Machine learning enhances first-ever photo of a black hole

Researchers have used machine learning to improve the first photo of a black hole captured by the Event Horizon Telescope in 2017. The new method, called PRIMO, uses data based on what we know about the universe's physical laws to produce a more accurate image. The updated portrait of the black hole at the center of the galaxy Messier 87 shows a thinner ring of light and matter surrounding its center, consistent with Albert Einstein's predictions. The researchers expect further research in machine learning and telescope hardware to lead to additional revisions.