AI Finds 100+ Hidden Planets in NASA Data
Astronomers have used a powerful new artificial intelligence system called RAVEN to analyze data from NASA’s TESS mission, uncovering more than 100 confirmed exoplanets, including 31 brand-new worlds. The system scanned observations from over 2.2 million stars, detecting faint dips in starlight that occur when planets pass in front of their host stars. Published in Monthly Notices of the Royal Astronomical Society (MNRAS), the findings represent one of the most detailed planet-hunting analyses ever done using AI.
RAVEN doesn’t just detect signals, it validates them. The system confirmed 118 planets and identified over 2,000 high-quality candidates, nearly 1,000 of them entirely new. Researchers say this makes it one of the most reliable automated tools for turning massive space datasets into confirmed discoveries, reducing noise and false detections that normally slow down planet searches.
Rare and Extreme Worlds
Among the discoveries are unusual planets that challenge current theories. Some are ultra-short-period worlds that complete an orbit in less than 24 hours, while others exist in the mysterious “Neptunian desert”, a region where such planets are expected to be extremely rare. Scientists say these findings are helping refine how planetary systems form and survive under extreme conditions.
Mapping the Galaxy with AI
Beyond individual discoveries, the study also reveals broader patterns in the galaxy. Researchers found that about 9–10% of Sun-like stars host close-in planets, while Neptunian desert planets appear around just 0.08% of stars. By processing enormous datasets consistently, RAVEN allows scientists to measure how common different types of planets really are, marking a shift toward large-scale, AI-driven astronomy.
According to the University of Warwick team, the system is designed to handle the full process; from detecting signals to statistically confirming planets while also identifying hidden biases in detection. This means future missions like ESA’s PLATO could rely on similar AI tools to uncover even more distant and unusual worlds across the galaxy.
Sources: University of Warwick, Science Daily, NASA TESS mission data
