Astronomers have trained Facebook’s facial recognition software to spot ‘burping’ black holes in deep space.
The artificial intelligence (AI) tool is programmed to pick out radio galaxies out from scans taken by radio telescopes.
These rare galaxies spew powerful radio jets from the supermassive black holes at their centres, and scientists believe they hold clues to the structure of the universe.
Using the new programme, dubbed ClaRAN, experts at the University of Western Australia hope to make it easier to spot the elusive galaxies – using the radio signals fired from their black holes.
‘These supermassive black holes occasionally burp out jets that can be seen with a radio telescope,’ said study lead author Dr Ivy Wong.
‘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.’
ClaRAN was built using an open source version of Microsoft and Facebook’s object detection software, which the latter firm uses to identify faces in your photos.
Dr Wong said the program was completely overhauled and trained to recognise galaxies instead of people.
It was fed a catalogue of thousands of images of radio galaxies picked out by human observers during previous galactic surveys.
Over time, the AI learned to spot the galaxies by recognising tiny shapes and patterns in survey data.
Study coauthor Dr Chen Wu said ClaRAN is an example of a new paradigm called ‘programming 2.0’.
‘All you do is set up a huge neural network, give it a ton of data, and let it figure out how to adjust its internal connections in order to generate the expected outcome,’ he said.
‘The new generation of programmers spend 99 per cent of their time crafting the best quality data sets and then train the AI algorithms to optimise the rest.
‘This is the future of programming.’
The upcoming EMU survey using the WA-based Australian Square Kilometre Array Pathfinder (ASKAP) telescope is expected to observe up to 70 million galaxies.
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,’ Dr Wong said.
Programmes like ClaRAN have huge implications for 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,’ Dr Wong 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.’