Nearly 400,000 spiral galaxies and 30,000 ring galaxies have been discovered in archival data from the Subaru Telescope, thanks to artificial intelligence and amateur astronomers.
by week
Galaxies display a wide range of shapes that reflect the history of individual galaxies. Datasets obtained from facilities such as the Subaru Telescope contain so many galaxies that astronomers cannot manually classify them all.
In a citizen science project called “Galaxy Cruise,” professional astronomers asked more than 10,000 volunteer citizen astronomers to make the classifications. But even divided among thousands of volunteers, classification still takes time, a Subaru Telescope statement said.
AI can make classifications quickly, but it first needs to be trained on a catalog of classification examples prepared by a human.
In this research, a team led by Rithem Shimakawa, an associate professor at Waseda University, trained AI on a set of 20,000 galaxies classified by humans as part of GALAXY CRUISE. The team then unleashed the AI on 700,000 galaxies in the Subaru Telescope's dataset.
The AI classified 400,000 of them as spiral galaxies, and 30,000 as ring galaxies. Although ring galaxies represent less than 5% of all galaxies, this research produced a large enough sample for useful statistical analysis.
To continue reading click here.
“Proud web fanatic. Subtly charming twitter geek. Reader. Internet trailblazer. Music buff.”
More Stories
The path of an asteroid the size of the Giza Pyramid worries scientists
The Sun is producing its biggest flare in nearly two decades, but Earth is supposed to be safe
NASA records the strongest solar flare in nearly two decades