Space is throwing up a lot of maybes. A new AI system from the University of Warwick is helping astronomers sort out which ones are actually planets.
Researchers said they confirmed more than 100 exoplanets, including 31 newly identified worlds, using a tool called RAVEN and data from NASA’s Transiting Exoplanet Survey Satellite, or TESS. The findings, published in MNRAS, come from analysis of observations from more than 2.2 million stars gathered during TESS’s first four years.
The team focused on planets that orbit very close to their stars and complete an orbit in less than 16 days. They said the work has produced one of the most precise measurements yet of how common these short-period planets 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 first author Dr. Marina Lafarga Magro, postdoctoral researcher at the University of Warwick.
“This represents one of the best characterized samples of close in planets and will help us identify the most promising systems for future study.”
Among the newly confirmed planets are ultra-short-period planets that circle their stars in under 24 hours. Others sit in the “Neptunian desert”, a region where few planets are expected to exist based on current theories. The study also found tightly packed multi-planet systems, including previously unknown pairs of planets orbiting the same star.
The researchers said modern planet-hunting missions can flag thousands of possible planets, but checking which signals are genuine is still difficult because false signals can mimic planets, including eclipsing binary stars.
“The challenge lies in identifying if the dimming is indeed caused by a planet in orbit around the star or by something else, like eclipsing binary stars, which is what RAVEN tries to answer. Its strength stems from our carefully created dataset of hundreds of thousands of realistically simulated planets and other astrophysical events that can masquerade as planets. We trained machine learning models to identify patterns in the data that can tell us the type of event we have detected, something that AI models excel at,” said Warwick’s Dr. Andreas Hadjigeorghiou, who led development of the pipeline.
“In addition, RAVEN is designed to handle the whole process in one go, from detecting the signal, to vetting it with machine learning and statistically validating it. This gives the pipeline an additional edge over contemporary tools that only focus on specific parts of the workflow.”
Dr. David Armstrong, associate professor at Warwick and senior co-author on the RAVEN studies, said: “RAVEN allows us to analyse enormous datasets consistently and objectively. Because the pipeline is well-tested and carefully validated, this is not just a list of potential planets. it is also reliable enough use as a sample to map the prevalence of distinct types of planets around Sun-like stars.”
In a companion MNRAS study, the team measured how often close-in planets occur around Sun-like stars, mapping results by orbital period and planet size. They found about 9 to 10 percent of Sun-like stars host a close-in planet.
The researchers said that aligns with earlier findings from NASA’s Kepler mission, but the new analysis reduces uncertainties by up to a factor of ten. They also said they made the first direct measurement of how rare “Neptunian desert” planets are, finding they appear around just 0.08 percent of Sun-like stars.
“For the first time, we can put a precise number on just how empty this ‘desert’ is,” said Dr. Kaiming Cui, postdoctoral researcher at Warwick and first author of the population study.
“These measurements show that TESS can now match, and in some cases surpass, Kepler for studying planetary populations.”
Read more from Science Daily.
