A PhD student at the Australian National University has developed an artificial intelligence network capable of analyzing distant galaxies.
Researchers at the Australian National University have figured out how to use artificial intelligence to scan space for new galaxies. According to a university press release, the study, led by PhD student Elise Hamilton, showed how neural networks could be created to isolate the most turbulent and “messy” galaxies for study, offering insight into the long list of forces at play in the universe.
Hampton, who is currently a student at the ANU Research School of Astronomy and Astrophysics, said, “I love artificial intelligence. It was actually a very simple program to write, once I learned how. 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’s program looks for galaxies with turbulent and vibrant centers, powered by black holes and producing massive galactic wind gusts. “We believe these winds blow so much material out of the galaxies that they eventually starve themselves to death,” Hampton said.
Galactic winds can also lead to the formation of new stars. By studying these forces, Hampton’s work could lend new insights into the way galaxies form and die. The program helps distinguish between light from forming stars, matter being sucked into black holes, and supersonic winds.
The Artificial Neural Network created by Hampton is inspired by the human brain and is capable of learning and adapting to new data. The program is able to analyze galaxies using roughly 4,000 spectra that had previously been studied by other astrophysicists.