Neural network based dynamic domain decomposition for multiscale kinetic equations

DOI10.4208/CICP.OA-2025-0228MaRDI QIDQ7363039zbMATH OpenFDO

Authors Q. Wang, Yi Cai, Tao Xiong

Publication date 29 September 2026

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

Full work available at URL https://doi.org/10.4208/CICP.OA-2025-0228

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Finite volume methods for initial value and initial-boundary value problems involving PDEs (65M08) Artificial neural networks and deep learning (68T07) Rarefied gas flows, Boltzmann equation in fluid mechanics (76P05)

Cites work

• A data-driven shock capturing approach for discontinuous Galerkin methods
• A discontinuous Galerkin implementation of a domain decomposition method for kinetic-hydrodynamic coupling multiscale problems in gas dynamics and device simulations
• A hierarchical uniformly high order DG-IMEX scheme for the 1D BGK equation
• A hierarchy of hybrid numerical methods for multiscale kinetic equations
• A hybrid discontinuous Galerkin scheme for multi-scale kinetic equations
• A hybrid method for hydrodynamic-kinetic flow. II: Coupling of hydrodynamic and kinetic models
• A Model for Collision Processes in Gases. I. Small Amplitude Processes in Charged and Neutral One-Component Systems
• A multiscale kinetic-fluid solver with dynamic localization of kinetic effects
• A particle-particle hybrid method for kinetic and continuum equations
• Approximation by superpositions of a sigmoidal function
• Coupling of the Boltzmann and Euler equations with automatic domain decomposition
• Fluid simulations with localized Boltzmann upscaling by direct simulation Monte-Carlo
• Gas flows caused by evaporation and condensation on two parallel condensed phases and the negative temperature gradient: Numerical analysis by using a nonlinear kinetic equation
• Learning representations by back-propagating errors
• Moment realizability and the validity of the Navier–Stokes equations for rarefied gas dynamics
• Predicting continuum breakdown with deep neural networks
• Predicting failure of the continuum fluid equations in transitional hypersonic flows
• Simulations of micro channel gas flows with domain decomposition technique for kinetic and fluid dynamics equations
• Unified solver for rarefied and continuum flows with adaptive mesh and algorithm refinement

This page was built for publication: Neural network based dynamic domain decomposition for multiscale kinetic equations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7363039)