First-ever black hole photo gets sharper thanks to AI

In 2019, National Science Foundation and Event Horizon Telescope captured the first-ever photo of a supermassive black hole. And now, the blurry blob that excited us so much back then has got its fancy, sharp, more detailed version.

A team of researchers has developed a new AI model and used it to give the iconic photo a makeover. This gives us a totally new look at the black hole and gives scientists more information about it.

[Related reading: First photo of the black hole in the centre of the Milky Way is revealed]

The original image shows a supermassive black hole and its shadow at the heart of a distant galaxy Messier 87, 55 million light-years from Earth. As I mentioned, it was captured with the Event Horizon Telescope (EHT), which is made of an array of eight ground-based radio telescopes. It was designed particularly to capture images of a black hole, and as we all know – it performed its task successfully.

A team of researchers has developed a new machine-learning technique called PRIMO (principal-component interferometric modeling). This AI enhances the fidelity and sharpness of radio interferometry images, and they tested it on EHT’s famous image. Here are the two versions compared:

PRIMO was developed by EHT members Lia Medeiros (Institute for Advanced Study), Dimitrios Psaltis (Georgia Tech), Tod Lauer (NSF’s NOIRLab), and Feryal Ozel (Georgia Tech). A paper describing their work is published in The Astrophysical Journal Letters.

“With our new machine-learning technique, PRIMO, we were able to achieve the maximum resolution of the current array,” says lead author Lia Medeiros. “Since we cannot study black holes up close, the detail in an image plays a critical role in our ability to understand its behavior. The width of the ring in the image is now smaller by about a factor of two, which will be a powerful constraint for our theoretical models and tests of gravity.”

[via Space.com]