approximation by neural networks
- Deep reinforcement learning for the control of conjugate heat transfer
- Data-driven fractional subgrid-scale modeling for scalar turbulence: a nonlocal LES approach
- Mesh-Conv: convolution operator with mesh resolution independence for flow field modeling
- Simple computational strategies for more effective physics-informed neural networks modeling of turbulent natural convection
- Machine learning for fluid flow reconstruction from limited measurements
- Data-driven discovery of multiscale chemical reactions governed by the law of mass action
- Adversarial sampling of unknown and high-dimensional conditional distributions
- A general neural particle method for hydrodynamics modeling
- Stable \textit{a posteriori} LES of 2D turbulence using convolutional neural networks: backscattering analysis and generalization to higher \(Re\) via transfer learning
- A robust super-resolution reconstruction model of turbulent flow data based on deep learning
- Deep reinforcement learning of viscous incompressible flow
- A simplified multilayer perceptron detector for the hybrid WENO scheme
- A dynamic mode decomposition technique for the analysis of non-uniformly sampled flow data
- Physics-informed distribution transformers via molecular dynamics and deep neural networks
- Neural-network-based control of discrete-phase concentration in a gas-particle corner flow with optimal energy consumption
- Turbulence theories and statistical closure approaches
- Incorporating grain-scale processes in macroscopic sediment transport models. A review and perspectives for environmental and geophysical applications
- Integration of neural networks with numerical solution of PDEs for closure models development
- Recurrent neural networks (RNNs) learn the constitutive law of viscoelasticity
- A nudged hybrid analysis and modeling approach for realtime wake-vortex transport and decay prediction
- Assimilation of disparate data for enhanced reconstruction of turbulent mean flows
- A review on deep reinforcement learning for fluid mechanics
- Subgrid-scale model for large-eddy simulation of isotropic turbulent flows using an artificial neural network
- Machine learning in sedimentation modelling.
- Machine learning for vortex induced vibration in turbulent flow
- Coupled and uncoupled dynamic mode decomposition in multi-compartmental systems with applications to epidemiological and additive manufacturing problems
- Physics and equality constrained artificial neural networks: application to forward and inverse problems with multi-fidelity data fusion
- ModalPINN: an extension of physics-informed neural networks with enforced truncated Fourier decomposition for periodic flow reconstruction using a limited number of imperfect sensors
- Output-weighted and relative entropy loss functions for deep learning precursors of extreme events
- Data driven modeling of interfacial traction-separation relations using a thermodynamically consistent neural network
- SVD perspectives for augmenting DeepONet flexibility and interpretability
- A projection-based, semi-implicit time-stepping approach for the Cahn-Hilliard Navier-Stokes equations on adaptive octree meshes
- Detection of multiple interacting features of different strength in compressible flow fields
- Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
- Theoretical prerequisites for physically justified machine learning and its applications to fluid dynamics
- PDE-constrained models with neural network terms: optimization and global convergence
- Reinforcement-learning-based control of confined cylinder wakes with stability analyses
- Conditioning and accurate solutions of Reynolds average Navier–Stokes equations with data-driven turbulence closures
- Flow over an espresso cup: inferring 3-D velocity and pressure fields from tomographic background oriented Schlieren via physics-informed neural networks
- Large-eddy simulation on the similarity between wakes of wind turbines with different yaw angles
- Spatio-temporal microstructure of sprays: data science-based analysis and modelling
- The turbulent dynamo
- Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network
- Data-driven resolvent analysis
- From the POD-Galerkin method to sparse manifold models
- A Deep Learning Approach for the Computation of Curvature in the Level-Set Method
- Coherent structure identification in turbulent channel flow using latent Dirichlet allocation
- Cluster-based hierarchical network model of the fluidic pinball – cartographing transient and post-transient, multi-frequency, multi-attractor behaviour
- Application of physics-constrained data-driven reduced-order models to shape optimization
- Physics-guided deep learning for generating turbulent inflow conditions
- High-resolution fluid–particle interactions: a machine learning approach
- VPVnet: a velocity-pressure-vorticity neural network method for the Stokes' equations under reduced regularity
- Machine learning active-nematic hydrodynamics
- Modern Koopman theory for dynamical systems
- Interpreted machine learning in fluid dynamics: explaining relaminarisation events in wall-bounded shear flows
- Solving time dependent Fokker-Planck equations via temporal normalizing flow
- Leveraging reduced-order models for state estimation using deep learning
- Output-weighted optimal sampling for Bayesian regression and rare event statistics using few samples
- Using machine learning to detect the turbulent region in flow past a circular cylinder
- The \(l_1\)-based sparsification of energy interactions in unsteady lid-driven cavity flow
- The structure of reconstructed flows in latent spaces
- Interpreting neural network models of residual scalar flux
- Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows
- Unsupervised deep learning for super-resolution reconstruction of turbulence
- The most robust representations of flow trajectories are Lagrangian coherent structures
- Phase-based control of periodic flows
- Unsupervised modelling of a transitional boundary layer
- Deep neural networks for waves assisted by the Wiener-Hopf method
- Data-driven, physics-based feature extraction from fluid flow fields using convolutional neural networks
- Data-driven discovery of governing equations for fluid dynamics based on molecular simulation
- Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
- Robust flow control and optimal sensor placement using deep reinforcement learning
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)
