Communications of the ACM
Face Recognition for Galaxies: Artificial Intelligence Brings New Tools to Astronomy
University of California, Santa Cruz researchers used computer simulations of galaxy formation to train a deep learning algorithm, which then proved surprisingly good at analyzing images of galaxies from the Hubble Space Telescope.
Credit: Greg Snyder, Space Telescope Science Institute
University of California, Santa Cruz researchers used computer simulations of galaxy formation to train a deep learning algorithm, which analyzed images of galaxies from the Hubble Space Telescope.
The researchers used the simulations to create mock images of simulated galaxies as they would look in observations by the Hubble Space Telescope. The mock images were used to train the deep learning system to recognize three key phases of galaxy evolution previously identified in the simulations.
The researchers then gave the system a large set of actual Hubble images to classify. The results showed a high level of consistency in the neural network's classifications of simulated and real galaxies.
The researchers used state-of-the-art galaxy simulations developed with an international team of collaborators from the University of Heidelberg and Hebrew University.
Deep learning has the potential to reveal aspects of the observational data that humans cannot see, the researchers say.
From University of California, Santa Cruz
View Full Article
Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA
No entries found