RotEqNet: rotation-equivariant network for fluid systems with symmetric high-order tensors

DOI10.1016/J.JCP.2022.111205MaRDI QIDQ2138017zbMATH OpenOpenAlexWikidataFDO

Authors Liyao Gao, Yifan Du, Hongshan Li, Guang Lin

Publication date 11 May 2022

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2005.04286

zbMATH Keywords

machine learningtensor analysisfluid systemsrotation-equivariant

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Turbulence (76Fxx) Fluid mechanics (76-XX)

Recommendations

• Learning Lagrangian fluid mechanics with E(3)-equivariant graph neural networks
• An equivariant neural operator for developing nonlocal tensorial constitutive models
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• Theoretical prerequisites for physically justified machine learning and its applications to fluid dynamics
• Hidden fluid mechanics: Learning velocity and pressure fields from flow visualizations

Cites work

• scientific article; zbMATH DE number 6003858 (Why is no real title available?)
• scientific article; zbMATH DE number 3130180 (Why is no real title available?)
• scientific article; zbMATH DE number 1032051 (Why is no real title available?)
• scientific article; zbMATH DE number 3245332 (Why is no real title available?)
• A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials
• A more general effective-viscosity hypothesis
• A theory of the learnable
• Accelerating flash calculation through deep learning methods
• Continuum mechanics for engineers.
• Deep learning in fluid dynamics
• Fourth-rank tensors of the thirty-two crystal classes: multiplication tables
• LARGE-EDDY SIMULATION OF TURBULENT COMBUSTION
• Learnability and the Vapnik-Chervonenkis dimension
• Machine learning strategies for systems with invariance properties
• Multilayer feedforward networks are universal approximators
• Neural network modeling for near wall turbulent flow.
• On isotropic integrity bases
• Pattern recognition and machine learning.
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• Scikit-learn: machine learning in Python
• Some recent developments in turbulence closure modeling
• Subgrid-scale modelling for the large-eddy simulation of high-Reynolds-number boundary layers
• The handbook of fluid dynamics
• The optimal sample complexity of PAC learning

Cited in

(2)

• An equivariant neural operator for developing nonlocal tensorial constitutive models
• Learning Lagrangian fluid mechanics with E(3)-equivariant graph neural networks

Describes a project that uses

Uses Software

• randomForest
• Scikit
• Adam
• torchdiffeq
• PRMLT
• RotDCF
• RotEqNet

This page was built for publication: RotEqNet: rotation-equivariant network for fluid systems with symmetric high-order tensors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2138017)