Somewhere out there — quite a lot of somewheres, in fact — more than a hundred new worlds have just stepped out of the shadows.
Astronomers at the University of Warwick have validated over 100 previously hidden exoplanets buried in data from NASA's Transiting Exoplanet Survey Satellite (TESS), thanks to a new artificial intelligence tool that can spot the faint fingerprints of distant planets where humans struggle to look.
The system is called RAVEN — RAnking and Validation of ExoplaNets — and it has been let loose on observations of more than 2.2 million stars gathered during the first four years of the TESS mission. The results, published in the Monthly Notices of the Royal Astronomical Society, are nothing short of staggering.
A bumper haul
"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, the postdoctoral researcher at Warwick who led the validation study.
"This represents one of the best characterised samples of close-in planets and will help us identify the most promising systems for future study."
In other words: a single AI tool, run over a NASA dataset, has roughly doubled what we know about a particular slice of the galaxy.
How RAVEN sees what we can't
TESS hunts for planets the same way an eagle-eyed neighbour spots someone walking past a window — by watching for tiny dips in a star's brightness as an orbiting world passes in front of it. The trouble is, plenty of other things in space can mimic that flicker, particularly pairs of stars eclipsing one another.
RAVEN was trained on hundreds of thousands of realistically simulated planets and impostor signals, learning to tell the genuine articles from the fakes.
"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," explained Dr Andreas Hadjigeorghiou, who led the pipeline's development.
Crucially, RAVEN does the lot in one go — detection, vetting, and statistical validation — where existing tools tend to handle just one stage of the process.
Strange new worlds
It is the kind of haul that astronomers will be picking through for years. Among the newly confirmed planets are several extreme and rare types:
- Ultra-short-period planets that whip around their stars in less than 24 hours.
- "Neptunian desert" planets — Neptune-sized worlds found in a region so close to their stars that such planets were thought to barely survive there.
- Tightly packed multi-planet systems, including newly spotted pairs orbiting the same star at close range.
The Neptunian desert had been a long-running puzzle. Intense radiation from a host star is thought to strip the atmospheres from gas planets that wander too close. Now, for the first time, the rarity has a number on it.
"For the first time, we can put a precise number on just how empty this 'desert' is," said Dr Kaiming Cui, who led a companion study on planetary populations. The answer: such worlds occur around just 0.08 per cent of Sun-like stars.
A foundation for what comes next
The team also pinned down how often close-in planets show up around Sun-like stars more generally — about 9 to 10 per cent — matching results from NASA's earlier Kepler mission but with uncertainties up to ten times smaller.
Dr David Armstrong, associate professor at Warwick and senior co-author, said the well-validated catalogue is more than a tally of trophies.
"RAVEN allows us to analyse enormous datasets consistently and objectively," he said. "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."
The team has released interactive catalogues for other researchers to explore, with the European Space Agency's upcoming PLATO mission expected to follow up on the most promising targets.
A hundred new worlds, found not by a bigger telescope but by a smarter way of looking. Not bad for a Tuesday.



