PCMag editors select and review products independently. If you buy through affiliate links, we may earn commissions, which help support our testing.

With AI and Radio Telescopes, Scientists Plan to Capture Black Hole Images

An algorithm will compose an image made up of radio waves measured by telescopes around the globe.

 & Tom Brant Managing Editor

Our team tests, rates, and reviews more than 1,500 products each year to help you make better buying decisions and get more from technology.

Our Expert
LOOK INSIDE PC LABS HOW WE TEST
65 EXPERTS
43 YEARS
41,500+ REVIEWS

Harnessing the power of multiple telescopes around the globe, an MIT researcher has come up with an algorithm that may allow scientists to capture the first images of black holes.

To see a black hole from Earth would require a telescope with a 10,000-kilometer diameter. Such a lens is impossible, since it would be roughly the size of Earth itself. So a project called Event Horizon Telescope is working on synchronizing multiple telescopes around the world to approximate the capacity of a single giant one.

That's where MIT graduate student Katie Bouman comes in. Using machine learning and artificial intelligence, she has developed an algorithm that can adjust for fluctuations in atmospheric noise—"galactic dust," as she puts it—in addition to the differing sizes of the telescopes themselves. The result will be a single image that could show a black hole.

The telescopes use radio wavelengths, not the optical lenses of the sort that can be found in amateur astronomers' backyards. That means they're better suited to the task of taking photos of far-off space objects, such as the millions of potential black holes NASA has already identified.

"Radio wavelengths come with a lot of advantages," Bouman said in a blog post. "Just like how radio frequencies will go through walls, they pierce through galactic dust. We would never be able to see into the center of our galaxy in visible wavelengths because there's too much stuff in between."

But radio waves don't make for good pictures: according to MIT, the world's largest single radio-telescope dish has a 1,000-foot diameter, but an image it produced of the moon, for example, would be blurrier than the image seen through an ordinary backyard optical telescope. So Bouman's algorithm will mathematically enhance the radio waves captured by the telescope network to resemble an optical image.

The Event Horizon project currently counts nine telescopes around the world, according to its website, mostly in the US and South America. Three more are expected to join, including one near the South Pole.

About Our Expert

Tom Brant

Tom Brant

Managing Editor

I’m a managing editor at PCMag.com focused on PC hardware. Reading this during the day? Then you've caught me testing gear and editing reviews of Wi-Fi routers, printers, laptops, and tons of other personal tech. (Reading this at night? Then I’m probably dreaming about all those cool products.) I’ve covered the consumer tech world as an editor, reporter, and analyst since 2015.

I've covered most major consumer tech events, including CES, Computex, Google I/O, and IFA. I've also appeared on CBS News, in USA Today, and at many other outlets to offer analysis on breaking technology news.

Before I joined the tech-journalism ranks, I wrote on topics as diverse as Borneo's rainforests, Middle Eastern airlines, and Big Data's role in presidential elections. A graduate of Middlebury College, I also have a master's degree in journalism and French Studies from New York University.

The Technology I Use

While most people buy a phone or laptop and stick with it for years, I’m lucky enough to use devices based on Android, iOS, macOS, and Windows daily as part of my job. As a result, I cycle through lots of tech in addition to my IT-issue work laptop. (Yes, that's a ThinkPad.) Personally, I’ve also owned a lot of tech products both cutting-edge and cringeworthy, from the Nintendo GameCube and the original MacBook to the Palm m105 and the CueCat.

Read full bio