Scrutiny of sky, data finds kindred system

Nasa is set to make a major finding from its planet-hunting Kepler space telescope. The planet-hunting satellite has been working with Google's AI system

Scrutiny of sky, data finds kindred system

As for Kepler-90, its planetary system could have more than eight planets, the scientists pointed out - they could just lie farther away from the star and not have orbited enough times for Kepler to have spotted them during its primary mission.

The Kepler space telescope searches for these exoplanets -those planets orbiting stars beyond our solar system - by measuring how the brightness of a star changes when a planet transits, or crosses in front of its disk.

A search for new worlds around 670 known multiple-planet systems using this machine-learning technique yielded not one, but two discoveries: Kepler-90i and Kepler-80g.

Researchers trained a computer to learn how to identify the faint signal of transiting exoplanets in Kepler's vast archive of deep-space data.

NASA's discovery of the new planet comes with help of some fancy artificial intelligence by Google.

The star known as Kepler-90, is just a bit hotter and larger than the Sun; astronomers already knew of seven planets around it. 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, on par with Mercury.

"The Kepler-90 star system is like a mini version of our solar system".

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

Other planetary systems probably hold more promise for life than Kepler-90.

Using Google machine learning, NASA discovered an eighth planet circling Kepler-90, a sun-like star 2,545 light-years from Earth.

The findings also establish the growing role that neural networks and other machine learning techniques could play in the hunt for more elusive planets outside our own solar neighbourhood. A combination of computer software running automated tests and human judgement are used to verify the most promising results, but that means that the weakest signals are often missed.

The find sets a new record for the most exoplanets around a single star and, for the first time, ties with our own.

Machine learning had not been applied to data acquired by the Kepler telescope until Shallue came up with the idea, he said.

Kepler-90i is what's called a "super-Earth" exoplanet.

"Their assumption was that multiple-planet systems would be the best places to look for more exoplanets", researchers wrote in the press release.

Besides, he said that this information would be a "treasure trove" that other experts will be able to use fpr further research.

The next three planets beyond Kepler-90i - 90d, 90e and 90f - fall into a sub-Neptune size class and complete an orbit every 60, 92 and 125 days, respectively.

NASA's Ames Research Center is located in California's Silicon Valley. Kepler has gathered four years of data on what's in the sky and found 150,000 stars - much more than people could see.

If you want to search for planets among Kepler's weaker signals - which are far more numerous - then that haystack gets "much, much larger", he added.

The researchers used TensaFlow, an open source software library produced by Google, and it only took two hours to train the computer model using a regular desktop PC.

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

Latest News