Artificial Intelligence, NASA Data Used to Discover Eighth Planet Circling Distant Star


The Kepler Space Telescope was launched in 2009 to search for Earth-like planets around distant, sun-like stars.

The discovery was made by applying artificial intelligence to data from NASA's Kepler Space Telescope.

Researchers from the U.S. space agency and the tech giant have taught a computer to review massive amounts of Kepler Telescope star data.

"This finding shows that our data will be a treasure trove available to innovative researchers for years to come", said Paul Hertz, director of NASA's Astrophysics Division, in the release. And these planets resemble those around us: rocky planets circling in orbit near the star, with gas giants farther away.

Even without Pluto, our solar system always held the record for most planets orbiting a single star.

NASA estimated the planet΄s surface temperature to be around 426 degrees Celsius (800 Fahrenheit) and said it likely was inhospitable to life.

All of the planets in the Kepler-90 system are closely situated to its star. It also discovered a sixth, Earth-sized planet in the Kepler-80 system.

Astronomers had never before observed an eight-planet network beside the solar system that includes Earth, researchers said.

With the idea of eventually differentiating among exoplanets, Christopher Shallue, senior software engineer at Google AI in California, and Andrew Vanderburg, astronomer and NASA Sagan postdoctoral fellow at the University of Texas, Austin, trained a computer how to differentiate between images of cats and dogs.

We can't claim our solar system is unique anymore.

With the discovery of Kepler-90i, the solar system is now tied with the Kepler-90 star system with the most number of planets.

Google Opens Its First AI Center in Beijing, China
The next year, Google stood up to the authorities and stopped voluntarily censoring its search results in the country. Like Google , most major US information technology companies can not ignore the booming growth market that is China .

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.

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.

Aimed at distant planet researchers, Mr. Vanderburg has received funding through a NASA fellowship. They found that the computer was able to identify which signals were of plants 96 per cent of the times.

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 TRAPPIST-1 star, an ultra-cool dwarf, has seven Earth-size planets orbiting it.

Shallue, a senior software engineer at Google AI, chose to apply a neural network concept to the vast amounts of Kepler data in his spare time.

The U-shaped dip of Kepler 90i passing in front of its star was too weak a signal for human detection.

"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", he said.

The research paper reporting these findings has been accepted for publication in The Astronomical Journal. It also has an orbit of 14.4 days.

"These results demonstrate the enduring value of Kepler's mission", Jessie Dotson, project scientist at NASA's Ames Research Center, said in a statement. "I hope it may give people more of a reason to go into astronomy to use more advanced technology like this".