Google and university researchers are using deep learning to discover exoplanets
Researchers from Google and multiple universities have discovered two new exoplanets (planets outside our solar system) using a convolutional neural network dubbed AstroNet K2. An additional 14 other objects could be also be identified as exoplanets with additional research.
The announcement builds upon research released last year by Harvard University astrophysicist Andrew Vanderburg and Google AI’s Chris Shallue, which also uses machine learning to sift through NASA’s Kepler data to find celestial bodies in space. Google later open-sourced its exoplanet-searching model trained with Kepler data on GitHub.
“The work is significant because this is the first time that a neural network has ever been successfully applied to K2 data,” Dattilo told VentureBeat in a phone interview. “Different types of machine learning have been applied to all various types of astronomical datasets like its predecessor was on Kepler data, but there are different challenges that go with K2 data because the telescope was unstable.”
For the first four years after its launch in 2009, the Kepler space telescope was used to study potential Earth-like planets passing in front of stars. It would observe more than 200,000 stars, but a mechanical malfunction made it unable to focus on a single part of the sky, making data collection far more sporadic. Kepler was officially retired by NASA last year.
To overcome this challenge, more than 30,000 images with promising characteristics were collected and examined, and more than 22,000 we’re used for training the semi-supervised AI system. AstroNet K2 is 98 percent accurate in test datasets.
Members of the Google Brain team, the astronomy departments at the University of California, Berkeley, the University of Texas, Austin, and the Harvard-Smithsonian Center for Astrophysics shared the findings in a paper. They conclude that AstroNet K2 is “not yet ready to completely automatically detect and identify planet candidates” due to the identification of too many false positives, but it could augment astronomists today working to better understand the universe.
“It doesn’t just give us a handful of candidates and say, ‘These are the ones. These are planets,’ and that’s it. It returns a whole bunch of them dampened by false positive signals. So you need the help of a human astronomer to sort through those and see what isn’t a planet, but instead of 20,000 signals, now you only have to look through 1,000 signals, and that saves so much time,” she said.
Like its predecessor, AstroNet K2 will be further refined and open-sourced to be made available to the wider AI community in the future, Dattilo said.
BruceDayne Enterprise's
via VentureBeat https://venturebeat.com
https://brucedayne.com March 26, 2019 at 07:17PMBruceDayne, Khari Johnson March 26, 2019 at 08:31PM