Third rock from the star Kepler-90

For the first time, researchers have used artificial intelligence to discover an exoplanet around another star.
By | Published: December 14, 2017
Kepler-90i, a recently discovered exoplanet (labeled in red) found using Google AI technology, is part of a system with a very similar configuration to our solar system, where small planets lie near the star and larger planets are found further away.
NASA/Ames Research Center/Wendy Stenzel
It’s official: the Sun is no longer the only star with eight planets.

In a joint teleconference today, NASA and Google announced the recent discovery of an eighth planet orbiting the Sun-like star Kepler-90, located some 2,500 light-years from Earth. The newly discovered exoplanet, named Kepler-90i, is a rocky world with a surface temperature of roughly 800°F (426°C) that zooms around its host star once every 14.4 days.

The discovery of Kepler-90i (as well as the discovery of another exoplanet known as Kepler-80g) was made using the first neural network — developed by Google — designed to analyze archival data from the Kepler Space Telescope.

“A neural network is a machine learning algorithm that is very loosely inspired by the human brain,” said Christopher Shallue, senior software engineer at Google AI and co-author of the study. During a teleconference, he explained that the algorithm takes sample inputs, learns to identify patterns in the data, and then uses those patterns to make future identifications.

When Kepler was first launched in 2009, astronomers didn’t know how common planets around other stars were. But within four years, Kepler generated a dataset of 35,000 possible planetary signals from just one relatively small area of the sky. Though some basic algorithms were used to sort and filter the data, human brains were still the primary workhorses for identifying exoplanets. This not only took a lot of valuable time, but also meant the weakest signals were often overlooked.

Before the new neural network could analyze the Kepler data, researchers had to first train it to spot transiting exoplanets from Kepler’s light curves. Light curves show how the brightness of a star drops off when an orbiting planet passes in front of it.

Using 15,000 previously confirmed exoplanet signals as flash cards, the neural network “learned” to correctly identify true planets. After the neural network knew what patterns it was looking for, the researchers turned it loose on 670 of Kepler’s weaker signals. In these weak signals, the AI found two likely exoplanets — Kepler-90i and Kepler-80g. The researchers pointed out the probability that the exoplanet detections were false positives is only 1 in 10,000.

“Just as we expected, there are exciting discoveries lurking in our archived Kepler data, waiting for the right tool or technology to unearth them,” said Paul Hertz, Astrophysics Division director at NASA, in a press release. “This finding shows that our data will be a treasure trove available to innovative researchers for years to come.

Kepler has discovered more than 2,500 of the 3,500 confirmed exoplanets to-date, many of which are much smaller and fainter than previously detected exoplanets.
NASA/Ames Research Center/Jessie Dotson and Wendy Stenzel
“These results demonstrate the enduring value of Kepler’s mission,” said Jessie Dotson, Kepler’s project scientists at NASA’s Ames Research Center. “New ways of looking at the data — such as this early-stage research to apply machine learning algorithms — promises to continue to yield significant advances in our understanding of planetary systems around other stars. I’m sure there are more firsts in the data waiting for people to find them.”

The researchers’ findings have been accepted for publication in The Astronomical Journal. The team will also be publicly releasing the neural network’s code and training model for anyone who would like to run their own analysis of the Kepler data.