Optimizing automatic morphological classification of galaxies with machine learning and deep learning using Dark Energy Survey imaging
- Cheng, Ting-Yun ORCID School of Physics and Astronomy, The University of Nottingham, University Park, Nottingham NG7 2RD, UK
- Conselice, Christopher J School of Physics and Astronomy, The University of Nottingham, University Park, Nottingham NG7 2RD, UK
- Aragón-Salamanca, Alfonso School of Physics and Astronomy, The University of Nottingham, University Park, Nottingham NG7 2RD, UK
- Li, Nan School of Physics and Astronomy, The University of Nottingham, University Park, Nottingham NG7 2RD, UK
- Bluck, Asa F L Kavli Institute for Cosmology, The University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK
- Hartley, Will G Department of Physics, ETH Zurich, Wolfgang-Pauli-Strasse 16, CH-8093 Zurich, Switzerland
- Annis, James Fermi National Accelerator Laboratory, P.O. Box 500, Batavia, IL 60510, USA
- Brooks, David Department of Physics & Astronomy, University College London, Gower Street, London WC1E 6BT, UK
- Doel, Peter Department of Physics & Astronomy, University College London, Gower Street, London WC1E 6BT, UK
- García-Bellido, Juan Instituto de Fisica Teorica UAM/CSIC, Universidad Autonoma de Madrid, E-28049 Madrid, Spain
- James, David J Harvard-Smithsonian Center for Astrophysics, Cambridge, MA 02138, USA
- Kuehn, Kyler Australian Astronomical Optics, Macquarie University, North Ryde NSW 2113, Australia
- Kuropatkin, Nikolay Fermi National Accelerator Laboratory, P.O. Box 500, Batavia, IL 60510, USA
- Smith, Mathew ORCID School of Physics and Astronomy, University of Southampton, Southampton SO17 1BJ, UK
- Sobreira, Flavia Laboratório Interinstitucional de e-Astronomia – LIneA, Rua Gal. José Cristino 77, Rio de Janeiro, RJ-20921-400, Brazil
- Tarle, Gregory Department of Physics, University of Michigan, Ann Arbor, MI 48109, USA
- 2020-2-19
Published in:
- Monthly Notices of the Royal Astronomical Society. - Oxford University Press (OUP). - 2020, vol. 493, no. 3, p. 4209-4228
English
ABSTRACT
There are several supervised machine learning methods used for the application of automated morphological classification of galaxies; however, there has not yet been a clear comparison of these different methods using imaging data, or an investigation for maximizing their effectiveness. We carry out a comparison between several common machine learning methods for galaxy classification [Convolutional Neural Network (CNN), K-nearest neighbour, logistic regression, Support Vector Machine, Random Forest, and Neural Networks] by using Dark Energy Survey (DES) data combined with visual classifications from the Galaxy Zoo 1 project (GZ1). Our goal is to determine the optimal machine learning methods when using imaging data for galaxy classification. We show that CNN is the most successful method of these ten methods in our study. Using a sample of ∼2800 galaxies with visual classification from GZ1, we reach an accuracy of ∼0.99 for the morphological classification of ellipticals and spirals. The further investigation of the galaxies that have a different ML and visual classification but with high predicted probabilities in our CNN usually reveals the incorrect classification provided by GZ1. We further find the galaxies having a low probability of being either spirals or ellipticals are visually lenticulars (S0), demonstrating that supervised learning is able to rediscover that this class of galaxy is distinct from both ellipticals and spirals. We confirm that ∼2.5 per cent galaxies are misclassified by GZ1 in our study. After correcting these galaxies’ labels, we improve our CNN performance to an average accuracy of over 0.99 (accuracy of 0.994 is our best result).
- Language
-
- English
- Open access status
- green
- Identifiers
-
- DOI 10.1093/mnras/staa501
- ISSN 0035-8711
- Persistent URL
- https://sonar.ch/global/documents/66731
Statistics
Document views: 36
File downloads:
- Full-text: 0