Application of neural networks for the reconstruction of supernova neutrino energy spectra following fast neutrino flavor conversions
Sajad Abbar, Meng-Ru Wu, Zewei Xiong
Abstract
Neutrinos can undergo fast flavor conversions (FFCs) within extremely dense astrophysical environments, such as core-collapse supernovae (CCSNe) and neutron star mergers (NSMs). In this study, we explore FFCs in a neutrino gas, revealing that when the FFC growth rate significantly exceeds that of the vacuum Hamiltonian, all neutrinos (regardless of energy) share a common survival probability dictated by the energy-integrated neutrino spectrum. We then employ physics-informed neural networks (PINNs) to predict the asymptotic outcomes of FFCs within such a multienergy neutrino gas. These predictions are based on the first two moments of neutrino angular distributions for each energy bin, typically available in state-of-the-art CCSN and NSM simulations. Our PINNs achieve errors as low as <a:math xmlns:a="http://www.w3.org/1998/Math/MathML" display="inline"><a:mo>≲</a:mo><a:mn>6</a:mn><a:mo>%</a:mo></a:math> and <c:math xmlns:c="http://www.w3.org/1998/Math/MathML" display="inline"><c:mo>≲</c:mo><c:mn>18</c:mn><c:mo>%</c:mo></c:math> for predicting the number of neutrinos in the electron channel and the relative absolute error in the neutrino moments, respectively. Published by the American Physical Society 2024