Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows
From MaRDI portal
Publication:5145046
DOI10.1017/jfm.2020.948zbMath1461.76306arXiv2004.11566OpenAlexW3114871366MaRDI QIDQ5145046
Kunihiko Taira, Koji Fukagata, Kai Fukami
Publication date: 19 January 2021
Published in: Journal of Fluid Mechanics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2004.11566
Related Items (27)
Reconstruction of three-dimensional turbulent flow structures using surface measurements for free-surface flows based on a convolutional neural network ⋮ Mesh-Conv: convolution operator with mesh resolution independence for flow field modeling ⋮ Adversarial sampling of unknown and high-dimensional conditional distributions ⋮ Unsteady flow prediction from sparse measurements by compressed sensing reduced order modeling ⋮ High-resolution fluid–particle interactions: a machine learning approach ⋮ PhySR: physics-informed deep super-resolution for spatiotemporal data ⋮ Predicting turbulent dynamics with the convolutional autoencoder echo state network ⋮ Variational multiscale super‐resolution: A data‐driven approach for reconstruction and predictive modeling of unresolved physics ⋮ Multi-scale reconstruction of turbulent rotating flows with proper orthogonal decomposition and generative adversarial networks ⋮ Four-dimensional variational data assimilation of a turbulent jet for super-temporal-resolution reconstruction ⋮ A physics-informed diffusion model for high-fidelity flow field reconstruction ⋮ Geometric Schrödinger microfluidic modeling for spherical ferromagnetic mKdV flux ⋮ Sub-grid scale model classification and blending through deep learning ⋮ Using machine learning to detect the turbulent region in flow past a circular cylinder ⋮ Turbulence theories and statistical closure approaches ⋮ Sparse identification of nonlinear dynamics with low-dimensionalized flow representations ⋮ A turbulent eddy-viscosity surrogate modeling framework for Reynolds-averaged Navier-Stokes simulations ⋮ Shallow neural networks for fluid flow reconstruction with limited sensors ⋮ Prediction of turbulent heat transfer using convolutional neural networks ⋮ A data-driven model based on modal decomposition: application to the turbulent channel flow over an anisotropic porous wall ⋮ Reconstruction, optimization, and design of heterogeneous materials and media: basic principles, computational algorithms, and applications ⋮ Nonlinear mode decomposition with convolutional neural networks for fluid dynamics ⋮ Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression ⋮ Three-dimensional realizations of flood flow in large-scale rivers using the neural fuzzy-based machine-learning algorithms ⋮ Kinetic-energy-flux-constrained model using an artificial neural network for large-eddy simulation of compressible wall-bounded turbulence ⋮ Predicting drag on rough surfaces by transfer learning of empirical correlations ⋮ A transformer-based synthetic-inflow generator for spatially developing turbulent boundary layers
Uses Software
Cites Work
- A fast immersed boundary method using a nullspace approach and multi-domain far-field boundary conditions
- Machine learning closures for model order reduction of thermal fluids
- The immersed boundary method: a projection approach
- Network structure of two-dimensional decaying isotropic turbulence
- Reducing the Dimensionality of Data with Neural Networks
- Machine Learning for Fluid Mechanics
- Subgrid modelling for two-dimensional turbulence using neural networks
- Turbulence statistics in fully developed channel flow at low Reynolds number
- Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations
- Data-driven prediction of unsteady flow over a circular cylinder using deep learning
- Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
- Learning representations by back-propagating errors
- Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
- Deep learning in fluid dynamics
- Turbulence Modeling in the Age of Data
- Approximation by superpositions of a sigmoidal function
This page was built for publication: Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows
