Artificial intelligence allowed researchers to peer deep into the hearts of distant galaxies.
A researcher took inspiration from neural networks, and wrote a program that could find the most "messy" and turbulent galaxies out of a sample of thousands, the Australian National University reported. The Artificial Neural Networks are a group of computer programs inspired by the brain. They rely on an interconnected set of individual processors, similar to neurons.
"I love artificial intelligence. It was actually a very simple program to write, once I [learned] how," saud PhD student Elise Hampton, who is studying at the ANU Research School of Astronomy and Astrophysics. "The program took eight minutes to [analyze] 300,000 data points from 1,188 galaxies. For one person to do it would have taken years."
Hampton is focusing on galaxies that are characterized by brightly glowing centers driven by massive black holes, which emit powerful galactic winds.
"We believe these winds blow so much material out of the galaxies that they eventually starve themselves to death," she said.
Galactic winds can trigger the formation of new stars, so Hampton hopes to gain insight into the processes that work in these galaxies to influence stellar births and deaths. In order to study these messy galaxies, researchers must distinguish between different light spectra within them. These observations can reveal phenomena such as matter falling into black holes and supersonic galactic winds. In the past this process has been extremely tedious, but artificial intelligence could help solve the problem.
The findings were presented at the 25th Astronomical Data Analysis Software and Systems Conference.
