To explore the farthest reaches of the Milky Way and uncover the secrets of star formation, a Japanese research team has developed a deep learning model. Led by Osaka Metropolitan University, the team used artificial intelligence to analyze large amounts of data from space telescopes. Their efforts revealed bubble-like structures that had previously been overlooked in astronomical databases.
Like other galaxies, the Milky Way has these bubble-like structures that appear primarily during the birth and activity of massive stars. These structures are called "Spitzerbubbles" and they provide valuable information about how galaxies form and how stars form.
Graduate student Shimpei Nishimoto and professor Toshikazu Onishi worked with researchers from institutions across Japan to create an artificial intelligence model to detect these bubbles more effectively. By analyzing images from the Spitzer Space Telescope and the James Webb Space Telescope, their model accurately identified the Spitzer Bubble, a shell-like structure believed to have been created by a supernova explosion.
"Our results show that not only star formation but also the effects of explosive events within galaxies can be studied in detail," said graduate student Nishimoto.
Professor Onishi added: "In the future, we hope that advances in artificial intelligence technology will accelerate the elucidation of the mechanisms of galaxy evolution and star formation."
Compiled from /ScitechDaily