Application of Neural Networks for the Reconstruction of Supernova Neutrino Energy Spectra Following Fast Neutrino Flavor Conversions
This work addresses the challenge of modeling neutrino behavior in supernovae and neutron star mergers, offering a computational tool for astrophysicists, though it is incremental as it applies existing PINN methods to a specific domain problem.
The study tackled the problem of predicting fast neutrino flavor conversions in dense astrophysical environments by using physics-informed neural networks to reconstruct neutrino energy spectra, achieving errors as low as ~6% for neutrino counts and ~18% for moment predictions.
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 \emph{multi-energy} 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 multi-energy 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 $\lesssim6\%$ and $\lesssim 18\%$ for predicting the number of neutrinos in the electron channel and the relative absolute error in the neutrino moments, respectively.