University of Warwick researchers confirm 118 new exoplanets using AI system RAVEN applied to NASA TESS data

Astronomers at the University of Warwick validated 118 new planets and over 2,000 high-quality planet candidates using the RAVEN pipeline, analyzing observations from more than 2.2 million stars gathered during TESS's first four years. The newly confirmed planets include ultra-short-period worlds orbiting in under 24 hours and rare 'Neptunian desert' planets.

RAVEN is an automated system that combines machine learning trained on realistic simulations to filter out false signals—such as eclipsing binary stars or instrument noise—and statistically confirms planet candidates. The pipeline handles the entire workflow in one process: detecting signals, vetting them with machine learning, and statistically validating them.

The validated dataset enabled researchers to measure how common close-in planets are around Sun-like stars with reduced uncertainties by up to a factor of ten compared to earlier findings. Results show that about 9–10% of Sun-like stars host a close-in planet, and 'Neptunian desert' planets appear around just 0.08% of Sun-like stars. Findings were published in MNRAS.