Astronomers discover 8 alien signals coming from nearby stars

Are we alone in the universe?

Scientists may have just moved us closer to answering this question. The team – led by researchers from the University of Toronto – has streamlined the search for extraterrestrial life by using a new algorithm to organize the data from their telescopes into categories, in order to distinguish between real signals and interference. This has allowed them to quickly sort through the information and find patterns, through an artificial intelligence process known as machine learning.

They discovered eight extraterrestrial signals that seem to have the hallmarks of technology. The study, published in the journal Nature Astronomy, doesn't claim to have found evidence of intelligent aliens, but the researchers believe that using artificial intelligence is a promising way to search for extraterrestrial intelligence.

"I am impressed by how well this approach has performed on the search for extraterrestrial intelligence," study co-author Cherry Ng, an astronomer at the University of Toronto, said in a statement. "With the help of artificial intelligence, I'm optimistic that we'll be able to better quantify the likelihood of the presence of extraterrestrial signals from other civilizations."

The search for extraterrestrial intelligence, or SETI, has been ongoing since the 1960s and is focused on finding evidence of technologically-generated signals, known as technosignatures, from advanced extraterrestrial civilizations.

Astronomers have been using powerful radio telescopes to scan thousands of stars and hundreds of galaxies in the hopes of discovering these technosignatures. It is assumed that an advanced extraterrestrial civilization would possess the sophistication to emit such signals.

Despite being located in areas with minimal interference from technology, the search for extraterrestrial intelligence (SETI) still faces major challenges due to human disturbance. Peter Ma, an undergraduate student and researcher at the University of Toronto, explains that "in many of our observations, there is a lot of interference."

To differentiate extraterrestrial signals from human-generated interference, the team trained their machine-learning tools through simulations of both types of signals. They tested a variety of algorithms, evaluated their accuracy and false-positive rates, and ultimately chose a powerful algorithm created by Ma.

The new technique uses a method called "semi-unsupervised learning," which combines supervised and unsupervised learning. The algorithm was first trained to differentiate between human-made radio signals originating from Earth and signals from elsewhere.

The researchers analyzed 150 terabytes of data from the Green Bank Telescope in West Virginia, covering observations of 820 stars near Earth, and discovered eight previously overlooked signals from five stars located between 30 and 90 light-years from Earth.

Ma's algorithm, referred to as "semi-unsupervised learning," is a combination of two subtypes of machine learning, supervised and unsupervised learning. It utilizes the strengths of both techniques to improve the accuracy of the algorithm.

In this approach, supervised learning is used to guide and train the algorithm, while unsupervised learning is used to uncover hidden patterns in the data. This combination allows the algorithm to generalize the information it has learned and to more easily detect new patterns in the data, leading to better results in the search for extraterrestrial signals.

Ma's innovative idea to apply semi-unsupervised learning to SETI started as a high school project. “I only told my team after the paper’s publication that this all started as a high-school project that wasn’t really appreciated by my teachers.”

Dr. Ng, says new ideas are very important in a field like SETI. “By poking the data with every technique, we might be able to discover exciting signals.”

Scientists from the Breakthrough Listen SETI effort say these signals had two features in common with signals that might be created by intelligent aliens: they are present when looking at the star and absent when looking away, and they change in frequency over time in a way that makes them appear far from the telescope. However, these features could arise by chance and further observations are necessary to make any claims about extraterrestrial life.

"First, they are present when we look at the star and absent when we look away — as opposed to local interference, which is generally always present," Steve Croft(opens in new tab), project scientist for Breakthrough Listen at the Green Bank Telescope, said in the statement. "Second, the signals change in frequency over time in a way that makes them appear far from the telescope."

The research team hopes to apply their algorithm to data from more powerful radio telescopes, such as MeerKAT in South Africa or the planned Next Generation Very Large Array. They believe that this new technique, combined with the next generation of telescopes, will allow them to search millions of stars instead of just hundreds.

"With our new technique, combined with the next generation of telescopes, we hope that machine learning can take us from searching hundreds of stars to searching millions," Ma said.

Despite the initial results not leading to the discovery of extraterrestrial life, the use of machine learning in the search for extraterrestrial intelligence holds great promise. The authors of the study are optimistic that artificial intelligence will help them better quantify the likelihood of the presence of extraterrestrial signals from other civilizations.

Note: Materials provided above by The Brighter Side of News. Content may be edited for style and length.

Like these kind of feel good stories? Get The Brighter Side of News' newsletter.