Home Science New AI algorithm helps find 8 radio signals from space

New AI algorithm helps find 8 radio signals from space

by News Desk
0 comment

A new artificial intelligence algorithm created by students in Toronto is helping researchers look for signs of life on stars.

Peter Xianyuan Ma, an undergraduate student and researcher at the University of Toronto, said he started working on algorithms in 12th grade during the pandemic.

“I was just looking for a project and was interested in astronomy,” he told CTV News Toronto.

The idea was to help distinguish between technical radio signals created by human technology and signals that could come from other forms of life in the universe.

“What we’re looking for are signs in the technology that indicate whether the sender is intelligent or not. And we continue to find ourselves, unsurprisingly,” Ma explained. We don’t want to see our own noisy signal.”

Using this algorithm, researchers were able to discover eight new radio signals emanating from five different stars about 30 to 90 light-years away from Earth, says Ma.

These signals fade away when researchers look away, largely ruling out interference from Earth-originated signals, Ma said. When they returned to the area, the signal was still there.

“We are all very skeptical and we are scratching our heads,” he said. “We’ve proven that we found what we wanted to find… Now what do we do with all this? That’s another question.”

Steve Croft, project scientist for Breakthrough Listen at the Green Bank Telescope, says finding radio signals in space is like trying to find a needle in a haystack.

“You have to be aware of the haystack itself and not throw away the needle when looking at individual pieces of hay,” Croft, who collaborated on Marr’s research, told CTV News Toronto.

An image from the Green Bank Telescope is shown here. (Credit Breakthrough Listen / Steve Croft)

According to Croft, the algorithms used to discover these signals must consider multiple characteristics. This may indicate whether it is being transmitted from a position in the sky or whether it is being transmitted from a rotating planet or star, such as whether the transmission varies over time.

“The algorithm Peter developed allowed us to do this more efficiently,” he said.

The problem, Croft said, is recognizing that false positives can still exist even though the signal meets this criterion. A possible sign of extraterrestrial life could also be nothing more than a “bizarre-shaped haystack,” he added.

“That’s why we need to see if the signal is still there. And in these particular examples that Peter found in his algorithm, the signal wasn’t there when he repointed the telescope. , I can’t say either way, but is this real?”

Researchers have searched the skies for technologically-generated signals since the 1960s, searching thousands of stars and galaxies for signs of intelligent life. This process is called “SETI” or “Search for Extraterrestrial Intelligence”.

But interference from our own radio signals has always proven to be a challenge.Croft says most technologies have some sort of Bluetooth or wireless wave element that creates static electricity, which can cause a lot of We need to collect data.

“It’s a challenge, but computing provides the solution,” he said.

“So computing, especially machine learning algorithms, allows us to look through this big haystack and look for interesting signal needles.”

Ma said the “technosignal” may not have been found yet, but we shouldn’t give up. The next step is to employ multiple types of search algorithms to find more and more signals to study.

Peter Ma is in this photo taken in 2021. (Adar Kahiri)

Although the “dream” is to find evidence of life, Ma says he’s more focused on the scientific effort to actively look for it.

This sentiment is also echoed by Croft, who said that answering the question of whether humans are alone in this universe is most appealing.

“I don’t go to work every day to find aliens, but I do. You know, I have a certain optimism.”

You may also like

Leave a Comment

Copyright ©️ All rights reserved. | Canadian Trends