Classifying galaxies with artificial intelligence

Date:
August 11, 2020
Source:
National Institutes of Natural Sciences
Summary:
Astronomers have applied artificial intelligence (AI) to ultra-wide
field-of-view images of the distant Universe captured by the Subaru
Telescope, and have achieved a very high accuracy for finding
and classifying spiral galaxies in those images. This technique,
in combination with citizen science, is expected to yield further
discoveries in the future.



FULL STORY ========================================================================== Astronomers have applied artificial intelligence (AI) to ultra-wide
field-of- view images of the distant Universe captured by the Subaru
Telescope, and have achieved a very high accuracy for finding
and classifying spiral galaxies in those images. This technique,
in combination with citizen science, is expected to yield further
discoveries in the future.


==========================================================================
A research group, consisting of astronomers mainly from the National Astronomical Observatory of Japan (NAOJ), applied a deep-learning
technique, a type of AI, to classify galaxies in a large dataset of images obtained with the Subaru Telescope. Thanks to its high sensitivity, as
many as 560,000 galaxies have been detected in the images. It would be extremely difficult to visually process this large number of galaxies
one by one with human eyes for morphological classification. The AI
enabled the team to perform the processing without human intervention.

Automated processing techniques for extraction and judgment of
features with deep-learning algorithms have been rapidly developed
since 2012. Now they usually surpass humans in terms of accuracy and
are used for autonomous vehicles, security cameras, and many other applications. Dr. Ken-ichi Tadaki, a Project Assistant Professor at NAOJ,
came up with the idea that if AI can classify images of cats and dogs,
it should be able to distinguish "galaxies with spiral patterns" from
"galaxies without spiral patterns." Indeed, using training data prepared
by humans, the AI successfully classified the galaxy morphologies with
an accuracy of 97.5%. Then applying the trained AI to the full data set,
it identified spirals in about 80,000 galaxies.

Now that this technique has been proven effective, it can be extended
to classify galaxies into more detailed classes, by training the
AI on the basis of a substantial number of galaxies classified by
humans. NAOJ is now running a citizen-science project "GALAXY CRUISE,"
where citizens examine galaxy images taken with the Subaru Telescope to
search for features suggesting that the galaxy is colliding or merging
with another galaxy. The advisor of "GALAXY CRUISE," Associate Professor Masayuki Tanaka has high hopes for the study of galaxies using artificial intelligence and says, "The Subaru Strategic Program is serious Big Data containing an almost countless number of galaxies.

Scientifically, it is very interesting to tackle such big data with
a collaboration of citizen astronomers and machines. By employing
deep-learning on top of the classifications made by citizen scientists
in GALAXY CRUISE, chances are, we can find a great number of colliding
and merging galaxies."

========================================================================== Story Source: Materials provided by
National_Institutes_of_Natural_Sciences. Note: Content may be edited
for style and length.


========================================================================== Journal Reference:
1. Tomoka Tosaki, Rhythm Shimakawa, Cristian E Rusu, Masao Hayashi,
Hideya
Fukumoto, Masanori Iye, Ken-ichi Tadaki. Spin parity of spiral
galaxies II: a catalogue of 80 k spiral galaxies using
big data from the Subaru Hyper Suprime-Cam survey and deep
learning. Monthly Notices of the Royal Astronomical Society, 2020;
496 (4): 4276 DOI: 10.1093/mnras/ staa1880 ==========================================================================

Link to news story: https://www.sciencedaily.com/releases/2020/08/200811120120.htm

--- up 3 weeks, 6 days, 1 hour, 55 minutes
* Origin: -=> Castle Rock BBS <=- Now Husky HPT Powered! (1337:3/111)