8 Potential Technosignatures Found Beyond Our Solar System Thanks to Machine Learning
With the aid of machine learning, 8 potential technosignatures have been found around five nearby stars. Technosignatures for those who are familiar, are technologically-generated signals that could identify advanced extraterrestrial civilizations. The campaign to find these signals comes from Breakthrough Listen, a privately funded initiative, which may have spotted evidence of extraterrestrial civilizations. In a statement, Peter Ma, an undergraduate student at the University of Toronto Canada said, “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.”
Researchers analyzed over 150 terabytes of data which represented the observations of 820 nearby stars. The team found the new algorithm excelled by organizing the data from telescopes into categories. This allowed them to make distinctions between what is called “noise” or interference that can be ignored and real signals. To ensure that the new algorithm wasn’t being fooled by Earth-originating noise and data, the team trained their machine learning tools to tell the difference between human-created interference, and potential signals originating from outside of Earth. Ma said of the process, “In many of our observations, there is a lot of interference,…We need to distinguish the exciting radio signals in space from the uninteresting radio signals from Earth.”
To do this, they first tested the range of algorithms to determine both precision and how often they provided false positives. What worked best was an algorithm that combined two sub-fields of machine learning, supervised learning, and unsupervised learning. which together can go through large datasets in search of hidden patterns. And it was using this new algorithm that 8 signals were discovered that originated from five different star systems.
Each star is located between 30 and 90 light-years away from Earth. Though these are very vast distances from what we’re used to on our planet, in galactic terms, it’s within the same neighborhood. The project itself is searching 1 million nearby stars, as well as the “Local Group“, which is our local group of galaxies, and the Milky Way’s plane for evidence and signs of alien life. But what exactly separates these signals from others to be classified as potentially being technosignatures? Project scientist for Breakthrough Listen, Steve Croft explains, “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.”
He goes on to say, “Second, the signals change in frequency over time in a way that makes them appear far from the telescope.” With these results, the team is optimistic that with the help of AI, life outside of our planet can be found. Cherry Ng, a co-author on the research and an astronomer also at the University of Toronto, said, “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.”
Finally in a second statement through SETI, Ma announced the expansion of the program to search for a million stars using the MeerKat telescope. “We’re scaling this search effort to 1 million stars today with the MeerKAT telescope and beyond…We believe that work like this will help accelerate the rate we’re able to make discoveries in our grand effort to answer the question, ‘Are we alone in the universe?’”
Originally posted on OpenDataScience.com
Read more data science articles on OpenDataScience.com, including tutorials and guides from beginner to advanced levels! Subscribe to our weekly newsletter here and receive the latest news every Thursday. You can also get data science training on-demand wherever you are with our Ai+ Training platform. Subscribe to our fast-growing Medium Publication too, the ODSC Journal, and inquire about becoming a writer.
