For a long time, it was believed that our solar system had the highest number of planets of any star system in the Milky Way. But the recent discovery of Kepler-90i, a rocky planet orbiting a sun-like star located 2,545 light-years from Earth, suggests we might not be that special after all.
Kepler-90i is in fact the eighth planet to be discovered in the Kepler-90 system, a “mini version” of our solar system with its most distant planet located as close to its star as the Earth is to the sun. “For the first time since our solar system planets were discovered thousands of years ago, we know for sure that our solar system is not the sole record holder for the most planets,” Andrew Vanderburg, a NASA researcher and an astronomer at the University of Texas at Austin, said in a statement.
As explained in a press release from NASA, researchers were able to identify the previously missed planet by adopting machine learning techniques that are designed to find patterns in data the same way human brains do. The algorithm was developed by Christopher Shallue, a senior software engineer with Google’s research team Google AI.
After learning that NASA’s Kepler Space Telescope had collected a large dataset on exoplanets—planets that orbit a star outside of our solar system—Shallue started thinking of ways in which artificial intelligence could be used to make sense of all that data. Together with Vanderburg, he then trained a computer to look for dips in brightness as these are often clues that a planet is transiting a star.
This kind of monitoring had previously been done by using automated tests or the human eye but, as Shallue explained, the new method was able to capture some of the weakest signals that had been previously missed. “Just as we expected, there are exciting discoveries lurking in our archived Kepler data, waiting for the right tool or technology to unearth them,” Paul Hertz, director of NASA’s Astrophysics Division in Washington, said in the release. “This finding shows that our data will be a treasure trove available to innovative researchers for years to come.”
Shallue and Vanderburg, whose findings are due to be published in an upcoming issue of The Astronomical Journal, now plan to apply their algorithm to the telescope’s full data set, which encompasses more than 150,000 stars.