The AI bot named “ClaRAN” spots radio galaxies that emit radio jets from supermassive black holes.
A team of researchers have taught an Artificial Intelligence (AI) programme — that used to recognise faces on Facebook — to identify galaxies in deep space. The AI bot named “ClaRAN” scans images taken by radio telescopes. Its job is to spot radio galaxies — galaxies that emit powerful radio jets from supermassive black holes at their centres. ClaRAN is the brainchild of big data specialist Dr Chen Wu and astronomer Dr Ivy Wong from The University of Western Australia node of the International Centre for Radio Astronomy Research (ICRAR). [caption id=“attachment_4272145” align=“alignnone” width=“1280”]![The collision of two black holes - a tremendously powerful event detected for the first time ever by the Laser Interferometer Gravitational-Wave Observatory, or LIGO - is seen in this still image from a computer simulation released in Washington February 11, 2016. Scientists have for the first time detected gravitational waves, ripples in space and time hypothesized by Albert Einstein a century ago, in a landmark discovery announced on Thursday that opens a new window for studying the cosmos. REUTERS/The SXS (Simulating eXtreme Spacetimes)/Handout via Reuters FOR EDITORIAL USE ONLY. NOT FOR SALE FOR MARKETING OR ADVERTISING CAMPAIGNS. THIS IMAGE HAS BEEN SUPPLIED BY A THIRD PARTY. IT IS DISTRIBUTED, EXACTLY AS RECEIVED BY REUTERS, AS A SERVICE TO CLIENTS TPX IMAGES OF THE DAY - GF10000304971]()
The collision of two black holes. Image: Reuters[/caption] Black holes are found at the centre of most, if not all, galaxies. “These supermassive black holes occasionally burp out jets that can be seen with a radio telescope,” said Dr Wong. “Over time, the jets can stretch a long way from their host galaxies, making it difficult for traditional computer programmes to figure out where the galaxy is. That’s what we’re trying to teach ClaRAN to do,” she added. “ClaRAN” grew out of an open source version of Microsoft and Facebook’s object detection software, said Dr Wu, adding that the programme was overhauled and trained to recognise galaxies instead of people. ClaRAN itself is an open source and publicly available on Microsoft-owned GitHub. Traditional computer algorithms are able to correctly identify 90 per cent of the sources. “That still leaves 10 percent or seven million ‘difficult’ galaxies that have to be eyeballed by a human due to the complexity of their extended structures,” Dr Wong said. “If ClaRAN reduces the number of sources that require visual classification down to one per cent, this means more time for our citizen scientists to spend looking at new types of galaxies,” she added in a paper published in the journal Monthly Notices of the Royal Astronomical Society. “ClaRAN” has huge implications for how telescope observations are processed.
- Home
- Tech
- science
- Reseachers train AI bot to identify galaxies in deep space through image scans
 "Reseachers train AI bot to identify galaxies in deep space through image scans")
 "US ready to ‘impose costs’ on Russia if war in Ukraine drags on, says Hegseth")
 "US tells Hamas to stop violence against Gaza civilians and disarm 'without delay'")
 "China seizes 60,000 maps mislabelling Taiwan, omitting South China Sea islands")
 "Syria’s Sharaa pledges to honor Russia ties, seeks economic and military support in Kremlin visit")
 "US ready to ‘impose costs’ on Russia if war in Ukraine drags on, says Hegseth")
 "US tells Hamas to stop violence against Gaza civilians and disarm 'without delay'")
 "China seizes 60,000 maps mislabelling Taiwan, omitting South China Sea islands")
 "Syria’s Sharaa pledges to honor Russia ties, seeks economic and military support in Kremlin visit")
