Giving black hole researchers a clearer view
55 million light years from Earth
Researchers have developed a new machine-learning technique , known as PRIMO , to enhance the fidelity and sharpness of radio interferometry images . The purpose ? Creating a new , high-fidelity version of the Event Horizon Telescope ' s iconic image of the supermassive black hole at the centre of Messier 87 , a giant elliptical galaxy located 55 million lightyears from Earth .
Building on the image taken in 2017 by the Event Horizon Telescope , PRIMO relies on a branch of machine learning known as dictionary learning , which teaches computers certain rules by exposing them to thousands of examples .
“ With our new machine-learning technique , PRIMO , we were able to achieve the maximum resolution of the current array ,” said lead author Lia Medeiros .
EHT with PRIMO aimagazine . com 15