AI and the World's Hard Problems · Astronomy & space · arXiv · 2026-10-20
A deep learning algorithm for black hole spin estimation using hot-spot secondary images
The authors built a deep learning model that links hot-spot emission radius, black hole inclination and spin to the position-angle difference between primary and secondary images of a hot spot near Sagittarius A*. Using the IPOLE radiative transfer code, they generated about 100,000 models. Their algorithm STIHOS estimated spin and inclination accurately in most observational tests, including cases where only half of the orbit is visible.