Astronomers Utilize AI to Unravel the Mysteries of Black Holes
While we may not have telescopes that can reveal all the mysteries of supermassive black holes just yet, AI is stepping in to help. Recently, an international collaboration of astronomers successfully trained a neural network using millions of black hole simulations, enabling it to decode unclear data captured from these fascinating cosmic objects in real-time.
Among the various techniques used to study black holes, the Event Horizon Telescope (EHT) stands out as the most renowned. The EHT is not a single telescope but a network of radio telescopes scattered worldwide that function together as a unified instrument. This collaboration has made it possible to capture images of the supermassive black holes M87 and Sagittarius A*. These images are not traditional photographs but rather visual representations of the radio waves emitted by the black holes.
To generate these images, supercomputers located in different regions processed the radio signals collected by the EHT. However, a significant amount of the gathered data was discarded because it was challenging to interpret. The newly developed neural network, trained by specialists at the Morgridge Research Institute in Wisconsin, aims to harness this wealth of data to enhance the EHT’s readings and facilitate new discoveries.
According to a press release from the institute, the AI successfully reanalyzed the previously discarded information, setting new parameters for Sagittarius A*, the black hole at the heart of the Milky Way. An alternative visualization of the black hole’s structure was produced, uncovering new features of this cosmic entity.
“Researchers now suspect that the black hole at the center of the Milky Way is rotating at nearly maximum speed,” the researchers stated in the press release. The new image also suggests that the rotation axis of the black hole is aligned with Earth and provides insights into the materials orbiting around the black hole.
Previously, astronomers estimated that Sagittarius A* rotates at a moderate to fast pace. Determining its actual rotational speed is crucial, as it helps us understand the behavior of the radiation surrounding the black hole and gives insights into its stability.
“It’s thrilling that we are challenging the existing theories,” said lead researcher Michael Janssen from Radboud University Nijmegen in the Netherlands, in the press release. “However, I view our AI and machine learning method primarily as an initial step. Our next goal will be to refine and expand the related models and simulations.”
This story originally appeared on WIRED en Español and has been translated from Spanish.
