Unsupervised deep learning for super-resolution reconstruction of turbulence

Abstract

Recent attempts to use deep learning for super-resolution reconstruction of turbulent flows have used supervised learning, which requires paired data for training. This limitation hinders more practical applications of super-resolution reconstruction. Therefore, we present an unsupervised learning model that adopts a cycle-consistent generative adversarial network that can be trained with unpaired turbulence data for super-resolution reconstruction. Our model is validated using three examples: (i) recovering the original flow field from filtered data using direct numerical simulation (DNS) of homogeneous isotropic turbulence; (ii) reconstructing full-resolution fields using partially measured data from the DNS of turbulent channel flows; and (iii) generating a DNS-resolution flow field from large eddy simulation (LES) data for turbulent channel flows. In examples (i) and (ii), for which paired data are available for supervised learning, our unsupervised model demonstrates qualitatively and quantitatively similar performance as that of the best supervised-learning model. More importantly, in example (iii), where supervised learning is impossible, our model successfully reconstructs the high-resolution flow field of statistical DNS quality from the LES data. This demonstrates that unsupervised learning of turbulence data is indeed possible, opening a new door for the wide application of super-resolution reconstruction of turbulent fields.

References in corpus (19)

• Machine Learning for Fluid Mechanics
• Turbulence Modeling in the Age of Data
• Direct numerical simulation of turbulent channel flow up to $R{e}_{\tau }\approx 5200$
• Super-resolution reconstruction of turbulent flows with machine learning
• A public turbulence database cluster and applications to study Lagrangian evolution of velocity increments in turbulence
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• Artificial Neural Networks trained through Deep Reinforcement Learning discover control strategies for active flow control
• Deep Neural Networks for Data-Driven Turbulence Models
• Data-driven prediction of unsteady flow fields over a circular cylinder using deep learning
• Machine learning based spatio-temporal super resolution reconstruction of turbulent flows
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Searching for turbulence models by artificial neural network
• Assessment of supervised machine learning methods for fluid flows
• A neural network approach for the blind deconvolution of turbulent flows
• Synthetic turbulent inflow generator using machine learning
• Deep unsupervised learning of turbulence for inflow generation at various Reynolds numbers
• Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database
• Synchronization to big-data: nudging the Navier-Stokes equations for data assimilation of turbulent flows
• A Multi-Pass GAN for Fluid Flow Super-Resolution

Cited by in corpus (45)

• Enhancing Computational Fluid Dynamics with Machine Learning
• Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning
• 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
• Improving aircraft performance using machine learning: a review
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• From coarse wall measurements to turbulent velocity fields through deep learning
• 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
• A transformer-based synthetic-inflow generator for spatially-developing turbulent boundary layers
• Super-resolution reconstruction of turbulent flow at various Reynolds numbers based on generative adversarial networks
• Deep reinforcement learning for large-eddy simulation modeling in wall-bounded turbulence
• Sparse sensor reconstruction of vortex-impinged airfoil wake with machine learning
• Generative Modeling of Turbulence
• Single-snapshot machine learning for super-resolution of turbulence
• Forecasting small scale dynamics of fluid turbulence using deep neural networks
• Multi-scale data reconstruction of turbulent rotating flows with Gappy POD, Extended POD and Generative Adversarial Networks
• 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
• Influence of adversarial training on super-resolution turbulence reconstruction
• Investigation of nonlocal data-driven methods for subgrid-scale stress modelling in large eddy simulation
• Stochastic particle advection velocimetry (SPAV): theory, simulations, and proof-of-concept experiments
• A physics-inspired alternative to spatial filtering for large-eddy simulations of turbulent flows
• Robust training approach of neural networks for fluid flow state estimations
• Deep learning fluid flow reconstruction around arbitrary two-dimensional objects from sparse sensors using conformal mappings
• Frame invariant neural network closures for Kraichnan turbulence
• Predictive data-driven model based on generative adversarial network for premixed turbulence-combustion regimes
• Scalable communication for high-order stencil computations using CUDA-aware MPI
• Reconstructing three-dimensional bluff body wake from sectional flow fields with convolutional neural networks
• Generative Adversarial Networks to infer velocity components in rotating turbulent flows
• Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
• Reconstructing unsteady flows from sparse, noisy measurements with a physics-constrained convolutional neural network
• Generative prediction of flow fields around an obstacle using the diffusion model
• Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection
• Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks
• Neural Network Complexity of Chaos and Turbulence
• Machine-learning-based simulation of turbulent flows over periodic hills using a hybrid U-Net and Fourier neural operator framework
• Model-based time super-sampling of turbulent flow field sequences
• Spatiotemporal wall pressure forecast of a rectangular cylinder with physics-aware DeepU-Fourier neural network
• A multiscale and multicriteria Generative Adversarial Network to synthesize 1-dimensional turbulent fields
• On Deep-Learning-Based Closures for Algebraic Surrogate Models of Turbulent Flows
• Reconstruction of three-dimensional turbulent flows from sparse and noisy planar measurements: A weight-sharing neural network approach
• Correlation and decomposition framework for identifying and disentangling flow structures: canonical examples and application to isotropic turbulence
• Guided Unconditional and Conditional Generative Models for Super-Resolution and Inference of Quasi-Geostrophic Turbulence