An international research team has developed an AI-based algorithm that successfully identified five ultra-short-period planets, all smaller than Earth, from data provided by NASA’s Kepler telescope.
These planets, with orbital periods of less than one day, include four of the closest known to their solar-like stars, and their sizes are comparable to that of Mars.
This marks the first time astronomers have utilized AI to both detect and verify planetary signals in a single step.
Led by Ge Jian from the Shanghai Astronomical Observatory under the Chinese Academy of Sciences, the study was recently published in the Monthly Notices of the Royal Astronomical Society.
The AI algorithm outperformed traditional methods, boosting search speeds by 15 times and improving detection accuracy by 7%.
