00:04this is the first image of a black hole ever taken captured only back in 2019 the image of
00:09black hole m87 was taken by the event horizon telescope and at the time was an epic moment in
00:15astronomy but now using machine learning ai researchers just made that very image even
00:20sharper this is the new and improved version of the 2019 picture upscaled by an algorithm called
00:25primo or the principal component interferomatic modeling program getting images of black holes is
00:30difficult for a multitude of reasons not least of which is that they gobble up anything that passes
00:35over their event horizons even light but even the closest black holes are over a thousand light years
00:40away in fact this one housed in the messier 87 galaxy is 55 million light years away though the one
00:46advantage astronomers have in finding black holes is their size in the case of m87 it's 6.5 billion
00:52times the mass of our sun which is not only how experts were able to detect it but also how
00:57the
00:57machine learning was able to fill in the gaps and transform the image the ai was trained using some
01:0230 000 images of simulated black holes allowing it to work out different patterns to find the one that
01:07would fit just right for m87 with one of the astrophysicists working on the project saying
01:11about it quote if a picture is worth a thousand words the data underlying that image have many more
01:16stories to tell primo will continue to be a critical tool in extracting such insights
01:21you
01:24you
Comments