AI confirms 50 new planets from old NASA data, in a first for machine learning

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. Get the latest science stories from CNET every week. Telescopes like NASA's Transiting Exoplanet Survey Satellite (TESS) look for a telltale dip in brightness that indicates something is passing by a star.