Researchers at the University of Warwick have validated over 100 exoplanets, including the discovery of 31 new planets, using a novel artificial intelligence tool. The AI, called RAVEN, analyzed data collected by NASA’s Transiting Exoplanet Survey Satellite (TESS), which identifies potential planets by detecting dips in starlight as planets pass in front of their host stars.
The findings, published in Monthly Notices of the Royal Astronomical Society, demonstrate a significant advancement in the speed and accuracy of exoplanet detection. This technology is crucial as the search for habitable worlds beyond our solar system intensifies, and AI is increasingly playing a role in sifting through vast amounts of astronomical data.
The RAVEN pipeline examined data from more than 2.2 million stars gathered during TESS’s first four years of operation. The team focused on identifying planets with short orbital periods – those completing an orbit in less than 16 days – to refine our understanding of how common these close-in worlds are.
“Using our newly developed RAVEN pipeline, we were able to validate 118 new planets, and over 2,000 high-quality planet candidates, nearly 1,000 of them entirely new,” said Dr. Marina Lafarga Magro, Postdoctoral Researcher at the University of Warwick. “This represents one of the best characterised samples of close in planets and will help us identify the most promising systems for future study.”
Among the validated planets are several noteworthy populations, including ultra-short-period planets (orbiting their stars in under 24 hours), planets found in the “Neptunian desert” – a region where planet formation is theoretically unlikely – and previously unknown multi-planet systems orbiting the same star. The discovery highlights the potential for uncovering diverse planetary systems with the aid of AI-powered analysis of existing astronomical data.
Current planet-hunting missions generate thousands of potential planet candidates, but confirming these signals and determining the prevalence of different planet types remains a significant challenge. RAVEN addresses this challenge by automating and streamlining the validation process, as detailed in this University of Warwick news release.
