The interstellar clouds of distant, ancient galaxies are often filled with carbon. That means, if astronomers can track down and detect these bits of carbon, which they call neutral carbon absorbers, they can learn a lot about how galaxies evolve.
However, actually detecting neutral carbon absorbers—a process that usually involves finding the signature fingerprint of carbon absorption lines in the spectrum of light emitted by a galaxy—is tedious. It is also very difficult. Out of millions of galaxies, astronomers know only a few dozen that contain these absorbers.
Connected: Machine learning can help track down alien technology. Here’s how
Sounds like a job for AI. Or, to be more precise, it sounds like a job for a deep neural network.
Specifically, researchers recently put a neural network to work on spectroscopic galaxy data taken more than a decade ago—and discovered more than a hundred new galaxies with neutral carbon absorbers.
How did they do this? Well, before you can use a neural network, you need to train it first. Unfortunately, as we have discussed, there are not enough carbon neutral dampers known to do this adequately. So instead of using real data, the researchers generated a set of 5 million fictitious spectra and used them to teach the neural network what to look for: patterns often too subtle for the human eye to spot.
The researchers then fitted their neural network to the data from Sloan Digital Sky Survey III. When they did this, they pointed to neutral carbon absorbers in 107 galaxies that were not previously known to have these characteristics.
Where do we go from here?
Carbon is an indicator of a certain stage of galactic evolution. Its presence indicates that a galaxy has undergone rapid changes and produced many elements heavier than hydrogen or helium. It is possible, these researchers believe, that the presence of carbon in a galaxy could indicate the development of a disk similar to the Milky Way. And the newly identified carbon-containing galaxies date back to about 10.8 billion years ago—relatively early in the history of the universe—which makes this fact quite interesting.
In many ways, astronomy is an ideal field to seek the help of AI methods. Astronomers now find themselves dealing with huge mountains of data; It’s too much for humans to analyze in any reasonable timeframe – let alone analyze in a way that can find the very small patterns they ever need.
“It is necessary to develop innovative AI algorithms that can quickly, accurately and comprehensively explore rare and weak signals in massive astronomical data,” he said. Jian Gean astronomer at the Shanghai Astronomical Observatory of China, in a statement.
The authors published their work May 14 in the journal Monthly Notices of the Royal Astronomical Society.
#finds #hidden #data #galactic #evolution #galaxies #Heres
Image Source : www.space.com