Data Science Investment Counter —Funding raised by UK data science companies in 2018.
£ 5.640 Million

Artificial intelligence bot trained to recognise galaxies

A new artificial intelligence program was trained by scientists at The University of Western Australia node of the International Centre for Radio Astronomy Research (ICRAR) to identify galaxies in deep space.

Fourteen radio galaxy predictions ClaRAN made during its scan of radio and infrared data. Credit: Dr Chen Wu and Dr Ivy Wong, ICRAR/UWA.

The AI bot is named ClaRAN, and it scans images taken by radio telescopes. It was previously used to recognise faces on Facebook, but scientists have reprogrammed it to work with galaxies.

ClaRAN’s main job is to spot radio galaxies, those galaxies emitting powerful radio jets from supermassive black holes at their centres.

Astronomer Dr Ivy Wong from ICRAR who worked on ClaRAN with big data specialist Dr Chen Wu said black holes are found at the centre of most galaxies.

“These supermassive black holes occasionally burp out jets that can be seen with a radio telescope”, she said.

“Over time, the jets can stretch a long way from their host galaxies, making it difficult for traditional computer programs to figure out where the galaxy is.

“That’s what we’re trying to teach ClaRAN to do.”

Dr Wong added the upcoming EMU survey using the WA-based Australian Square Kilometre Array Pathfinder (ASKAP) telescope is expected to find up to 70 million galaxies across the Universe, and that traditional computer algorithms are able to correctly identify 90 per cent of the sources.

“That still leaves 10 per cent, or seven million ‘difficult’ galaxies that have to be eyeballed by a human due to the complexity of their extended structures,” she said.

Dr Wong believes ClaRAN will have a huge impact on how telescope observations are processed.

“If we can start implementing these more advanced methods for our next generation surveys, we can maximise the science from them,” she said.

“There’s no point using 40-year-old methods on brand new data, because we’re trying to probe further into the Universe than ever before.”

Since ClaRAN was developed out of an open source version of Microsoft and Facebook’s object detection software, the program is open source and publicly available on GitHub.


Co-working space and blog dedicated to all things data science.

Subscribe to our newsletter