NASA finds out solar system similar to ours by using Artificial Intelligence

15 December 2017, 08:43 AM
NASA finds out solar system similar to ours by using Artificial Intelligence (Source: NASA)
NASA finds out solar system similar to ours by using Artificial Intelligence (Source: NASA)

Nasa’s Kepler space telescope with the help of artificial intelligence has discovered a solar system with as many as planets as our own.

NASA confirmed this news in a statement given on Thursday, saying, “Our solar system now is tied for most number of planets around a single star.”

However, none of the planets are likely to be hospitable to carry life on them.

The solar system, with eight planets, is the largest known outside ours and orbits around a star called Kepler 90 about some 2,545 light-years away.

“The Kepler-90-star system is like a mini version of our solar system. You have small planets inside and big planets outside, but everything is scrunched in much closer,” said Andrew Vanderburg, an astronomer at the University of Texas at Austin.

Kepler-90i, the newly identified planet, is rocky like Earth, but orbits its star once in every 14.4 days, which count to two weeks on the Earth.

Vanderburg said, “Kepler-90i is not a place I'd like to go visit, though. Its surface is likely far too hot.”

The calculated temperature of the Kepler-90i, as recorded by NASA, is about 426 degrees Celsius, which is nearly as hot as Mercury, the first planet in our Solar System. The scientists found this by using machine learning from Google.

The process involved teaching a computer to scan a trove of 35,000 possible planetary signals collected from NASA's Kepler Space Telescope for search for signs of planetary transits, that are the dimming of light when planets pass in front of a star.

The Kepler space telescope was launched in 2009 and has scanned around 1,50,000 stars. Some 2,500 far-away worlds have been already confirmed by NASA using Kepler data.

Christopher Shallue, a senior software engineer with Google’s research team, said, “I became interested in applying neural networks toc astronomy when I learned that the Kepler mission had collected so much data that it was impossible for scientists to examine it all manually. Instead scientists selected the strongest signals, which are the most likely to be actual planets, to receive the most attention.”

“Machine learning really shines when there is too much data for humans to examine for themselves,” said Shallue.

More planets are expected to be found because researchers plan to apply their neural network to Kepler’s full set of 1,50,000 stars.

“There is a lot of unexplored real estate in the Kepler 90 system. It would almost be surprising to me if there weren't any more planets in around that star,” said Vanderburg.

More Earth-like planets can be searched or identified one day suing artificial intelligence.

Also Read: NASA likely to make big announcement over the findings of alien life

“For the first time since our solar system planets were discovered thousands of years ago, we know for sure that the solar system is not the sole record holder for the most planets, and we have just scratched the surface. Maybe there are systems out there with so many planets that they make our eight-planet solar system seem ordinary,” Vanderburg said.

The studies are published in The Astronomical Journal.

First Published: Friday, December 15, 2017 08:12 AM
For all the latest Science News Download the News Nation App available on Android and iOS.