AI Algorithm Inspired by Galaxy Mergers Discovers Exoplanets

An international research team has developed a revolutionary AI algorithm that discovers exoplanets, some smaller than Earth, with orbital periods shorter than a day. The algorithm, inspired by torque balance in galaxy mergers, was reported by the Xinhua News Agency. The newly discovered exoplanets are among the closest to their stars. Their sizes are comparable to Mars, making them interesting for study. This marks the first successful use of AI in analyzing astronomical data to find new celestial bodies. The findings were published in the Monthly Notices of the Royal Astronomical Society by a team led by Dr. Jie Yang from the Shanghai Astronomical Observatory of the Chinese Academy of Sciences. The probability of discovering planets with exceptionally close orbital periods is notably low, around 0.5% similar to the Sun. Since 2011, 145 such planets have been identified, with about 30 having diameters smaller than Earth's. These discoveries expand knowledge of the formation and evolution of rare exoplanets. Astronomers traditionally use the transit method to detect exoplanets. This method relies on detecting periodic dimming of a star's brightness as a planet passes in front of it. While effective, detecting small planets with ultra-short orbital periods can be challenging. This development demonstrates the significance of AI in science and opens new possibilities for discovering unknown celestial bodies. The discovery highlights the potential of AI technologies in space exploration.