A team of researchers from the University of Georgia has developed a fresh method for locating and identifying extrasolar planets. An exoplanet using machine learning, an advancement of artificial intelligence (AI), has been discovered.
A recent study showed that by scanning protoplanetary discs, the gas surrounding young stars, AI can accurately determine the presence of the exoplanet. The recently released results represent a first step in using machine learning to identify previously ignored exoplanets.
Lead author of the study Jason Terry said in a statement, “We confirmed the planet using traditional techniques, but our models directed us to run those simulations and showed us exactly where the planet might be.”
“When we applied our models to a set of older observations, they identified a disk that wasn’t known to have a planet despite having already been analyzed. Like previous discoveries, we ran simulations of the disk and found that a planet could re-create the observation.”
According to Terry, Several images that sharply focused on a specific region of the disc that turned out to contain the traditional indicator of a planet – an enormous change in the velocity of the gas around the planet – indicated the existence of a planet.
“This demonstrates that our models – and machine learning in general – have the ability to quickly and accurately identify important information that people can miss. This has the potential to dramatically speed up analysis and subsequent theoretical insights,” Terry said.