Machine Learning Acceleration of Neutron Star Pulse Profile Modeling

Abstract Ray-tracing algorithms that compute pulse profiles from rotating neutron stars are essential tools for constraining neutron star properties with data from missions such as Neutron star Interior Composition Explorer. However, the high computational cost of these simulations presents a significant bottleneck for inference algorithms that require millions of evaluations, such as Markov Chain Monte Carlo methods. In this work, we develop a neural network model that accelerates this calculation by predicting the observed flux from the surface of a spinning neutron star as a function of its physical parameters and rotational phase. Leveraging GPU-parallelized evaluation, we demonstrate that our model achieves many orders of magnitude speedup compared to traditional ray tracing while maintaining high accuracy. We also show that the trained network can efficiently accommodate complex emission geometries, including noncircular and multiple hotspots, by integrating over localized flux patches.