The updated image retains its original shape, but with a thinner frame and sharper resolution (Photo: AFP)

The first photo of a Black Hole taken four years ago showed a fuzzy, fiery doughnut-shaped object.

Now researchers have used artificial intelligence to give this cosmic beauty a touch-up.

The updated photo, published in the Astrophysical Journal Letters on Thursday, retains the original shape, but with a thinner border and sharper resolution.

The image, released in 2019, gave a glimpse of the massive black hole at the center of the M87 galaxy, 53 million light-years from Earth. For comparison, a light-year is 5.8 trillion miles.

The black hole was captured by the Event Horizon Telescope Collaboration (EHT), a large number of telescopes around the planet synchronized to work together.

Researchers used artificial intelligence to enhance cosmic beauty (Photo: AFP)

But even as many telescopes worked together, data gaps remained.

In the latest study, scientists drew from the same data and used machine learning to fill in the missing pieces.

The resulting photo is similar to the original, but with a thinner “doughnut” and a darker center, the researchers said.

“To me, it feels like we’re really seeing it for the first time,” said lead author Lia Medeiros, an astrophysicist at the Institute for Advanced Study in New Jersey, USA.

She said the team plans to use machine learning for other images of celestial bodies, which may include the black hole at the center of our Milky Way galaxy.

One of the largest and brightest in the known universe, the M87 galaxy is 53.49 million light-years from Earth. It is notable for firing a fast beam of charged subatomic particles that spans about 5,000 light-years, making it the perfect target for the EHT project.

Although the telescopes that make up the EHT are not physically connected, they can synchronize their recorded data with atomic clocks that precisely time their observations.