Published: Sun, December 17, 2017
IT | By Lester Massey

NASA discovers new planet 2500 light years away, thanks to Google AI

NASA discovers new planet 2500 light years away, thanks to Google AI

NASA has used Google's artificial intelligence (AI) to discover a record-tying eighth exoplanet circling a Sun-like star 2,545 light-years from Earth, marking the first finding of an eight-planet solar system like ours.

"It ties Kepler 90 with our own Solar System for having the most known planets", said Paul Hertz, Astrophysics Division director at NASA Headquarters, during NASA's press conference. "You have small planets inside and big planets outside, but everything is scrunched in much closer", Vanderburg said. "But Kepler 90i is probably not a place I'd like to go visit". Its existence brings up the total number of planets in the Kepler-90 system to eight, the same number of planets in our solar system.

This image shows all the spacecraft involved in the search for alien planets (Photo: NASA)What is Kepler 90i like? The data was then analysed using machine learning technology from Google.

The research team found the new planet, known as Kepler-90i - as well as another world in a different system - after analyzing archival data from NASA's Kepler mission using Google machine-learning techniques.

Today, NASA announced the latest discovery made using its Kepler space observatory.

"In my spare time, I started googling for "finding exoplanets with large data sets" and found out about the Kepler mission and the huge data set available", said Shallue.

NASA has discovered an eighth planet around a distant star, which means we're no longer the largest solar system we know of. Brightness dips as planets in front of their star.

In 2014, Kepler shifted to a second mission known as K2, during which it hunts for exoplanets on a more limited basis but also makes a variety of other observations.


Additionally, an Earth-sized planet was spotted orbiting Kepler-80, the release said.

Artificial intelligence has been used before to process the Kepler data, but by imitating the way neurons connect in the human brain, Shallue and Vandenberg were able to train the computer to seek out and identify weak transit signals that had previously been missed.

Machine learning developed by Google was crucial to the discovery. Astronomers now suspect at least one planet orbits every star in the sky.

"Machine learning really shines in situations where there is so much data that humans can't search it for themselves", Shallue said.

The neural network is trained on 15,000 signals from the Kepler dataset that have been previously verified as planets or non-planets. So far, scientists have confirmed around 2,500 exoplanets, with 30 of those potentially being Earth-like planets located within their stars' habitable zones where liquid water could exist.

Vanderburg said the got lots of false positives of planets, but also more potential real ones too.

What's perhaps even more remarkable is that just by looking at this data scientists can determine its size, distance from the star and even some basic information about its composition and atmosphere.

The new study has been accepted for publication in The Astronomical Journal.

Like this: