The researchers were able to use machine learning to improve the previously published image of a black hole photo taken in 2017. The result shows a portrait of the black hole at the center of the Messier 87 galaxy, 53 million light-years from Earth, with a thinner ring of light and matter surrounding its centre.
The original images were taken by the Event Horizon Telescope in 2017. The first image looked like a “blurred donut,” but the researchers used a new method called PRIMO to reconstruct a more accurate image.
PRIMO is a “new dictionary-learning-based algorithm that learns to recover high-fidelity images even in the presence of sparse coverage” by training on generated simulations of more than 30,000 black holes. In other words, it uses machine learning data based on what we know about the physical laws of the universe – and black holes in particular – to produce a better-looking and more accurate shot than raw data captured in 2017.
The researchers say the new image is consistent with Albert Einstein’s predictions, and they say that with advances in this area, in 20 years, the image could be different from the image that emerges today, and could be even better.
61088
