AI and the World's Hard Problems · Astronomy & space · arXiv · 2026-10-23
Simulation-based inference of profile evolution for high-precision pulsar timing
Pulsar profiles change shape with observing frequency, which biases arrival-time measurements if not modelled, and existing profile-domain timing methods rely on computationally expensive stochastic sampling. The authors propose a simulation-based inference approach that uses a normalising flow conditioned on a convolutional embedding of the frequency-phase portrait. From a single portrait, it returns joint posteriors for dispersion measures, arrival times and profile-evolution parameters almost instantly.