Summary
University of Warwick researchers developed RAVEN, an AI pipeline that analyzed tess observations of over 2.2 million stars from the spacecraft’s first four years, focusing on close-in planets with orbital periods under 16 days. The system confirmed over 100 new exoplanets and identified ~2,000 additional candidates — roughly half previously undetected — which, if confirmed, would represent a major expansion of nasa’s ~6,000-entry exoplanet catalog. RAVEN handles the full detection-to-validation workflow (signal detection, machine-learning vetting, statistical validation). The results also quantified the Neptunian desert, finding close-in Neptune-sized worlds occur around only 0.08% of sun-like stars, and showed that ~10% of sun-like stars host a close-in planet — validating earlier Kepler findings.
Key Claims
- RAVEN confirmed 100+ new exoplanets hidden in four years of TESS data (attributed to the University of Warwick team)
- ~2,000 additional exoplanet candidates identified, ~half previously undetected (team)
- ~10% of sun-like stars host a close-in planet, consistent with Kepler results (team)
- Close-in Neptune-sized worlds occur around just 0.08% of sun-like stars, putting a “precise number” on the Neptunian desert (Kaiming Cui)
- TESS can now match and in some cases surpass Kepler for studying planetary populations (Cui)
Notable Quotes
“This represents one of the best characterized samples of close-in planets and will help us identify the most promising systems for future study.” — Marina Lafarga Magro, University of Warwick
“Because the pipeline is well-tested and carefully validated, this is not just a list of potential planets — it is also reliable enough to use as a sample to map the prevalence of distinct types of planets around sun-like stars.” — David Armstrong, University of Warwick