A Hybrid Neural Network Emulator for M1 Neutrino Reaction Rates in Binary Neutron Star Merger Simulations
Abstract
We present a neural network emulator for the bns_nurates library, which computes neutrino reaction rates used in binary neutron star merger simulations. Following a hybrid strategy, we emulate only the computationally dominant two-dimensional reactions---pair processes, bremsstrahlung, and inelastic neutrino-electron scattering---while evaluating the inexpensive one-dimensional processes still with bns_nurates. We find that the emulator reproduces the opacities to within a few percent across the relevant thermodynamic conditions and accelerates their evaluation by roughly an order of magnitude. When deployed in a global Athenak binary neutron star merger simulation, it recovers the remnant structure, neutrino luminosities, and ejecta composition of a reference run using the full bns_nurates library, at approximately half the overall cost
Related
- Charged-current neutrino opacity within the relativistic Hartree-Fock framework for astrophysical simulations of core-collapse supernovae and binary neutron star mergers
- An asteroseismic age estimate for the Pleiades using a neural-network emulator of rotating δ Scuti pulsation models
- An updated model of neutrino emission from proto-neutron stars
- Multipolar neutrino radiation in binary neutron star mergers: Angular structure, rotational variability, and implications for electron fraction
- Three-flavor neutrino Boltzmann transport and flavor instabilities in long-lived neutron-star merger remnants
BibTeX
@misc{qiu2026hybrid,
title = {{A Hybrid Neural Network Emulator for M1 Neutrino Reaction Rates in Binary Neutron Star Merger Simulations}},
author = {Yi Qiu and David Radice and Raffaele Ferrari and Albino Perego},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.28740},
eprint = {2610.28740},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.28740},
}
RIS
TY - UNPB
TI - A Hybrid Neural Network Emulator for M1 Neutrino Reaction Rates in Binary Neutron Star Merger Simulations
AU - Yi Qiu
AU - David Radice
AU - Raffaele Ferrari
AU - Albino Perego
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.28740
UR - https://arxiv.org/abs/2610.28740
AB - We present a neural network emulator for the bns_nurates library, which computes neutrino reaction rates used in binary neutron star merger simulations. Following a hybrid strategy, we emulate only the computationally dominant two-dimensional reactions---pair processes, bremsstrahlung, and inelastic neutrino-electron scattering---while evaluating the inexpensive one-dimensional processes still with bns_nurates. We find that the emulator reproduces the opacities to within a few percent across the relevant thermodynamic conditions and accelerates their evaluation by roughly an order of magnitude. When deployed in a global Athenak binary neutron star merger simulation, it recovers the remnant structure, neutrino luminosities, and ejecta composition of a reference run using the full bns_nurates library, at approximately half the overall cost
ER -