An international team of researchers, led by Professor Ge Jian from the Shanghai Astronomical Observatory at the Chinese Academy of Sciences, has made a groundbreaking discovery using artificial intelligence.
They developed a sophisticated deep learning algorithm that combines Graphics Processing Unit (GPU) phase folding with neural networks. This innovative approach allowed them to analyze data from the Kepler space telescope’s 2017 release efficiently.
Employing this cutting-edge technique, the team identified five ultra-short period exoplanets, each smaller than Earth and orbiting their host stars in less than 24 hours. Remarkably, four of these newfound celestial bodies are the tiniest exoplanets ever discovered, with dimensions similar to Mars and located extremely close to their stars.
This achievement marks the first time astronomers have used AI for both searching candidate signals and confirming genuine exoplanets, demonstrating the potential of machine learning in advancing astronomical research.
The findings of this study have been published in the Monthly Notices of the Royal Astronomical Society (MNRAS), highlighting the significance of the team’s contribution to the field of exoplanet discovery.
By leveraging AI and deep learning, this research not only accelerates the discovery of distant worlds but also opens new avenues for exploring the universe, bringing us one step closer to understanding the cosmos.
Reference(s):
cgtn.com
