Small neural networks trained on exact solutions can replace the iterative root-finding in a relativistic Riemann solver, giving exact-like accuracy about 14 times faster in 1D tests.
Numerical hydrodynamics in special relativity
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This review is concerned with a discussion of numerical methods for the solution of the equations of special relativistic hydrodynamics (SRHD). Particular emphasis is put on a comprehensive review of the application of high-resolution shock-capturing methods in SRHD. Results obtained with different numerical SRHD methods are compared, and two astrophysical applications of SRHD flows are discussed. An evaluation of the various numerical methods is given and future developments are analyzed.
citation-role summary
background 1
citation-polarity summary
fields
gr-qc 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A "Neural" Riemann solver for Relativistic Hydrodynamics
Small neural networks trained on exact solutions can replace the iterative root-finding in a relativistic Riemann solver, giving exact-like accuracy about 14 times faster in 1D tests.