SPACE/COSMOS
AI approach uncovers dozens of hidden planets in NASA’s TESS data
University of Warwick
image:
This is an artist's impression of a unique type of exoplanet discovered with the Hubble Space Telescope. The planet is so close it to its star that it completes an orbit in 10.5 hours. The planet is only 750,000 miles from the star, or 1/130th the distance between Earth and the Sun.
The Jupiter-sized planet orbits an unnamed red dwarf star that lies in the direction of the galactic center; the exact stellar distance is unknown. Hubble detected the planet in a survey that identified 16 Jupiter-sized planets in short-period, edge-on orbits (as viewed from Earth) that pass in front of their parent stars. Hubble could not see the planets, but measured the dimming of starlight as the planets passed in front of their stars.
This illustration presents a purely speculative view of what such a "hot Jupiter" might look like. It could have a powerful magnetic field that traps charged particles from the star. These particles create glowing auroral rings around the planet's magnetic poles. A powerful magnetic flux tube links the planet and star. This enhances stellar activity and triggers powerful flares. A powerful stellar wind creates a bowshock around the planet. The planet's atmosphere seethes at 3,000 degrees Fahrenheit.
Credit: NASA, ESA, and A. Schaller (for STScI) - https://science.nasa.gov/asset/hubble/artists-impression-of-an-ultra-short-period-planet/ - This file is licensed under the Creative Commons Attribution 4.0 International license.
view moreCredit: NASA, ESA, and A. Schaller (for STScI)
Astronomers at the University of Warwick have validated over 100 exoplanets, including 31 newly detected planets, using a new artificial intelligence tool applied to data from NASA’s Transiting Exoplanet Survey Satellite (TESS), a space mission that monitors the sky for the subtle dimming of starlight caused when planets pass in front of their host stars.
Published in MNRAS, the team applied their newly developed AI pipeline called RAVEN to observations of over 2.2 million stars collected during TESS’s first four years of operations. They focused on finding planets that orbit close to their stars, completing an orbit in less than 16 days, providing the most accurate assessment of how common these short-period 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 first author 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 newly validated planets are several especially valuable populations, including:
Ultra-short-period planets, orbiting their stars in less than 24 hours
‘Neptunian desert’ planets, a rare class found in a region where theory predicts planets should be scarce
Close orbiting multi-planet systems, including previously unknown planetary pairs around the same star
RAVEN’s edge
Modern planet-hunting missions routinely identify thousands of possible planets (candidates), but confirming which signals are real, and understanding how common different types of planets are, remains a major challenge with the current methods.
"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 the 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, added: “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.”
Planetary Prevalences
With this well-characterised set of validated planets, the team was able to move beyond individual discoveries and study the population of close-in exoplanets in detail. In a companion MNRAS study, they measured how frequently close orbiting planets occur around Sun-like stars; mapping results across orbital period and planet size with unprecedented detail.
They found that around 9–10% of Sun-like stars host a close-in planet, which was consistent with NASA’s Kepler mission - a space telescope that previously measured how common planets are around other stars, but RAVEN had uncertainties up to ten times smaller.
The study also provides the first direct measurement of ‘Neptunian desert’ planets, showing they occur around just 0.08% 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.”
A foundation for future discoveries
Together, these studies demonstrate how large astronomical data and new AI developments go hand in hand, generating new discoveries while stress-testing AI on difficult research problems as well as transforming both planet discovery and planetary population science.
The team has also released interactive tools and catalogues, allowing other researchers to explore the results and identify promising targets for future observations with ground-based telescopes and upcoming missions such as ESA’s PLATO.
ENDS
Notes to Editors
This research was supported by UKRI funding under the Horizons Frontier research guarantee program – INNATE. reference EP/X027562/1
The three RAVEN papers are:
Automatic search for transiting planets in TESS-SPOC FFIs with RAVEN: Over 100 newly validated planets and over 2000 vetted candidates DOI: 10.1093/mnras/stag512
Demographics of Close-In TESS Exoplanets Orbiting FGK Main-sequence Stars, MNRAS (2026) DOI: 10.1093/mnras/stag022
RAVEN: RAnking and Validation of ExoplaNets. https://arxiv.org/abs/2509.17645
RAVEN explainer
RAVEN is an automated planet vetting and validation framework designed to solve one of the biggest bottlenecks in modern astronomy: turning vast volumes of space telescope data into reliable discoveries. It scans observations/data from millions of stars for the tiny dips in brightness caused by planets passing in front of their host stars, uses artificial intelligence models trained on realistic simulations to reject false positives such as binary stars and instrumental noise, and then statistically validates the strongest signals. Crucially, it also measures which types of planets are easiest, and hardest, to detect and correctly classify, allowing scientists to correct for hidden biases. This means RAVEN does not just validate new worlds faster; it produces cleaner datasets that can be used to answer bigger questions about how common distinct types of planets really are.
About the University of Warwick
Founded in 1965, the University of Warwick is a world-leading institution known for its commitment to era-defining innovation across research and education. A connected ecosystem of staff, students and alumni, the University fosters transformative learning, interdisciplinary collaboration, and bold industry partnerships across state-of-the-art facilities in the UK and global satellite hubs. Here, spirited thinkers push boundaries, experiment, and challenge convention to create a better world.
An exampler of a multi-planet close orbiting system - the Kepler-11 System
Kepler-11 is a sun-like star around which six planets orbit. At times, two or more planets pass in front of the star at once, as shown in this artist’s conception of a simultaneous transit of three planets observed by NASA’s Kepler spacecraft on Aug. 26, 2010.
Image credit: NASA/Tim Pyle - https://www.nasa.gov/image-article/kepler-11-system/ - This file is licensed under the Creative Commons Attribution 4.0 International license.
Credit
NASA/Tim Pyle
Journal
Monthly Notices of the Royal Astronomical Society
Method of Research
Experimental study
Subject of Research
Not applicable
Article Title
Automatic search for transiting planets in TESS-SPOC FFIs with RAVEN: Over 100 newly validated planets and over 2000 vetted candidates
Article Publication Date
24-Mar-2026
Study: New explanation for unique ‘negative superhump’ features of deep-space binary star systems
UNLV-led team of astrophysicists resolves decades-old conundrum with new theory on mechanisms driving periodic brightness variations in cataclysmic variable star systems.
University of Nevada, Las Vegas
LAS VEGAS – March 23, 2026 – New UNLV-led research is helping to unravel clues to a cosmic mystery that has eluded scientists for decades.
Cataclysmic variables (CVs) are binary star systems in which primary stars – incredibly dense and compact white dwarfs – accumulate material from nearby companion stars. The material spirals in towards the white dwarf through what is known as an accretion disk. These deep space systems are responsible for a number of cosmic phenomena, including sudden bursts of light known as classical novae that temporarily appear to resemble new stars before fading away over time.
Modern astronomical instruments have enabled scientists to understand many of the mechanisms that drive CVs. But one phenomenon – periodic brightness variations referred to as superhumps – has proven more difficult to explain. First identified roughly 50 years ago, these brightness modulations appear for periods either slightly longer (positive superhumps) or shorter (negative superhumps) than the duration of the system’s orbital time frame.
In a new paper published March 23 in The Astrophysical Journal Letters, a team of astrophysicists from UNLV and the Space Telescope Science Institute offers a new explanation for the occurrence of negative superhumps in CVs.
For decades, the prevailing theory for their formation was that the disk of collected material around the white dwarf is both circular and tilted to the binary orbit, causing it to precess backwards in a motion similar to that of a spinning top. The problem with this theory, the UNLV team says, is that there hasn’t been a strong explanation for how the disk could be tilted or what could sustain the tilt.
Instead, the team proposes in the new paper that the accretion disk can become eccentric – in other words, it becomes elongated rather than circular. The eccentric accretion disk gradually rotates its orbit over time through a process known as retrograde apsidal precession. And, as a result of pressure, it naturally produces negative superhumps without requiring a disk tilt.
“Cataclysmic variables have been visible to the human eye for hundreds of years, and what began as observations of a blinking light in the sky were later revealed to be one star eating another star,” said David Vallet, study lead author and postdoctoral researcher in the Department of Physics and Astronomy at UNLV. “While observations of superhumps date back to the 1970s, we believe the eccentric disk model clears up prevailing concerns of the tilted disk model and explains the prevalence of negative superhumps across a wide range of binary star masses.”
In certain systems, this new model shows that disk expansion may create conditions in the inner and outer portions of the disk to allow for the temporary coexistence of positive and negative superhumps. According to researchers, the theory may also explain how positive superhumps can occur in high mass ratio systems if the disk density builds up in the outer parts of the disk.
These areas will form the focus of the team’s future research, which will involve using large numerical simulations to model an evolving disk and match a predicted light curve to the observations.
“Every piece of this puzzle increases our knowledge of mechanisms that drive the evolution of our universe,” said Vallet.
Publication Details
“Negative superhumps in cataclysmic variables driven by retrograde apsidal disk precession” was published March 23 in The Astrophysical Journal Letters. Co-authors include David Vallet, Rebecca Martin, and Stephen Lepp with the Nevada Center for Astrophysics at UNLV; and Stephen Lubow with the Space Telescope Science Institute in Baltimore. Martin and Lepp are professors in the UNLV Department of Physics and Astronomy, and Vallet is a postdoctoral researcher.
Journal
The Astrophysical Journal Letters
Method of Research
Observational study
Subject of Research
Not applicable
Article Title
Negative Superhumps in Cataclysmic Variables Driven by Retrograde Apsidal Disk Precession
Article Publication Date
23-Mar-2026
No comments:
Post a Comment