Machine learning-based detection of nonaxisymmetric fast neutrino flavor instabilities in core-collapse supernovae

In dense neutrino environments like core-collapse supernovae (CCSNe) and neutron star mergers, neutrinos can undergo fast flavor conversions when their angular distribution of neutrino electron lepton number (νELN) crosses zero along some directions. While previous studies have demonstrated the detection of axisymmetric νELN crossings in these extreme environments, nonaxisymmetric crossings have remained elusive, mostly due to the absence of models for their angular distributions. In this study, we present a pioneering analysis of the detection of nonaxisymmetric νELN crossings using machine learning (ML) techniques. Our ML models are trained on data from two CCSN simulations, one with rotation and one without, where nonaxisymmetric features in neutrino angular distributions play a crucial role. We demonstrate that our ML models achieve detection accuracies exceeding 90%. This is an important improvement, especially considering that a significant portion of νELN crossings in these models eluded detection by earlier methods. Published by the American Physical Society 2025