Google's newly released open source code now gives the public a chance to hunt alien planets using data gathered by NASA's Kepler space telescope.
How Kepler Space Telescope Finds Exoplanets
Kepler, which was launched in March 2009, finds exoplanets by detecting small changes in brightness captured when a planet transits or passes in front of its host star.
"When a planet passes in front of a star as viewed from Earth, the event is called a 'transit,'" NASA explained. "Kepler finds planets by looking for tiny dips in the brightness of a star when a planet crosses in front of it — we say the planet transits the star."
The exoplanet-hunting spacecraft has so far discovered more than 2,500 confirmed worlds outside of the solar system.
Machine Learning Helps Detect Signals Of Exoplanet In Kepler Data
Last year, Christopher Shallue, a senior software engineer with Google AI, and Andrew Vanderburg, astronomer at the University of Texas at Austin, discovered two alien planets using machine learning from Google.
Machine learning is an approach to artificial intelligence in which computers "learn."
The duo trained a computer to recognize weak exoplanet signals in the Kepler data using an approach based on how neurons connect in the human brain.
The artificial neural network sifted through Kepler data to find weak transit signals, which eventually led to the discovery of the new worlds called Kepler-80g and Kepler-90i.
Scientists saw potentials in using the technology to find some of the weakest signals of extraterrestrials worlds, which could pave way for new exoplanet discoveries.
"Just as we expected, there are exciting discoveries lurking in our archived Kepler data, waiting for the right tool or technology to unearth them," said NASA's Astrophysics Division director Paul Hertz. "This finding shows that our data will be a treasure trove available to innovative researchers for years to come."
Code Now Open-Sourced And Available For Use By The Public
Astronomy enthusiasts do not have to wait for long to use the tool to search for exoplanets. On March 8, Shallue announced that they are releasing the code for processing Kepler data to the public.
"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," Shallue wrote on the Google Research blog. "We're hard at work improving our model, and now that it's open sourced, we hope others will do the same!"