Early Prime Day Deals Roe v. Wade Overturned Surface Laptop Go 2 Review 4th of July Sales M2 MacBook Pro Deals Healthy Meal Delivery Best TVs for Every Budget Noise-Canceling Earbuds Dip to $100

AI confirms 50 new planets from old NASA data, in a groundbreaking first

Machine learning holds promise for making sense out of heaps of possible planet sightings.

An artist's conception of some of Kepler's big exoplanet finds.
NASA/W. Stenzel

Our planet-hunting telescopes have gotten so good at their jobs that they've located thousands of possible planets outside our solar system. That means scientists have to sift through a whole lot of data to figure out what's a real planet and what's a pretender.

A research team led by David Armstrong at the University of Warwick in the UK has worked out how to harness artificial intelligence to handle some of the heavy-lifting of planet confirmation, giving astronomers a new tool to help validate distant worlds.

Now playing: Watch this: These telescopes offer a unique way to view the night...

Telescopes like NASA's Transiting Exoplanet Survey Satellite (TESS) look for a telltale dip in brightness that indicates something is passing by a star. Sometimes this is a planet, sometimes it's a glitch, asteroids, dust or a quirk of a binary star system. 

The research team created a machine learning algorithm and trained it using data on confirmed planets and false-positives from NASA's retired Kepler mission. Then they turned it loose to analyze a group of unconfirmed planet candidates, also from the Kepler data. In a first, the AI system confirmed 50 planets out of that bunch.

"The algorithm we have developed lets us take 50 candidates across the threshold for planet validation, upgrading them to real planets," Armstrong said in a Warwick release Tuesday. Validating planets can help scientists direct their resources to interesting spots in space without wasting their time on "fake" planets. 

The ability to confirm planets using this method is a step forward. Scientists had been using machine learning to rank candidates. "Rather than saying which candidates are more likely to be planets, we can now say what the precise statistical likelihood is. Where there is less than a 1% chance of a candidate being a false positive, it is considered a validated planet," said Armstrong.

The technique holds promise for sifting through the large amounts of data churned out by projects like TESS and ESA's planned PLATO mission. TESS' primary mission alone spotted 66 new exoplanets and 2,100 candidates.

"We still have to spend time training the algorithm, but once that is done it becomes much easier to apply it to future candidates," Armstrong said. "You can also incorporate new discoveries to progressively improve it."