Frame invariant neural network closures for Kraichnan turbulence

DOI10.1016/j.physa.2022.128327OpenAlexW4309185442MaRDI QIDQ2111612

Suraj Pawar, Adil Rasheed, Prakash Vedula, Omer San

Publication date: 17 January 2023

Published in: Physica A (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.02928

zbMATH Keywords

geophysical flowsequivariant neural networksframe invariancessubgrid scale closure modeling

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX)

Related Items

A multifidelity deep operator network approach to closure for multiscale systems

Uses Software

• Fluid flow phenomena
• GitHub

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Backscatter in the rational LES model
• Computational design for long-term numerical integration of the equations of fluid motion: Two-dimensional incompressible flow. I
• A simple and stable scale-similarity model for large eddy simulation: Energy balance and existence of weak solutions
• A stable and scale-aware dynamic modeling framework for subgrid-scale parameterizations of two-dimensional turbulence
• High order accurate finite difference schemes based on symmetry preservation
• Neural networks based subgrid scale modeling in large eddy simulations
• A domain decomposition method for the non-intrusive reduced order modelling of fluid flow
• Attention-based convolutional autoencoders for 3D-variational data assimilation
• A nonintrusive hybrid neural-physics modeling of incomplete dynamical systems: Lorenz equations
• Spatiotemporally dynamic implicit large eddy simulation using machine learning classifiers
• Data-driven reduced order model with temporal convolutional neural network
• Data-driven modelling of nonlinear spatio-temporal fluid flows using a deep convolutional generative adversarial network
• Subgrid-scale model for large-eddy simulation of isotropic turbulent flows using an artificial neural network
• High-order methods for decaying two-dimensional homogeneous isotropic turbulence
• Stationary two-dimensional turbulence statistics using a Markovian forcing scheme
• A paradigm for data-driven predictive modeling using field inversion and machine learning
• Invariant data-driven subgrid stress modeling in the strain-rate eigenframe for large eddy simulation
• Two-Dimensional Turbulence
• Mathematics of Large Eddy Simulation of Turbulent Flows
• Scale-similar models for large-eddy simulations
• An approximate deconvolution model for large-eddy simulation with application to incompressible wall-bounded flows
• Galilean invariance of subgrid-scale stress models in the large-eddy simulation of turbulence
• A dynamic subgrid-scale eddy viscosity model
• Subgrid-scale backscatter in turbulent and transitional flows
• Vortex merging in quasi-geostrophic flows
• Turbulent Flows
• Subgrid modelling for two-dimensional turbulence using neural networks
• A dynamic eddy-viscosity closure model for large eddy simulations of two-dimensional decaying turbulence
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Learning data-driven discretizations for partial differential equations
• Reynolds-averaged Navier–Stokes equations with explicit data-driven Reynolds stress closure can be ill-conditioned
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• Turbulence Modeling in the Age of Data
• Sub-grid scale model classification and blending through deep learning
• Computation of the Energy Spectrum in Homogeneous Two-Dimensional Turbulence
• Large Eddy Simulation for Incompressible Flows