Get all your news in one place.
100's of premium titles.
One app.
Start reading
The Independent UK
The Independent UK
National
Andrew Griffin

AI used to spot dozens of mysterious signals coming from deep in space

The source of ‘fast radio bursts’ remains a mystery but two Harvard academics are not discounting the possibility that they could be message from another galaxy ( Getty )

A pioneering artificial intelligence has been used to spot dozens of mysterious signals coming from deep in space.

The new AI spotted 72 previously undiscovered "fast radio bursts" emanating out of distant galaxies, according to Breakthrough Listen, a program searching for proof of life elsewhere in the universe.

FRBs have long been thought to be one of the mysterious phenomena in the universe. They are intense blasts of radio emissions that can be detected on Earth and then switch off.

Scientists do not know what is causing them, or how they might have come about. And actually spotting them can be incredibly difficult: only a relatively limited number of them have ever been detected.

But scientists have now spotted 72 of the blasts coming from the same place. And they did it using an artificial intelligence that scanned through existing data and found numerous detections that had not yet been found.

The FRBs are coming from the only known source that has sent out repeating messages, with the rest of the blasts only ever being detected once. That makes it an especially interesting source for scientists, who can watch the spot in the hope of learning more about the signals.

The bursts emanating from 121102 are thought to be coming out of a galaxy three billion light years from Earth. But it is still unclear what is actually causing them: suggestions have included everything from highly magnetised neutron stars to messages being created by alien technology.

The AI that found the burst looked through 400 terabytes of previously collected data to discover them. It was trained to look for the characteristics of the blasts and then try and spot them in the dataset, looking through it far more quickly than a human ever could.

“Not all discoveries come from new observations,” remarked Pete Worden, Executive director of the Breakthrough Initiatives which include Listen, “In this case, it was smart, original thinking applied to an existing dataset. It has advanced our knowledge of one of the most tantalizing mysteries in astronomy.”

The new results are published in a paper by Zhang et al that has been accepted for publication in the Astrophysical Journal. A pre-print version of the paper is available online.

Sign up to read this article
Read news from 100's of titles, curated specifically for you.
Already a member? Sign in here
Related Stories
Top stories on inkl right now
One subscription that gives you access to news from hundreds of sites
Already a member? Sign in here
Our Picks
Fourteen days free
Download the app
One app. One membership.
100+ trusted global sources.