Super-Speed AI Helps Astronomers Find Cosmic Trove Of New Exoplanets

American astronomers led by Joshua Roth at Princeton University have discovered over 10,000 new exoplanet candidates using advanced AI tools, marking the largest cache of planet candidates ever found. The team analyzed 80 million light curves from NASA's TESS satellite, employing AI software like the Cambridge Exoplanet Transit Recovery Algorithm and a Random Forest machine learning system. The findings, published in a paper titled 'The T16 Planet Hunt: 10,000 New Planet Candidates from TESS Cycle 1,' include over 9,000 gas giants (Hot Jupiters), more than 100 Neptune-size bodies, and 11 potential super-Earths. The collaboration spans Princeton, MIT, UCLA, and Las Campanas Observatory in Chile, and represents a global lead in AI-assisted exoplanet discovery.