UC Berkeley and the SETI Institute have developed a new machine learning tool that simulates what an extraterrestrial intelligence message received on Earth would look like. This is Setigen, an open source library that, according to the authors, could “change the rules of the game” for future searches for intelligent life beyond our planet.
This artificial intelligence will begin to develop simulations of alien radio signals. The goal is to create different electromagnetic signatures that could be transmitted by a technological civilization trying to communicate with other species, like us humans, throughout the universe.
Since the middle of the 20th century, scientists at the SETI Institute (Search for Extraterrestrial Intelligence) have transmitted radio signals into space to check if there is someone beyond the planetary borders who can answer and communicate through these messages.
The researchers are also looking for technological signatures, such as electromagnetic signals that may be emitted by intelligent civilizations. As no SETI radio signal has been detected so far, experts must make assumptions about its shape in order to develop algorithms to help search for it.
“What Setigen does is facilitate the production of synthetic SETI signals, which can be used on completely synthetic data or aggregated on top of real observational data to provide a more realistic RFI noise floor,” explains Bryan Brzycki, lead author of this research.
“In this way, we can produce large datasets of synthetic signals to analyze the sensitivity of existing algorithms or to serve as the basis for machine learning training.”
Basically, what this innovative tool does is simulate what an extraterrestrial intelligence message might look like, which could be the first step in trying to contact some civilization beyond our planet, as long as they are also willing to make contact. .