Researchers at Breakthrough Listen, a SETI (Search for Extraterrestrial Intelligence) project led by the University of California, Berkeley (UC Berkeley), used machine learning to discover 72 fast radio bursts from a mysterious source about 3 billion light years from Earth.
The algorithms identified radio signs in data recorded over a five-hour period on Aug. 26, 2017.
An earlier analysis of that 400 terabytes of data used standard computer algorithms to identify 21 bursts during that period. UC Berkeley researcher Gerry Zhang and his colleagues subsequently developed a machine learning algorithm and used it to reanalyze the 2017 data, finding an additional 72 bursts.
The new algorithm relies on some of the same techniques that Internet technology companies use to optimize search results and classify images.
Zhang said these findings are “only the beginning of using these powerful methods to find radio transients. We hope our success may inspire other serious endeavors in applying machine learning to radio astronomy.”
From University of California, Berkeley
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found