Super-resolution reconstruction of turbulent flows with machine learning

Abstract

We use machine learning to perform super-resolution analysis of grossly under-resolved turbulent flow field data to reconstruct the high-resolution flow field. Two machine-learning models are developed; namely the convolutional neural network (CNN) and the hybrid Downsampled Skip-Connection Multi-Scale (DSC/MS) models. These machine-learning models are applied to two-dimensional cylinder wake as a preliminary test and show remarkable ability to reconstruct laminar flow from low-resolution flow field data. We further assess the performance of these models for two-dimensional homogeneous turbulence. The CNN and DSC/MS models are found to reconstruct turbulent flows from extremely coarse flow field images with remarkable accuracy. For the turbulent flow problem, the machine-leaning based super-resolution analysis can greatly enhance the spatial resolution with as little as 50 training snapshot data, holding great potential to reveal subgrid-scale physics of complex turbulent flows. With the growing availability of flow field data from high-fidelity simulations and experiments, the present approach motivates the development of effective super-resolution models for a variety of fluid flows.

14 pages, 10 figures

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Turbulence Modeling in the Age of Data
• A neural network approach for the blind deconvolution of turbulent flows
• Network Structure of Two-Dimensional Decaying Isotropic Turbulence
• Extreme learning machine for reduced order modeling of turbulent geophysical flows
• Inferring flow parameters and turbulent configuration with physics-informed data-assimilation and spectral nudging
• Deep learning of mixing by two 'atoms' of stratified turbulence
• Application of Convolutional Neural Network to Predict Airfoil Lift Coefficient

Cited by in corpus (118)

• Machine Learning for Fluid Mechanics
• Enhancing Computational Fluid Dynamics with Machine Learning
• Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
• Machine learning based spatio-temporal super resolution reconstruction of turbulent flows
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Shallow Neural Networks for Fluid Flow Reconstruction with Limited Sensors
• Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning
• Assessment of supervised machine learning methods for fluid flows
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
• A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstruction
• Machine-learning-based reduced order modeling for unsteady flows around bluff bodies of various shapes
• A new prediction method of unsteady wake flow by the hybrid deep neural network
• Robust flow field reconstruction from limited measurements via sparse representation
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Scientific multi-agent reinforcement learning for wall-models of turbulent flows
• Deep Learning in Deterministic Computational Mechanics
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• Synthetic turbulent inflow generator using machine learning
• A Perspective on Machine Learning Methods in Turbulence Modelling
• Convolutional neural networks for fluid flow analysis: toward effective metamodeling and low-dimensionalization
• From coarse wall measurements to turbulent velocity fields through deep learning
• Sparse identification of nonlinear dynamics with low-dimensionalized flow representations
• Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
• Graph neural networks for laminar flow prediction around random 2D shapes
• High-fidelity reconstruction of turbulent flow from spatially limited data using enhanced super-resolution generative adversarial network
• Experimental velocity data estimation for imperfect particle images using machine learning
• Generalization techniques of neural networks for fluid flow estimation
• A transformer-based synthetic-inflow generator for spatially-developing turbulent boundary layers
• Sub-grid scale model classification and blending through deep learning
• Machine learning building-block-flow wall model for large-eddy simulation
• Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database
• Super-resolution reconstruction of turbulent flow at various Reynolds numbers based on generative adversarial networks
• Synchronization to big-data: nudging the Navier-Stokes equations for data assimilation of turbulent flows
• Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
• Reconstructing velocity and pressure from sparse noisy particle tracks using Physics-Informed Neural Networks
• Physics-inspired architecture for neural network modeling of forces and torques in particle-laden flows
• Sparse sensor reconstruction of vortex-impinged airfoil wake with machine learning
• Generative Modeling of Turbulence
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• Turbulence Enrichment using Physics-informed Generative Adversarial Networks
• Embedding Hard Physical Constraints in Neural Network Coarse-Graining of 3D Turbulence
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Single-snapshot machine learning for super-resolution of turbulence
• Flow Completion Network: Inferring the Fluid Dynamics from Incomplete Flow Information using Graph Neural Networks
• A Review of Mathematical and Computational Methods in Cancer Dynamics
• Multi-scale data reconstruction of turbulent rotating flows with Gappy POD, Extended POD and Generative Adversarial Networks
• Data-driven transient lift attenuation for extreme vortex gust-airfoil interactions
• Deep learning of the spanwise-averaged Navier-Stokes equations
• Data-driven nonlinear turbulent flow scaling with Buckingham Pi variables
• Reconstruction of three-dimensional turbulent flow structures using surface measurements for free-surface flows based on a convolutional neural network
• Identifying key differences between linear stochastic estimation and neural networks for fluid flow regressions
• Influence of adversarial training on super-resolution turbulence reconstruction
• Sampling and resolution characteristics in reduced order models of shallow water equations: intrusive vs non-intrusive
• Stochastic particle advection velocimetry (SPAV): theory, simulations, and proof-of-concept experiments
• Physics-Informed Neural Network Super Resolution for Advection-Diffusion Models
• Three-dimensional generative adversarial networks for turbulent flow estimation from wall measurements
• Ensemble flow reconstruction in the atmospheric boundary layer from spatially limited measurements through latent diffusion models
• Physics-informed neural networks modeling for systems with moving immersed boundaries: application to an unsteady flow past a plunging foil
• Self-critical machine-learning wall-modeled LES for external aerodynamics
• Convolutional-network models to predict wall-bounded turbulence from wall quantities
• Mechanisms of a Convolutional Neural Network for Learning Three-dimensional Unsteady Wake Flow
• Robust training approach of neural networks for fluid flow state estimations
• Compressing fluid flows with nonlinear machine learning: mode decomposition, latent modeling, and flow control
• Tensor-based flow reconstruction from optimally located sensor measurements
• Frame invariant neural network closures for Kraichnan turbulence
• Towards learning Lattice Boltzmann collision operators
• Deep Hierarchical Super Resolution for Scientific Data
• Predictive data-driven model based on generative adversarial network for premixed turbulence-combustion regimes
• Inserting machine-learned virtual wall velocity for large-eddy simulation of turbulent channel flows
• Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint
• Reconstructing three-dimensional bluff body wake from sectional flow fields with convolutional neural networks
• Robust deep learning for emulating turbulent viscosities
• Turbulence Scaling from Deep Learning Diffusion Generative Models
• Dimension Reduced Turbulent Flow Data From Deep Vector Quantizers
• Reconstructing unsteady flows from sparse, noisy measurements with a physics-constrained convolutional neural network
• Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
• Painting baryons onto N-body simulations of galaxy clusters with image-to-image deep learning
• Forecasting through deep learning and modal decomposition in two-phase concentric jets
• Generative prediction of flow fields around an obstacle using the diffusion model
• Data assimilation empowered neural network parameterizations for subgrid processes in geophysical flows
• Dynamics of a Data-Driven Low-Dimensional Model of Turbulent Minimal Pipe Flow
• Godunov Loss Functions for Modelling of Hyperbolic Conservation Laws
• Deep Learning for Efficient Reconstruction of High-Resolution Turbulent DNS Data
• Stop-and-go wave super-resolution reconstruction via iterative refinement
• Uncovering dynamically critical regions in near-wall turbulence using 3D Convolutional Neural Networks
• Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection
• Model-based multi-sensor fusion for reconstructing wall-bounded turbulence
• Using neural networks to solve the 2D Poisson equation for electric field computation in plasma fluid simulations
• Data compression for turbulence databases using spatio-temporal sub-sampling and local re-simulation
• Data-Driven Modeling of Geometry-Adaptive Steady Heat Transfer based on Convolutional Neural Networks: Heat Conduction
• Super-resolution reconstruction of turbulent flows from a single Lagrangian trajectory
• A wall model based on neural networks for LES of turbulent flows over periodic hills
• Towards high-accuracy deep learning inference of compressible turbulent flows over aerofoils
• Neural Network Complexity of Chaos and Turbulence
• A comparative study of various Deep Learning techniques for spatio-temporal Super-Resolution reconstruction of Forced Isotropic Turbulent flows
• Defiltering turbulent flow fields for Lagrangian particle tracking using machine learning techniques
• Model order reduction with neural networks: Application to laminar and turbulent flows
• Assimilation of disparate data for enhanced reconstruction of turbulent mean flows
• Network-based analysis of fluid flows: Progress and outlook
• On Deep-Learning-Based Closures for Algebraic Surrogate Models of Turbulent Flows
• PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics
• A turbulent eddy-viscosity surrogate modeling framework for Reynolds-Averaged Navier-Stokes simulations
• Reconstructing High-resolution Turbulent Flows Using Physics-Guided Neural Networks
• Reconstruction of three-dimensional turbulent flows from sparse and noisy planar measurements: A weight-sharing neural network approach
• Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence
• UCNN: A Convolutional Strategy on Unstructured Mesh
• Three-dimensional realizations of flood flow in large-scale rivers using the neural fuzzy-based machine-learning algorithm
• Adversarial sampling of unknown and high-dimensional conditional distributions
• Assessment of jet inflow conditions on the development of supersonic jet flows
• Latent attention on masked patches for flow reconstruction
• Generative Reconstruction of Spatiotemporal Wall-Pressure in Turbulent Boundary Layers via Patchwise Latent Diffusion
• Prediction of three-dimensional flood-flow past bridge piers in a large-scale meandering river using convolutional neural networks
• Physics-Informed Machine Learning of the Lagrangian Dynamics of Velocity Gradient Tensor
• Dynamic Deep Learning Based Super-Resolution For The Shallow Water Equations
• Modelling of Flow Past Long Cylindrical Structures