A team of researchers has developed a machine learning technique to give the first-ever image of a supermassive black hole a sharper new look.

The iconic image of the supermassive black hole at the center of Messier 87 is the result of a massive international collaboration of more than 200 astronomers. Event Horizon Telescope (EHT) scientists used a planet-wide array of seven ground-based telescopes to capture the incredible image. Since the first observations, additional telescopes have been added to the network.

The original image shared in 2019 is incredible, of course, but thanks to advances in artificial intelligence (AI), a research team has developed a machine learning technique called PRIMO that maximizes the resolution possibilities of the telescope network. existing.

PRIMO stands for Principal Component Interferometric Modeling, and it 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). An article describing the work of the team was published in Letters from the Astrophysical Journal.

PRIMO relies on a type of machine learning called dictionary learning. This technique teaches computers specific rules by exposing them to “thousands of examples”. The team exposed PRIMO to the EHT image of Messier 87, and computers analyzed more than 30,000 high-fidelity simulated images of “gas accreting on a black hole” to find common patterns among the tens of thousands of images. simulated.

Espace.com explains that the identified patterns were then sorted by how frequently they affected the simulations, which helped PRIMO reveal structures that the telescope array might have missed during initial observations.

“We are using physics to fill in missing data regions in a way that has never been done before using machine learning. This could have important implications for interferometry, which plays a role in fields ranging from exoplanets to medicine,” says Medeiros in a press release issued by The Institute for Advanced Studies.

“The results were then combined to provide a highly accurate representation of the EHT observations, simultaneously providing a high-fidelity estimate of the missing structure in the image,” explains NOIRLab. The machine learning algorithm used to create the sharp new photo is detailed in The Astrophysical Journal.

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

“PRIMO is a new approach to the difficult task of constructing images from EHT observations. It provides a way to compensate for missing information about the observed object, which is needed to generate the image that would have been seen using a single gigantic Earth-sized radio telescope,” says Tod Lauer.

Considering the new photo is technically the result of numerous AI-generated simulations, it’s natural to wonder how realistic it is.

“The team confirmed that the newly rendered image is consistent with EHT data and with theoretical expectations, including the bright emission ring that should be produced by hot gas falling into the black hole,” says NOIRLab. .

Using the original image, scientists determined that black hole Messier 87 is 40 billion kilometers (~25 million miles) in diameter, or nearly 29,000 suns. The black hole, which is about 500 million billion kilometers (~311 million billion miles) away, is believed to have a mass about 6.5 billion times that of the Sun.

However, these numbers may be revised due to the image AI upgrade. Scientists can study the new image to determine the mass of the black hole Messier 87 with additional precision. “Image 2019 was just the beginning. If a picture is worth a thousand words, the data underlying that picture has a lot more stories to tell. PRIMO will continue to be an essential tool for extracting such information,” says Medeiros.

Since the release of the original image in 2019, EHT scientists have also released research showing the magnetic fields of black hole M87 and the first image of the supermassive black hole at the center of the Milky Way galaxy. NOIRLab says PRIMO can also be applied to other EHT observations, including those of Sagittarius A*, the Milky Way’s central black hole.

Picture credits: L. Medeiros (Institute for Advanced Study), D. Psaltis (Georgia Tech), T. Lauer (NSF’s NOIRLab), and F. Ozel (Georgia Tech)