AI reveals first distant solar system rivaling our own in planet number

WASHINGTON, Dec. 14 (Xinhua) -- Scientists announced on Thursday they have found, for the first time, an eighth planet in a distant star system, tying it with our own solar system for having the most known planets.

The newly-discovered Kepler-90i, "a sizzling hot, rocky planet" that orbits its star once every 14.4 days, was found in data from NASA's Kepler Space Telescope using the "neural network" artificial intelligence approach developed by Google.

"Today, Kepler confirms that stars can have large families of planets, just like our solar system," Paul Hertz, director of the U.S. space agency NASA's Astrophysics Division said in a teleconference.

In the study, researchers first trained the neural network they developed to identify exoplanets using 15,000 signals from Kepler data that have already been examined previously.

It turned out the neural network correctly identified true planets and false positives 96 percent of the time.

Then, with the neural network having "learned" to detect the pattern of an exoplanet, the researchers directed their model to search for weaker signals in 670 star systems that already had multiple known planets.

Their assumption was that multiple-planet systems would be the best places to look for more exoplanets.

As a result, they found weak signals from a previously-missed eighth planet orbiting Kepler-90, a Sun-like star 2,545 light years from Earth in the constellation Draco and the first seven-planet system identified with Kepler back in 2013.

Other planetary systems, however, probably hold more promise for life than Kepler-90, which packs all eight planets closer to the host star than Earth is to the sun.

"About 30 percent larger than Earth, Kepler-90i is so close to its star that its average surface temperature is believed to exceed 800 degrees Fahrenheit (427 degrees Celsius), on par with Mercury," NASA said in a statement.

"Its outermost planet, Kepler-90h, orbits at a similar distance to its star as Earth does to the Sun."

Andrew Vanderburg, a NASA Sagan Postdoctoral Fellow and astronomer at the University of Texas at Austin, one of the researchers who developed the neural network, called Kepler-90 "a mini version of our solar system."

"You have small planets inside and big planets outside, but everything is scrunched in much closer," Vanderburg said.

The researchers also found a sixth planet in the Kepler-80 system.

"This one, the Earth-sized Kepler-80g, and four of its neighboring planets form what is called a resonant chain -- where planets are locked by their mutual gravity in a rhythmic orbital dance," NASA said.

The research paper reporting these findings has been accepted for publication in The Astronomical Journal.

Vanderburg and Christopher Shallue, a senior software engineer with Google's research team Google AI, planned to apply their neural network to Kepler's full set of more than 150,000 stars.

Launched in March 2009, Kepler is NASA's first mission to find potentially habitable Earth-size planets. The space telescope halted its mission in 2013 due to a technical glitch and began a new extended mission called K2 in 2014.

NASA said Kepler's first four-year dataset consists of 35,000 possible planetary signals.

Automated tests, and sometimes human eyes, are used to verify the most promising signals in the data, but the weakest signals often are missed, it said.

"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 Hertz. "This finding shows that our data will be a treasure trove available to innovative researchers for years to come." Enditem