In a recent development, artificial intelligence was used by researchers at NASA to discover the eighth planet circling a distant star. Orbiting around a star called Kepler-90, a Sun-like star 2,545 light-years from Earth, the planet was discovered using data from NASA’s Kepler Space Telescope.
“Our solar system now is tied for most number of planets around a single star, with the recent discovery of an eighth planet circling Kepler-90”, NASA said in a statement.
What is interesting to note here is that machine learning from Google was used for the discovery of Kepler-90i, which is a sizzling hot, rocky planet that orbits its star once every 14.4 days. The computers learned to identify planets by finding in Kepler data instances where the telescope recorded signals from planets beyond our solar system, known as exoplanets, NASA’s official website reported.
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.
Artificial “neural network” is the way out!
NASA researchers Christopher Shallue and Andrew Vanderburg trained a computer to learn how to identify exoplanets in the light readings recorded by Kepler, which identified minuscule change in the brightness captured when a planet passed in front of, or transited a star.
This artificial neural network which is inspired by the way neurons connect in the human brain sifted through Kepler data and found weak transit signals from a previously-missed eighth planet orbiting Kepler-90, in the constellation Draco.
While machine learning has previously been used in searches of the Kepler database, this research demonstrates that neural networks are a promising tool in finding some of the weakest signals of distant worlds, said the NASA website.
“The Kepler-90 star system is like a mini version of our solar system. You have small planets inside and big planets outside, but everything is scrunched in much closer,” said Vanderburg, a NASA Sagan Postdoctoral Fellow and astronomer at the University of Texas at Austin. Shallue, a senior software engineer with Google’s research team Google AI, came up with the idea to apply a neural network to Kepler data.
“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 Shallue. “Machine learning really shines in situations where there is so much data that humans can’t search it for themselves.”
Kepler’s four-year dataset consists of 35,000 possible planetary signals. Automated tests, and sometimes human eyes, are used to verify the most promising signals in the data. However, the weakest signals often are missed using these methods.
Training the neural network
The website explained that the researchers trained the neural network to identify transiting exoplanets using a set of 15,000 previously-vetted signals from the Kepler exoplanet catalogue. In the test set, the neural network correctly identified true planets and false positives 96 percent of the time.
As the neural network learnt to detect the pattern of a transiting exoplanet, the researchers directed their model to search for weaker signals in 670 star systems that already had multiple known planets, with an assumption that multiple-planet systems would be the best places to look for more exoplanets.
The researchers also believe that there might be more exciting discoveries lurking in achieved Kepler data, for which they are looking for right tools to unearth them. The research paper reporting these finding would be published in The Astronomical Journal.
Try deep learning using MATLAB