A new study using machine learning algorithms has picked up 8 extraterrestrial signals that appear to be signs of technology. This exciting discovery, published in the journal Nature Astronomy, raises the possibility of finding proof of intelligent aliens.
Revolutionizing the Search for ETI
With the help of AI, the search for extraterrestrial intelligence (SETI) is expected to be revolutionized. “I’m optimistic that with the help of AI, we’ll be able to better quantify the likelihood of the presence of extraterrestrial signals from other civilizations,” says astronomer Cherry Ng, a co-author of the study.
Semi-Unsupervised Learning
Lead author Peter Ma, an undergraduate at the University of Toronto, created a new technique called “semi-unsupervised learning.” This method combines both supervised and unsupervised machine learning techniques to differentiate between human-made radio signals from Earth and signals from other sources.
Analysis of 150 Terabytes of Data
The researchers analyzed 150 terabytes of data from the Green Bank Telescope in West Virginia, covering observations of 820 stars near Earth. From this data, they discovered 8 previously overlooked signals from 5 stars located between 30 light-years and 90 light-years from Earth.
Two Common Features of ETI Signals
According to Steve Croft, project scientist for Breakthrough Listen, these signals had two features in common with signals that might be created by intelligent aliens. The signals were present when looking at the star and absent when looking away, and they change in frequency over time.
Further Observations Needed
The researchers caution that further observations are needed to determine if these features could arise by chance. A follow-up observation at the Green Bank Telescope did not turn up any signs of the signals.
Machine Learning and Next Generation Telescopes
The research team hopes to apply their algorithm to data from powerful radio telescopes like MeerKAT in South Africa and the planned Next Generation Very Large Array in North America. With this combination, they hope to expand the search for extraterrestrial signals from hundreds of stars to millions.
