This site may earn affiliate commissions from the links on this page. Terms of utilise.

NASA's Kepler satellite has been observing the stars for nearly a decade, and it'due south produced a mountain of data in that time. Late last year, Google showed how machine learning could help astronomers dig through the Kepler backlog, and it discovered a few new exoplanets in the process. Google has now open sourced the planet-spotting AI so anyone can give it a shot.

We can't observe exoplanets directly yet, but we can spot the telltale dip in luminance when an exoplanet passes in front of its host star. Then, Kepler was designed to scan large swaths of the sky in search of these signals. However, there are a substantial number of candidate signals that might point to an exoplanet. We don't know for sure until astronomers tin examine the data more than closely, merely in that location's too much to bank check every reading. That'southward why astronomers take simply checked the 30,000 or so best candidates, which has resulted in the discovery of around ii,500 exoplanets.

Google's solution to the information backlog was to unleash the power of neural networks on the problem . That seems to be Google'southward go-to idea lately, whether you're talking about self-driving cars or smartphone photography. Using 15,000 examples of exoplanets in the data, Google trained its network to sift through Kepler information and place other exoplanet signals. After the preparation catamenia, Google's AI checked 670 stars that were known to have exoplanets. And wouldn't yous know it, Google spotted two new exoplanets that would accept otherwise gone unnoticed.

A neural network is adept at recognizing patterns, but you need a lot of data to train the network. Google is saving everyone the time of training a neural network on Kepler data by releasing its code freely. You lot tin can get the TensorFlow lawmaking on GitHub right now, and Kepler'due south information is also freely bachelor. Information technology'southward non every bit easy as grabbing both piles of code and launching an app, though. Experience with Google's TensorFlow platform and Python will help. Google'south blog post provides instructions on how you lot can examination the network past re-discovering Kepler 90i, one of the planets Google constitute in the original examination.

The Googlers behind this projection hope that the community will make employ of the code to go on the hunt for planets in Kepler's data. In that location are thousands more signals to analyze, and that could exist but the start. Googlers hope to develop more advanced neural networks to dig through NASA data for Kepler and future missions like the upcoming Transiting Exoplanet Survey Satellite.