By continuing to browse our site you agree to our use of cookies, revised Privacy Policy and Terms of Use. You can change your cookie settings through your browser.
I agree
Search Trends
SITEMAP
Copyright © 2024 CGTN. 京ICP备20000184号
Disinformation report hotline: 010-85061466
SITEMAP
Copyright © 2024 CGTN. 京ICP备20000184号
Disinformation report hotline: 010-85061466
An illustration of an exoplanet and its host star. /China Media Group
An international research team has crafted a sophisticated deep learning algorithm that integrates Graphics Processing Unit (GPU) phase folding with neural networks. Employing this innovative technique, the researchers identified five ultra-short period planets, each with a diameter inferior to Earth's and an orbital period shorter than 24 hours. The algorithm used data obtained from the Kepler space telescope's 2017 release.
Among these newfound celestial bodies, four are the tiniest exoplanets, positioned at the nearest proximity to their respective host stars, with dimensions akin to Mars.
This achievement signifies the inaugural utilization of AI by astronomers for the dual task of searching for candidate signals and identifying genuine ones. The results of this study have been published in the astronomy journal, Monthly Notices of the Royal Astronomical Society (MNRAS).
The research initiative is led by Professor Ge Jian of the Shanghai Astronomical Observatory, Chinese Academy of Sciences.