Machines used to teach astronomers about stars

A new method has been employed to determine the properties of millions of the stars in our Galaxy


Astronomers are using a method called machine learning to help them understand the properties of numerous stars.

Credit: NASA/JPL-Caltech

Modern super scopes are capable of surveying millions of stars and other celestial objects in a matter of moments. Although this deluge of information is useful and reveals a great deal about the Universe, the wealth of data can be drastically unmanageable. That’s why NASA astronomers have turned to machines to help sort through thousands of stars in the Milky Way.

The new initiative falls under the science of machine learning, where computers are used to find patterns from large data sets, patterns that could easily be missed through human error.

Astronomers have begun using computers to identify basic properties of the stars in our galaxy like size and composition.

Instead of studying these properties through spectroscopy, the usual method, computers use algorithms to quickly identify patterns that reveal a star's properties.

"It's like video-streaming services not only predicting what you would like to watch in the future, but also your current age, based on your viewing preferences," said Adam Miller of NASA's Jet Propulsion Laboratory.

"We are predicting fundamental properties of the stars."

Although machine learning has been applied by astronomers in the past, this is the first time it has been used to predict common stellar traits.

So far the team have inputted spectra data and information on variable brightness for 9,000 stars recorded by the Sloan Digital Sky Survey into a supercomputer.

The computer was able to make predictions about other stars simply by examining the associations between the inputted stars properties and light curves, the name of the plots produced from the analysis of variable star brightness.

"We can discover and classify new types of stars without the need for spectra, which are expensive and time-consuming to obtain," said Miller.


Like this article? Why not:
Machines used to teach astronomers about stars
previous news Article
Magnetic storm on Comet Lovejoy
next news Article
We use cookies to improve your experience of our website. Cookies perform functions like recognising you each time you visit and delivering advertising messages that are relevant to you. Read more here