United States space agency National Aeronautics and Space Administration (NASA) on Thursday announced the discovery of an eighth planet orbiting the star Kepler-90, which makes the explanatory system nearly like our own solar system and breaking the record for the star with the most exoplanets. And it discovers new planets in existing systems, observing signals that seem to be of interest, but are too weak to be noticed by humans. It's small, "sizzling" hot and rocky, whirling around its star every 14.4 days. 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.
In all, more than 3,560 exoplanets have been confirmed to date two-thirds of them spotted by the 2009-launched Kepler with another approximately 4,500 candidates awaiting verification.
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. Previously, earth΄s solar system had the largest known number of planets.
Unlike our own solar system however, the chances of life being on the eighth planet are slim as while it is about 30pc larger than our own planet, Kepler-90i is so close to its star that its average surface temperature is believed to exceed 400C, on a par with Mercury.
"The Kepler-90 star system is like a mini version of our solar system", said Andrew Vanderburg, an astronomic researcher at the University of Texas at Austin who worked on the discovery. Kepler-90h, the outermost planet in the system, orbits its star at a similar distance as Earth does to the Sun.
Most planets beyond our solar system are too far away to be imaged directly.
Using the neural network, the scientists were able to discover new planets in old data - Kepler-90i, as well as a sixth planet in a different star system, Kepler-80g.
Researchers hope astronomers will use this form of automation via machine learning as a tool to help astronomers make more of an impact, increase their productivity and inspire more people become astronomers. "It does that by learning by example, so we train the model by giving it a large set of labelled examples so it can learn which patterns it can use to make the decision on whether the data is in one category or the other".
Shallue, a senior software engineer with the Google AI team, came up with the idea of applying a neural network to Kepler data.
"We got lots of false positives of planets, but also potentially more real planets", said Vanderburg. In the test set, the neural network correctly identified true planets and false positives 96 percent of the time. "If you have a finer sieve then you will catch more rocks but you might catch more jewels, as well".
The new planet has been dubbed Kepler-90i. The result is an extremely stable system, similar to the seven planets in the TRAPPIST-1 system.
The research paper reporting these findings has been accepted for publication in The Astronomical Journal.
Though Kepler is still searching the skies, the data it has already sent back could contain evidence of even more exoplanets.
But that isn't where its similarities to our own solar system end. Other planets may lurk around stars surveyed by Kepler.