This PRIMO refined image of M87* gives scientists a chance to better match observations of an actual black hole to theoretical predictions.
"It provides a way to compensate for the missing information about the object being observed, which is required to generate the image that would have been seen using a single gigantic radio telescope the size of the Earth."Princeton's Institute of Advanced Study explained that PRIMO operates using dictionary learning, a branch of machine learning which enables computers to generate rules based on large sets of training material.
Once identified, these patterns were sorted based on how often they factored into simulations. This could then be incorporated into EHT images to create a high-fidelity image of M87* and reveal structures the telescope array may have missed.
No big deal. A thinner doughnut.
This is all wrong from an empirical point of view. The AI is trained using General Relativity making the image biased. This does not help in testing GR in the strong gravity regime. So it's not scientific .
Can we just admire that it looked exactly as it was predicted? There are more phenomena that relativity predicts, and I wonder if those things are actually out there.