Learning a generalized Navier-Stokes model beyond the continuum regime

DOI10.48550/arXiv.2610.07952MaRDI QIDQ7374820zbMATH OpenarXivFDO

Authors Sihong Shao, Yanli Wang, Zhongwei Xu

Publication date 6 October 2026

Published in arXiv

Tldr A data-driven generalized Navier-Stokes (GNS) model is proposed by learning a relationship between non-equilibrium variables and equilibrium variables from the Boltzmann equation's numerical solutions. This enables extending NS equations' applicability into the transition regime with reduced computational cost compared to the kinetic description given by the Boltzmann equation.

Full work available at URL https://doi.org/10.48550/arXiv.2610.07952

arXiv classification

math.NAphysics.flu-dyn

Cites work

• A fast spectral method for the Boltzmann collision operator with general collision kernels
• A framework for hyperbolic approximation of kinetic equations using quadrature-based projection methods
• Comparison of neural closure models for discretised PDEs
• Coupled constitutive relations: a second law based higher-order closure for hydrodynamics
• Decoupled Weight Decay Regularization
• Globally Hyperbolic Regularization of Grad's Moment System
• Hyperbolic Machine Learning Moment Closures for the BGK Equations
• Hyperbolic machine learning moment closures for the BGK equations
• Learning invariance preserving moment closure model for Boltzmann-BGK equation
• Machine learning-based moment closure model for the semiconductor Boltzmann equation with uncertainties
• New high-resolution central schemes for nonlinear conservation laws and convection-diffusion equations
• On the kinetic theory of rarefied gases
• Optimization methods for large-scale machine learning
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Regularized 13-moment equations for inverse power law models
• Solving continuum and rarefied flows using differentiable programming
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• Uniformly accurate machine learning-based hydrodynamic models for kinetic equations

This page was built for publication: Learning a generalized Navier-Stokes model beyond the continuum regime

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7374820)