skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Galaxy morphology prediction using Capsule Networks

Abstract

Abstract Understanding morphological types of galaxies is a key parameter for studying their formation and evolution. Neural networks that have been used previously for galaxy morphology classification have some disadvantages, such as not being inherently invariant under rotation. In this work, we studied the performance of Capsule Network (CapsNet), a recently introduced neural network architecture that is rotationally invariant and spatially aware, on the task of galaxy morphology classification. We designed two evaluation scenarios based on the answers from the question tree in the Galaxy Zoo project. In the first scenario, we used CapsNet for regression and predicted probabilities for all of the questions. In the second scenario, we chose the answer to the first morphology question that had the highest user agreement as the class of the object and trained a CapsNet classifier, where we also reconstructed galaxy images. We achieved promising results in both of these scenarios. Automated approaches such as the one introduced here will play a critical role in the upcoming large sky surveys.

Authors:
ORCiD logo [1];  [2];  [1];  [3]
  1. Astrophysical Institute, Department of Physics and Astronomy, Ohio University, Athens, OH 45701, USA
  2. Department of Chemistry and Biochemistry, Ohio University, Athens, OH 45701, USA
  3. School of Electrical Engineering and Computer Science, Ohio University, Athens, OH 45701, USA
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
1507230
Resource Type:
Published Article
Journal Name:
Monthly Notices of the Royal Astronomical Society
Additional Journal Information:
Journal Name: Monthly Notices of the Royal Astronomical Society Journal Volume: 486 Journal Issue: 2; Journal ID: ISSN 0035-8711
Publisher:
Oxford University Press
Country of Publication:
United Kingdom
Language:
English

Citation Formats

Katebi, Reza, Zhou, Yadi, Chornock, Ryan, and Bunescu, Razvan. Galaxy morphology prediction using Capsule Networks. United Kingdom: N. p., 2019. Web. doi:10.1093/mnras/stz915.
Katebi, Reza, Zhou, Yadi, Chornock, Ryan, & Bunescu, Razvan. Galaxy morphology prediction using Capsule Networks. United Kingdom. doi:10.1093/mnras/stz915.
Katebi, Reza, Zhou, Yadi, Chornock, Ryan, and Bunescu, Razvan. Mon . "Galaxy morphology prediction using Capsule Networks". United Kingdom. doi:10.1093/mnras/stz915.
@article{osti_1507230,
title = {Galaxy morphology prediction using Capsule Networks},
author = {Katebi, Reza and Zhou, Yadi and Chornock, Ryan and Bunescu, Razvan},
abstractNote = {Abstract Understanding morphological types of galaxies is a key parameter for studying their formation and evolution. Neural networks that have been used previously for galaxy morphology classification have some disadvantages, such as not being inherently invariant under rotation. In this work, we studied the performance of Capsule Network (CapsNet), a recently introduced neural network architecture that is rotationally invariant and spatially aware, on the task of galaxy morphology classification. We designed two evaluation scenarios based on the answers from the question tree in the Galaxy Zoo project. In the first scenario, we used CapsNet for regression and predicted probabilities for all of the questions. In the second scenario, we chose the answer to the first morphology question that had the highest user agreement as the class of the object and trained a CapsNet classifier, where we also reconstructed galaxy images. We achieved promising results in both of these scenarios. Automated approaches such as the one introduced here will play a critical role in the upcoming large sky surveys.},
doi = {10.1093/mnras/stz915},
journal = {Monthly Notices of the Royal Astronomical Society},
number = 2,
volume = 486,
place = {United Kingdom},
year = {2019},
month = {4}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
DOI: 10.1093/mnras/stz915

Citation Metrics:
Cited by: 3 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Rotation-invariant convolutional neural networks for galaxy morphology prediction
journal, April 2015

  • Dieleman, Sander; Willett, Kyle W.; Dambre, Joni
  • Monthly Notices of the Royal Astronomical Society, Vol. 450, Issue 2
  • DOI: 10.1093/mnras/stv632

Galaxies, Human Eyes, and Artificial Neural Networks
journal, February 1995


Combining Human and Machine Learning for Morphological Analysis of Galaxy Images
journal, October 2014

  • Kuminski, Evan; George, Joe; Wallin, John
  • Publications of the Astronomical Society of the Pacific, Vol. 126, Issue 944
  • DOI: 10.1086/678977

Machine learning and image analysis for morphological galaxy classification
journal, March 2004


Automated morphological classification of APM galaxies by supervised artificial neural networks
journal, August 1995

  • Naim, A.; Lahav, O.; Sodre, L.
  • Monthly Notices of the Royal Astronomical Society, Vol. 275, Issue 3
  • DOI: 10.1093/mnras/275.3.567

Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
journal, June 2017

  • Blanton, Michael R.; Bershady, Matthew A.; Abolfathi, Bela
  • The Astronomical Journal, Vol. 154, Issue 1
  • DOI: 10.3847/1538-3881/aa7567

Galaxy Zoo: morphological classifications for 120 000 galaxies in HST legacy imaging
journal, October 2016

  • Willett, Kyle W.; Galloway, Melanie A.; Bamford, Steven P.
  • Monthly Notices of the Royal Astronomical Society, Vol. 464, Issue 4
  • DOI: 10.1093/mnras/stw2568

ANN z : Estimating Photometric Redshifts Using Artificial Neural Networks
journal, April 2004

  • Collister, Adrian A.; Lahav, Ofer
  • Publications of the Astronomical Society of the Pacific, Vol. 116, Issue 818
  • DOI: 10.1086/383254

Galaxy Zoo: an independent look at the evolution of the bar fraction over the last eight billion years from HST-COSMOS★
journal, January 2014

  • Melvin, Thomas; Masters, Karen; Lintott, Chris
  • Monthly Notices of the Royal Astronomical Society, Vol. 438, Issue 4
  • DOI: 10.1093/mnras/stt2397

Galaxy Zoo: reproducing galaxy morphologies via machine learning★: Galaxy Zoo: morphology via machine learning
journal, April 2010


Galaxy And Mass Assembly (GAMA): understanding the wavelength dependence of galaxy structure with bulge-disc decompositions
journal, May 2016

  • Kennedy, Rebecca; Bamford, Steven P.; Häußler, Boris
  • Monthly Notices of the Royal Astronomical Society, Vol. 460, Issue 4
  • DOI: 10.1093/mnras/stw1176

LSST: From Science Drivers to Reference Design and Anticipated Data Products
journal, March 2019

  • Ivezić, Željko; Kahn, Steven M.; Tyson, J. Anthony
  • The Astrophysical Journal, Vol. 873, Issue 2
  • DOI: 10.3847/1538-4357/ab042c

Galaxy Zoo: evidence for diverse star formation histories through the green valley
journal, April 2015

  • Smethurst, R. J.; Lintott, C. J.; Simmons, B. D.
  • Monthly Notices of the Royal Astronomical Society, Vol. 450, Issue 1
  • DOI: 10.1093/mnras/stv161

Improving galaxy morphologies for SDSS with Deep Learning
journal, February 2018

  • Domínguez Sánchez, H.; Huertas-Company, M.; Bernardi, M.
  • Monthly Notices of the Royal Astronomical Society, Vol. 476, Issue 3
  • DOI: 10.1093/mnras/sty338

A Catalog of Visual-Like Morphologies in the 5 Candels Fields Using deep Learning
journal, October 2015

  • Huertas-Company, M.; Gravet, R.; Cabrera-Vives, G.
  • The Astrophysical Journal Supplement Series, Vol. 221, Issue 1
  • DOI: 10.1088/0067-0049/221/1/8

Estimating photometric redshifts with artificial neural networks
journal, March 2003

  • Firth, Andrew E.; Lahav, Ofer; Somerville, Rachel S.
  • Monthly Notices of the Royal Astronomical Society, Vol. 339, Issue 4
  • DOI: 10.1046/j.1365-8711.2003.06271.x

Detailed Structural Decomposition of Galaxy Images
journal, July 2002

  • Peng, Chien Y.; Ho, Luis C.; Impey, Chris D.
  • The Astronomical Journal, Vol. 124, Issue 1
  • DOI: 10.1086/340952

Galaxy Zoo: the dependence of morphology and colour on environment
journal, March 2009

  • Bamford, Steven P.; Nichol, Robert C.; Baldry, Ivan K.
  • Monthly Notices of the Royal Astronomical Society, Vol. 393, Issue 4
  • DOI: 10.1111/j.1365-2966.2008.14252.x

Galaxy types in the Sloan Digital Sky Survey using supervised artificial neural networks
journal, March 2004


Galaxy Zoo 2: detailed morphological classifications for 304 122 galaxies from the Sloan Digital Sky Survey
journal, September 2013

  • Willett, Kyle W.; Lintott, Chris J.; Bamford, Steven P.
  • Monthly Notices of the Royal Astronomical Society, Vol. 435, Issue 4
  • DOI: 10.1093/mnras/stt1458

Deep Recurrent Neural Networks for Supernovae Classification
journal, March 2017


Exploring galaxy evolution with generative models
journal, August 2018


Morphological Classification of galaxies by Artificial Neural Networks
journal, November 1992

  • Storrie-Lombardi, M. C.; Lahav, O.; Sodre, L.
  • Monthly Notices of the Royal Astronomical Society, Vol. 259, Issue 1
  • DOI: 10.1093/mnras/259.1.8P

Galaxy Zoo: morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
journal, September 2008

  • Lintott, Chris J.; Schawinski, Kevin; Slosar, Anže
  • Monthly Notices of the Royal Astronomical Society, Vol. 389, Issue 3
  • DOI: 10.1111/j.1365-2966.2008.13689.x