There is a question that mankind has been asking for thousands of years: are we alone in the universe? There is no answer to this question yet, but the best way to find out is to detect technosignals that alien civilizations may have developed. Until now, scientists have always struggled to distinguish between potential extraterrestrial signals and those of human origin. Canadian researchers have developed a new artificial intelligence algorithm that they hope will ease the search for aliens, leading them to discover 8 mysterious radio signals.
Experts led by Peter Ma, a student from the University of Toronto in Canada, discovered 8 radio signals after using an artificial intelligence algorithm they developed to look at 820 stars in a space field previously thought to be devoid of of any possible extraterrestrial activity.
These faint signals were overlooked by previous assessments, Ma said. “We need to distinguish between exciting radio signals in space and uninteresting radio signals from Earth,” Ma said, explaining that one reason for this was “too much interference in most observations.” he said.
Together with the SETI Institute, Breakthrough Listen and astronomers from scientific research institutions around the world, Ma has developed a new machine learning algorithm that can better capture potential alien signals from all the background noise on Earth.
This algorithm involved the use of deep learning, a form of machine learning and artificial intelligence that mimics the way humans obtain certain types of information and is a key technology in self-driving cars.
In this case, the researchers essentially took a classic algorithm from a simpler computer and used machine learning to teach them to distinguish between potential alien signals and those of human origin.
When the current algorithm scanned radio data from dozens of stars previously collected by the Robert C. Byrd Green Bank Telescope in West Virginia, it found nothing. But instead of finding anything interesting in that part of space, Ma and his colleagues now discovered eight different radio signals emanating from there.
Steve Croft, who works as a Breakthrough Listen project scientist at the Green Bank Telescope, said in a statement on the subject:
“The most important thing in any technosignature research is to look through these huge stacks of straw signals to find the needle that could be a transmission from an alien world. The vast majority of signals detected by our telescopes come from our own technology: GPS satellites, mobile phones, etc. Peter’s algorithm gives us a more efficient way to filter through the haystack and find signals using the characteristics we expect from techno signals. ”
On the other hand, the researchers said the 8 new signals detected could have come from five of the constellation of 820 stars located 30 to 90 light-years away. The signals have not been proven to be extraterrestrial, but the researchers announced that the technology they developed will open the door to many scientific studies. The research is published in the journal Nature Astronomy.