Artificial Intelligence Detects New Technosignature Signals of Interest

In a new paper published in the journal Nature Astronomy, astronomers with Breakthrough Listen Initiative — the largest ever scientific research program aimed at finding evidence of alien civilizations — present a new machine learning-based method that they apply to more than 480 hours of data from the Robert C. Byrd Green Bank Telescope, observing 820 nearby stars. The method analyzed 115 million snippets of data, from which it identified around 3 million signals of interest. The authors then inspected the 20,515 signals and they identified 8 previously undetected signals of interest, although follow-up observations of these targets have not re-detected them.

“The key issue with any technosignature search is looking through this huge haystack of signals to find the needle that might be a transmission from an alien world,” said Dr. Steve Croft, an astrophysicist at the University of California, Berkeley and a member of the Breakthrough Listen team.

“The vast majority of the signals detected by our telescopes originate from our own technology — GPS satellites, mobile phones, and the like.”

“Our algorithm gives us a more effective way to filter the haystack and find signals that have the characteristics we expect from technosignatures.”

Classical technosignature algorithms compare scans where the telescope is pointed at a target point on the sky with scans where the telescope moves to a nearby position, in order to identify signals that may be coming from only that specific point.

These techniques are highly effective. For example, they can successfully identify the Voyager 1 space probe, at a distance of 20 billion km, in observations with the Green Bank Telescope.

But these algorithms struggle in crowded regions of the radio spectrum, where the challenge is akin to listening for a whisper in a crowded room.

The process developed by the team inserts simulated signals into real data, and trains an artificial intelligence algorithm known as an autoencoder to learn their fundamental properties.

The output from this process is fed into a second algorithm known as a random forest classifier, which learns to distinguish the candidate signals from the noisy background.

“In 2021, our classical algorithms uncovered a signal of interest, denoted BLC1, in data from the Parkes telescope,” said Breakthrough Listen’s principal investigator Dr. Andrew Siemion, an astronomer at the University of California, Berkeley.

“The new algorithm is even more effective in finding signals like this.”

“Any technosignature candidate needs to be confirmed, however, and when we looked at these targets again with the Green Bank Telescope, the signals did not reappear.”

“But by applying this new technique to even larger datasets, we can more effectively identify technosignature candidates, and hopefully eventually even a confirmed technosignature.”

“These results dramatically illustrate the power of applying modern machine learning and computer vision methods to data challenges in astronomy, resulting in both new detections and higher performance,” said Dr. Cherry Ng, an astronomer at the French National Center for Scientific Research.

“Application of these techniques at scale will be transformational for radio technosignature science.”

_____

P.X. Ma et al. A deep-learning search for technosignatures from 820 nearby stars. Nat Astron, published online January 30, 2023; doi: 10.1038/s41550-022-01872-z