Princeton-led team discovers over 10,000 new exoplanet candidates using AI

American astronomers, armed with a suite of cutting-edge AI tools, have discovered a remarkable collection of planets orbiting alien stars across this sector of the Milky Way.

Just one generation after the first exoplanet orbiting a sun-like star was detected in 1995, a team of astrophysicists has uncovered the largest cache of planet candidates ever recorded — more than 10,000 orbs around a diverse range of stars — in a discovery powered largely by artificial intelligence.

Key Findings

The team, led by astrophysicist Joshua Roth at Princeton University, detailed its findings in a paper titled "The T16 Planet Hunt: 10,000 New Planet Candidates from TESS Cycle 1."

Roth, a graduate researcher at Princeton, told Forbes in an interview that the team identified a treasure trove of exoplanet candidates, ranging from colossal gas giants locked in tight orbits around their stars — known as "Hot Jupiters" — to "super-Earths" that may prove to be habitable.

"Hot Jupiters are the easiest to detect," Roth said, explaining that their immense size blocks a greater proportion of light when they cross in front of their star, and their short orbital periods create a rapid sequence of these light-blocking "transits," all of which can be captured by high-power imaging telescopes.

Breakdown of Discoveries

• Gas giants: More than 9,000 exoplanets
• Neptune-size bodies: Over 100
• Potential super-Earths: 11

The stars surveyed ranged from M-dwarfs — small, orange-colored suns that can live for more than a trillion years — to blue supergiants that burn brightly but die young.

AI-Powered Methodology

Roth's collaboration, spanning Princeton, MIT, UCLA, and Las Campanas Observatory in Chile, relied on an array of advanced AI tools to rapidly analyze stellar imagery captured by the Transiting Exoplanet Survey Satellite (TESS), a space-based telescope.

After the images were converted into light curves — graphs charting the changing brightness of a star, potentially caused by an orbiting planet partially eclipsing its sun — the team deployed AI software, including the Cambridge Exoplanet Transit Recovery Algorithm, to examine the 80 million light curves derived from TESS and narrow down the top exoplanet candidates.

A machine learning system called Random Forest, which the team trained, further refined the pool of potential planets.

Global Context

While astronomers around the world — from Cambridge University in the UK to a Western European coalition of scholars — have been experimenting with combining different AI breakthroughs to accelerate their searches for planets across the galaxy, Roth's team has taken the global lead in terms of making the most sensational and monumental discoveries.