Using artificial intelligence technologies, a study team from the University of Georgia has discovered evidence of a previously undiscovered planet outside of our solar system.
In recent research, the team demonstrated that by scanning protoplanetary discs, the gas around freshly formed stars, machine learning can accurately predict the presence of an exoplanet.
The recently released discoveries are a first step in applying machine learning to detect exoplanets that had previously gone unnoticed.
Jason Terry, a doctoral student in the UGA Franklin College of Arts and Sciences Department of Physics and Astronomy and the study’s lead author, said, “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.”
The study demonstrates how artificial intelligence may be used as a tool to extend researchers’ accuracy and more effectively use their time while engaged in such a large-scale project as investigating deep space.
The models were able to find a signal in data that had already been studied; they discovered something that had gone unnoticed before.