You can now hunt for exoplanets from the comfort of your home, thanks to Google’s open source machine learning algorithm. In December, US Space agency announced that the system had discovered two exoplanets by training a neural network to analyse data from NASA’s Kepler space telescope and accurately identifying the most promising planet signals.
Those techniques are now available to the public. "Today, we're excited to release our code for processing the Kepler data, training our neural network model and making predictions about new candidate signals," Google senior software engineer with the Google Brain Team and the lead author of that December discovery study, Chris Shallue, wrote on Google's blog.
“We consider this a successful proof-of-concept for using machine learning to discover exoplanets, and more generally another example of using machine learning to make meaningful gains in a variety of scientific disciplines,” Shallue said. “We hope this release will prove a useful starting point for developing similar models for other NASA missions, like K2 (Kepler’s second mission) and the upcoming Transiting Exoplanet Survey Satellite mission.”
The Kepler space telescope launched in 2009 hunts for planets by measuring the brightness of a star over time. When a planet passes in front of the star, it temporarily blocks some of the light, which causes the measured brightness to decrease and then increase again shortly.
To search for planets in Kepler data, scientists use automated software to detect signals that might be caused by planets, and then manually follow up to decide whether each signal is a planet or a false positive. To avoid being overwhelmed with more signals than they can manage, the scientists apply a cutoff to the automated detections. Even with this cutoff, to date, over 30,000 detected Kepler signals have been manually examined, and about 2,500 of those have been validated as actual planets.
The Google Brain team applies machine learning to a diverse variety of data, from human genomes to sketches to formal mathematical logic. “Considering the massive amount of data collected by the Kepler telescope, we wondered what we might find if we used machine learning to analyse some of the previously unexplored Kepler data,” Shallue wrote. In collaboration with University of Texas, the team developed a neural network to help search the low signal-to-noise detections for planets.
About 30,000 Kepler signals had already been manually examined and classified by humans. “We used a subset of around 15,000 of these signals, of which around 3,500 were verified planets or strong planet candidates, to train our neural network to distinguish planets from false positives,” Shallue said. The system was tested for its effectiveness by searching for new planets in a small set 670 stars.
Shallue pointed out that the neural network rejected most of these signals as spurious detections, but a handful of promising candidates rose to the top, including two newly discovered planets: Kepler-90 i and Kepler-80 g. The model is now available to the public, allowing researchers to train it further and discover more planets.