Chinese Scientists Discover Ultra-Short Period Planets Using Artificial Intelligence

Recently, an international team led by Professor Ge Jian from the Shanghai Astronomical Observatory of the Chinese Academy of Sciences has developed an innovative deep learning algorithm. This algorithm successfully identified five exoplanets, each smaller than Earth and exhibiting orbital periods of less than one day, in the stellar photometric data released by the Kepler satellite in 2017. Notably, four of these planets are the smallest and closest to their host stars ever discovered, resembling the size of Mars.

This marks the first time astronomers have employed artificial intelligence to simultaneously search for potential signals and confirm genuine signals in a single pass. The findings were published in the Monthly Notices of the Royal Astronomical Society (MNRAS). After five years of dedicated research, the team created a new algorithm that integrates GPU phase folding and convolutional neural networks, known as GPFC. This new method is approximately 15 times faster than the widely used BLS method, while improving detection accuracy and completeness by around 7%. The algorithm has proven successful in analyzing Kepler's datasets, identifying five new ultra-short-period exoplanets and showcasing its capabilities in detecting faint transit signals.

The existence of these ultra-short-period planets provides crucial insights into the early evolution of planetary systems, planetary interactions, and the dynamics of star-planet relationships, including tidal forces and atmospheric erosion. This research offers a new approach for efficiently and rapidly searching for transit signals in high-precision photometric data. It also highlights the vast potential of artificial intelligence in sifting through extensive astronomical datasets to uncover subtle signals.

The recently discovered exoplanets, comparable in size to Mars, experience extremely high surface temperatures due to their proximity to their host stars, resulting in significant volcanic activity driven by intense tidal forces affecting their internal structures.