NASA with the help of Google's Artificial finds a solar system like ours by analyzing data provided by Kepler Space Telescope
Recently researchers from NASA announced they have achieved some thing new. Using Google's Artificial Intelligence(AI) and data collected by Kepler Telescope scientists have identified a solar system like ours far far away, containing a star and 8 planets revolving it.
Recently researchers from NASA announced they have achieved some thing new. Using Google's Artificial Intelligence(AI) and data collected by Kepler Telescope scientists have identified a solar system like ours far far away, containing a star and 8 planets revolving it.
The newly-discovered Kepler-90i – a sizzling hot, rocky planet that orbits its star once every 14.4 days.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. Its outermost planet, Kepler-90h, orbits at a similar distance to its star as Earth does to the Sun.“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.
“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.”
NASA's Website says,'The discovery came about after Christopher Shallue along with another reasearcher Andrew Vanderburg trained a computer to learn how to identify exoplanets in the light readings recorded by Kepler – the minuscule change in brightness captured when a planet passed in front of, or transited, a star. Inspired by the way neurons connect in the human brain, this artificial “neural network” sifted through Kepler data and found weak transit signals from a previously-missed eighth planet orbiting Kepler-90, in the constellation Draco.'
In the test set, the neural network identified correct set of exoplanet data with 96% accuracy.After number of testings the researchers directed their model to search for weaker signals in 670 star systems that already had multiple known planets. Their assumption was that multiple-planet systems would be the best places to look for more exoplanets.
Neural network will become more precise as it is fed with more and more data patterns. Shallue and Vanderburg plan to apply their neural network to Kepler’s full set of more than 150,000 stars so that more exoplanets can be sifted out.
Read More on NASA Website
Why Artificial Intelligence?
NASA's Kepler Telescope has been searching alien worlds since 2009.Kepler’s dataset consists of more than 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.NASA was waiting for the right tool or technology to unearth them.Here comes the tech giant Google's Artificial Intelligence and Neural Network.Read More about Artificial Intelligence and Neural Networks
How researchers used Gooogle's Artificial Intelligent Neural Network to search earth like planets and solar systems like our's?
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. He became interested in exoplanet discovery after learning that astronomy, like other branches of science, is rapidly being inundated with data as the technology for data collection from space advances.“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.”
NASA's Website says,'The discovery came about after Christopher Shallue along with another reasearcher Andrew Vanderburg trained a computer to learn how to identify exoplanets in the light readings recorded by Kepler – the minuscule change in brightness captured when a planet passed in front of, or transited, a star. Inspired by the way neurons connect in the human brain, this artificial “neural network” sifted through Kepler data and found weak transit signals from a previously-missed eighth planet orbiting Kepler-90, in the constellation Draco.'
How Neural Network is trained to identify exoplanets?
A neural network is like our brain. If it is taught with enough examples , it can take decisions thereafter.So, researchers trained the neural network to identify transiting exoplanets using a set of 15,000 previously identified exoplanet data.The network learned it and identified similar data patterns in the huge collection of Kepler data.In the test set, the neural network identified correct set of exoplanet data with 96% accuracy.After number of testings the researchers directed their model to search for weaker signals in 670 star systems that already had multiple known planets. Their assumption was that multiple-planet systems would be the best places to look for more exoplanets.
Neural network will become more precise as it is fed with more and more data patterns. Shallue and Vanderburg plan to apply their neural network to Kepler’s full set of more than 150,000 stars so that more exoplanets can be sifted out.
Read More on NASA Website
No comments:
Write comments