A Hyperbolic Neural Closure for M1 Radiation Transfer

DOI10.48550/arXiv.2607.10364MaRDI QIDQ7284135arXivFDO

Authors Jiahao Zhang, Johannes Krotz, Dinshaw S. Balsara, Bongseok Kim, Dinshaw Balsara, Ryan McClarren, Guang Lin

Publication date 11 July 2026

Published in arXiv

Tldr We develop a novel hyperbolic neural closure for M1 radiation transfer, ensuring real eigenvalues of the Jacobian by parameterizing it through a symmetric matrix network and an entropy network, achieving both higher closure accuracy and improved solution stability in numerical simulations.

Full work available at URL https://doi.org/10.48550/arXiv.2607.10364

arXiv classification

cs.AIcs.CEcs.LGmath.NA

Cites work

• A hybrid Monte Carlo, discontinuous Galerkin method for linear kinetic transport equations
• A neural network closure for the Euler-Poisson system based on kinetic simulations
• A structure-preserving surrogate model for the closure of the moment system of the Boltzmann equation using convex deep neural networks
• An efficient class of WENO schemes with adaptive order for unstructured meshes
• An efficient, second order accurate, universal generalized Riemann problem solver based on the HLLI Riemann solver
• An implicit Monte Carlo scheme for calculating time and frequency dependent nonlinear radiation transport
• Approximate models for radiative transfer
• Data-driven, structure-preserving approximations to entropy-based moment closures for kinetic equations
• High-order entropy-based closures for linear transport in slab geometry
• Hyperbolic Conservation Laws in Continuum Physics
• Learning invariance preserving moment closure model for Boltzmann-BGK equation
• Machine learning moment closure models for the radiative transfer equation I: directly learning a gradient based closure
• Machine learning moment closure models for the radiative transfer equation IV: enforcing symmetrizable hyperbolicity in two dimensions
• Moment closure hierarchies for kinetic theories.
• Numerical approximation of hyperbolic systems of conservation laws
• Parametric Hyperbolic Conservation Laws: A Unified Framework for Conservation, Entropy Stability, and Hyperbolicity
• Structure-preserving neural networks for the regularized entropy-based closure of a linear, kinetic, radiative transport equation
• The Runge-Kutta discontinuous Galerkin method for conservation laws. I: Multidimensional systems
• Uniformly accurate machine learning-based hydrodynamic models for kinetic equations

This page was built for publication: A Hyperbolic Neural Closure for M1 Radiation Transfer

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7284135)