Astronomers are now using artificial intelligence to detect mysterious fast radio bursts coming from outer space.
The technology was developed by Wael Farah, a doctoral student at Australia’s Swinburne University of Technology.
Fast radio bursts (FRB) are brief pulses of radio waves coming from far outside our Milky Way galaxy, flaring with the power of about 500 million suns. They last only a few milliseconds and are thought to originate billions of light years from Earth.
Most FRBs detected only appear once, and astronomers have discovered about 85 since 2007.
Farah’s system has already identified five bursts, including one of the most energetic ever detected. Farah taught his on-site computer at the Molonglo Radio Observatory near Canberra, Australia, to recognize the signs and signatures of FRBs, and so far his system has produced high quality data.
The FRBs were found as part of the UTMOST FRB search program – a joint collaboration between Swinburne and the University of Sydney.
“Wael has used machine learning on our high-performance computing cluster to detect and save FRBs from amongst millions of other radio events, such as mobile phones, lightning storms, and signals from the Sun and from pulsars,” Molonglo project scientist Chris Flynn told the university website.