The existence of aliens has always intrigued us and for decades, humans have done a lot of research on the subject. And in such an effort, artificial intelligence (AI) is being used to find out if an alien really exists. The study is known as the search for extraterrestrial intelligence, known as SETI, where AI is trying to locate electromagnetic radiation signals coming from a technologically advanced civilization in a distant solar system. Telescopes have apparently been set up from the hills of West Virginia to the plains of rural Australia in an attempt to listen for such signals.
“It’s a new era for SETI research that is ushered in by machine learning technology,” says Franck Marchis, a planetary astronomer at the SETI Institute in Mountain View, California, as reported in the scientific journal Nature.
However, the biggest problem facing research at the moment is that big data is relatively new to SETI. Therefore, these searches return a large amount of data, including false positives caused by terrestrial interference from mobile phones, GPS, and other aspects of modern life.
“The biggest challenge for us in looking for SETI signals right now is not getting the data,” says Sofia Sheikh, an astronomer at the SETI Institute. “The hard part is differentiating signals from human or terrestrial technology from the type of signals that we would be looking for technology somewhere else in the Galaxy.”
An alternative to this is the use of algorithms that look for signals that match what astronomers think might be alien beacons. And the way to do it is Machine Learning (ML).
Machine learning algorithms are trained on large amounts of data and can learn to recognize features that are characteristic of terrestrial interference, making them very good at filtering out noise. “Machine learning is also good at detecting candidate extraterrestrial signals that don’t fall into the conventional categories and therefore might have been missed by previous methods,” Dan Werthimer, a SETI scientist at the University of California, told Nature. , Berkeley.
“We can’t always be anticipating what ET might send us,” Peter Ma, a mathematician and physicist at the University of Toronto, Canada, and lead author of today’s paper, agrees with Werthimer.