Artificial Intelligence joins search for extraterrestrial intelligence: Breakthrough Listen

BENGALURU: Breakthrough Listening – the initiative to find “techno-signatures” or signs of intelligent life in the universe – on Monday announced the results of a new method of searching for data powered by artificial intelligence.
In a paper published in the journal Nature Astronomy, the team analyzes 480 hours of data from the Green Bank Telescope (GBT) in West Virginia, and reports eight previously undetected signals of interest that have certain characteristics expected of genuine technoscope.
The research, led by University of Toronto undergraduate student Peter Ma, who began working with the Breakthrough Listening team while still in high school, identified about 3 million signals in scans of 820 stars observed with GBT.
“The key issue with any techno-signature search is sifting through this huge haystack of signals to find the needle that could be a transmission from an alien world,” Steve Croft, an astrophysicist from the Breakthrough Listen team told the University of California, explained. Berkeley (and one of Mom’s research advisors).
Croft added: “The vast majority of the signals detected by our telescopes come from our own technology – GPS satellites, mobile phones and the like. Peter’s algorithm gives us a more effective way to filter the hay and find signals that have the properties we expect from techno signatures.”
Classic techno-signature algorithms compare scans where the telescope is pointed at a target point on the sky with scans where the telescope is moving to a nearby position to identify signals that might only come from that particular point, Breakthrough added.
These techniques, it said, are highly effective. For example, they can successfully identify the Voyager-1 spacecraft, at a distance of 20 billion kilometers, in observations with the GBT. But these algorithms struggle in crowded regions of the radio spectrum, where the challenge is akin to listening to a whisper in a crowded room.
“The process developed by Ma embeds simulated signals into real data, and instructs an artificial intelligence algorithm known as an autoencoder to learn their fundamental properties. The output of 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,” Breakthrough said.
Andrew Siemion, Breakthrough Listen’s principal investigator, said that in 2021 their classical algorithms uncovered a signal of interest, designated BLC1, in data from the Parkes telescope and that Peter’s algorithm was even more effective at finding signals like this.
“However, any techno-signature candidate needs to be confirmed, and when we looked at these targets again with the GBT, the signals did not reappear. But by applying this new technique to even larger datasets, we can more effectively identify techno-signature candidates, and hopefully eventually even a confirmed techno-signature,” Siemion added.
S Pete Worden, Executive Director of Breakthrough Initiatives, said it was exciting to see new approaches being developed by imaginative young people at the start of their scientific careers.
“We will continue to monitor the stars that Peter observed, and we will continue to develop our use of artificial intelligence to help us answer humanity’s deepest question: are we alone?” Were said.
Cherry Ng, another of Ma’s research advisors at the University of Toronto and now an astronomer at the French National Center for Scientific Research, said 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.
“… Application of these techniques at scale will be transformative for radiotechno signature science,” Ng added.
Breakthrough said that larger data sets are imminent, adding that it recently announced the start of observations with the MeerKAT telescope in South Africa.
“There is such a large volume of data. The more traditional ways of looking for extraterrestrial life just aren’t enough,” explains Ma.