Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection

Abstract

A wavelet-based machine learning method is proposed for predicting the time evolution of homogeneous isotropic turbulence where vortex tubes are preserved. Three-dimensional convolutional neural networks and long short-term memory are trained with a time series of direct numerical simulation (DNS) data of homogeneous isotropic turbulence at the Taylor microscale Reynolds number 92. The predicted results are assessed by using flow visualization of vorticity and statistics, e.g., probability density functions of vorticity and enstrophy spectra. It is found that the predicted results are in good agreement with DNS results. The small-scale flow topology considering the second and third invariant of the velocity gradient tensor likewise shows an approximate match. Furthermore, we apply the pre-trained neural networks to coarse-grained vorticity data using superresolution. It is shown that the superresolved flow field well agrees with the reference DNS field and thus small-scale information and vortex tubes are well regenerated.

arXiv comment34 pages, 18 figures

References in corpus (22)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Machine Learning for Fluid Mechanics
• Turbulence Modeling in the Age of Data
• Fourier Neural Operator for Parametric Partial Differential Equations
• Super-resolution reconstruction of turbulent flows with machine learning
• Enhancing Computational Fluid Dynamics with Machine Learning
• Neural Ordinary Differential Equations
• Fluid Particle Accelerations in Fully Developed Turbulence
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
• Machine-learning-based reduced order modeling for unsteady flows around bluff bodies of various shapes
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• From coarse wall measurements to turbulent velocity fields through deep learning
• Modeling the pressure Hessian and viscous Laplacian in Turbulence: comparisons with DNS and implications on velocity gradient dynamics
• High-fidelity reconstruction of turbulent flow from spatially limited data using enhanced super-resolution generative adversarial network
• A transformer-based synthetic-inflow generator for spatially-developing turbulent boundary layers
• Long-term predictions of turbulence by implicit U-Net enhanced Fourier neural operator
• Divergence-free Wavelets for Navier-Stokes
• Super-Resolution Simulation for Real-Time Prediction of Urban Micrometeorology
• Validation and parameterization of a novel physics-constrained neural dynamics model applied to turbulent fluid flow
• Neural network models for preferential concentration of particles in two-dimensional turbulence

Cited by in corpus (2)

• Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
• Turbulent Injection assisted by Diffusion Models for Scale Resolving Simulations