A team working with data gathered by Nasa's Kepler space telescope has discovered an eighth planet in a star system previously thought to have only seven.

The discovery makes the star system the first known system, other than our own, to have eight planets.

The new planet was discovered when a form of machine learning known as a neural network, developed by Google, was applied to data previously gathered by Kepler.

The new planet, Kepler-90i, is thought to be rocky and lies in the Kepler-90 star system.

The Sun-like star is 2,545 light years from Earth and the planet orbits it once every 14.4 days.

Kepler-90i is incredibly hot, with average surface temperatures of 800 degrees Fahrenheit. 

The scientists say the Kepler 90 system could possibly have even more planets that have yet to be identified.

We need your consent to load this YouTube contentWe use YouTube to manage extra content that can set cookies on your device and collect data about your activity. Please review their details and accept them to load the content.Manage Preferences

The neural network was trained using the signals from 15,000 previously confirmed planets found by Kepler and gradually learned what they looked like to a confidence level of 96%.

The software then trawled the wider Kepler data set and discovered two new planets - Kepler-90i and another around a different star called Kepler-80g.

The team now plans to search the data from all 150,000 stars identified by Kepler to see if more planets can be confirmed.

In total 3,567 extra-solar or exoplanets have so far been identified in the universe, with 2,525 of those located by Kepler.

"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, director of NASA’s Astrophysics Division in Washington.

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

The neural network software was developed by researchers Christopher Shallue, a software engineer with Google, and Andrew Vanderburg, a NASA Sagan Postdoctoral Fellow and astronomer at the University of Texas at Austin.

They trained a computer to learn how to identify exoplanets in the light readings recorded by Kepler – the miniscule change in brightness captured when a planet passed in front of, or transited, a star. 

"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 Christopher Shallue.

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

"We got lots of false positives of planets, but also potentially more real planets," said Mr Vanderburg.

"It’s like sifting through rocks to find jewels. If you have a finer sieve then you will catch more rocks but you might catch more jewels, as well."