A Warwick University team used an AI pipeline called RAVEN to analyze NASA's TESS data and confirm more than 100 exoplanets, including 31 newly identified worlds, from observations of over 2.2 million stars during TESS's first four years.

RAVEN’s analysis validates 118 new planets and identifies over 2,000 high-quality planet candidates, with nearly 1,000 entirely new, creating a well-characterized sample of close-in planets for follow-up studies.

The findings, published in Monthly Notices of the Royal Astronomical Society, are based on data from more than 2.2 million stars over TESS’s first four years, focusing on short-period planets with orbital periods under 16 days.

RAVEN validated 118 new planets and identified over 2,000 high-quality planet candidates, nearly 1,000 of which are entirely new, enabling targeted follow-up studies.

The results demonstrate that AI-driven astronomy can efficiently handle massive datasets, improve the reliability of planet catalogs, and refine population statistics for different planet types.

Complementary analyses quantify that about 9–10% of Sun-like stars host close-in planets, with uncertainties greatly reduced, and Neptunian desert planets occur around roughly 0.08% of Sun-like stars, establishing precise occurrence rates.

The newly identified exoplanets include ultra-short-period planets (orbiting in under 24 hours) and planets in the Neptunian desert, along with tightly packed multi-planet systems around some stars.

The study highlights diverse planet types, noting ultra-short-period planets, planets in the Neptunian desert, and tightly packed multi-planet systems around the same star.

The RAVEN pipeline streamlines detection to statistical validation, enabling consistent, objective analysis of large datasets and robust sampling for studying planet populations around Sun-like stars.

Beyond detections, RAVEN’s broader impact includes enabling reliable, large-scale identification of planetary signals, reducing biases, and improving understanding of how common different planet types are across the galaxy.

The study released interactive catalogs and tools so other scientists can explore results and identify targets for follow-up observations with ground-based telescopes and future missions like ESA's PLATO.

TESS is now rivaling or surpassing Kepler for studying planetary populations, especially close-in planets, aided by the interactive catalogs and follow-up planning tools.