Scientists used artificial intelligence and NASA’s Kepler Space Telescope data to uncover 301 previously unknown exoplanets, which join the 4,569 already validated planets orbiting a multitude of distant stars. The team used a new deep neural network called ExoMiner that leverages NASA’s Pleiades supercomputer to distinguish real exoplanets from different types of false positives.
ExoMiner helped research teams who are professionals at sifting through data and deciphering possible exoplanets, more specifically, data gathered by NASA’s Kepler spacecraft and K2, its follow-on mission. Each of the 301 machine-validated planets were originally detected by the Kepler Science Operations Center pipeline and then promoted to planet candidate status by the Kepler Science Office.
- PERFECT ENTRY-LEVEL TELESCOPE: The Celestron PowerSeeker 80EQ is an easy-to-use and powerful telescope. This 80mm refractor telescope offers enough...
- MANUAL GERMAN EQUATORIAL MOUNT: With its slow-motion altitude rod, the German Equatorial mount allows you to navigate the sky with ease. Find...
- COMPACT AND PORTABLE: The ideal telescope for adults and kids to use together, the PowerSeeker is compact, lightweight, and portable. Take it to your...
Unlike other exoplanet-detecting machine learning programs, ExoMiner isn’t a black box – there is no mystery as to why it decides something is a planet or not. We can easily explain which features in the data lead ExoMiner to reject or confirm a planet,” said Jon Jenkins, exoplanet scientist at NASA’s Ames Research Center in California’s Silicon Valley.