Machine Learning :
Machine learning is in everything from media streaming services that predict what you want to watch, to the post office, where computers automatically read handwritten address and direct mail to the correct zip codes.
Earlier :
Machine learning has applied to the Cosmos before; what makes this latest effort unique is that it is the 1st to predict specific traits of stars, such as size and metal content. These traits are essential to learning about when a star was born & how it has changed since that time.
Need of Machine Learning :
Now astronomers are turning to machines to help them identify basic properties of stars based on sky survey images. Normally, these kinds of details require a spectrum, which is detailed sifting of starlight into different wavelengths. But, with machine learning, computer algorithms can quickly flip through available stacks of images, properties of stars with more information and short time and with less expensive.
Large Synoptic Survey Telescope :
Every night, telescope around the world obtain 1000's of images of the sky. The flood of new data is only expected to rise with upcoming wide field surveys like the Large Synoptic Survey Telescope ( LSST ), a National Science Foundation and Department of Energy project that will be based in Chile.
The Survey will image the entire visible sky every few nights, gathering data on billions of stars and how some of those stars change in brightness overtime.
Humans can't easily make sense of all this data. That is where machines, or in this case, computers using specialized algorithms can help out.
Training Period :
Before the machines can learn, scientists need a training period. Scientists started with 9000 stars as their training set. They obtained spectra for these stars, which revealed several of their basic properties....
Stars
Temperature
Heavy elements ( iron )
The varying brightness of stars had also been recorded by the Sloan Digital Sky survey, producing plots called " light curves ". By feeding the computer both sets of data, it could then make associations between the star properties and the light curves.
Scientists can discover and classify new types of stars without need of spectra, which are expensive and time consuming to obtain.
Comparison :
The technique essentially works in same way as Email Spam Filters. The spam filters are programmed to identify keywords associated with junk mail, and then remove the unwanted emails containing those words.
Similar way, the machine learning program becomes better at accurately predicting properties of the stars with addnl training from astronomers.
Goal :
The team's next goal is to get those computers smart enough to handle the more than 50 million variable stars that the LSST project will observe.
Adam Miller's Words :
He is the lead author of NASA's Jet Propulsion Laboratory in Pasadena, California.
He said, " With more information about the different kinds of stars in our Milkyway Galaxy, we can better map the Galaxy's Structure and History. This is exciting time to be applying advanced algorithms to astronomy ".
Final Words....!!!!
If you've any ideas... You can directly contact to the scientist. You can see the details below...
Whitney Clavin
Jet propulsion laboratory, Pasadena,
California.
Contact no: 818-354-4673
Email : whitney.clavin@jpl.nasa.gov