Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks

Cheng, Ting-Yun; Conselice, Christopher J; Aragón-Salamanca, Alfonso; Aguena, M; Allam, S; Andrade-Oliveira, F; Annis, J; Bluck, A F L; Brooks, D; Burke, D L; Kind, M Carrasco; Carretero, J; Choi, A; Costanzi, M; da Costa, L N; Pereira, M E S; De Vicente, J; Diehl, H T; Drlica-Wagner, A; Eckert, K; Everett, S; Evrard, A E; Ferrero, I; Fosalba, P; Frieman, J; García-Bellido, J; Gerdes, D W; Giannantonio, T; Gruen, D; Gruendl, R A; Gschwend, J; Gutierrez, G; Hinton, S R; Hollowood, D L; Honscheid, K; James, D J; Krause, E; Kuehn, K; Kuropatkin, N; Lahav, O; Maia, M A G; March, M; Menanteau, F; Miquel, R; Morgan, R; Paz-Chinchón, F; Pieres, A; Malagón, A A Plazas; Roodman, A; Sanchez, E; Scarpine, V; Serrano, S; Sevilla-Noarbe, I; Smith, M; Soares-Santos, M; Suchyta, E; Swanson, M E C; Tarle, G; Thomas, D; To, C

Abstract

We present in this paper one of the largest galaxy morphological classification catalogues to date, including over 20 million of galaxies, using the Dark Energy Survey (DES) Year 3 data based on Convolutional Neural Networks (CNN). Monochromatic i-band DES images with linear, logarithmic, and gradient scales, matched with debiased visual classifications from the Galaxy Zoo 1 (GZ1) catalogue, are used to train our CNN models. With a training set including bright galaxies (16 ≤ i < 18) at low redshift (z < 0.25), we furthermore investigate the limit of the accuracy of our predictions applied to galaxies at fainter magnitude and at higher redshifts. Our final catalogue covers magnitudes 16 ≤ i < 21, and redshifts z < 1.0, and provides predicted probabilities to two galaxy types – Ellipticals and Spirals (disk galaxies). Our CNN classifications reveal an accuracy of over 99% for bright galaxies when comparing with the GZ1 classifications (i < 18). For fainter galaxies, the visual classification carried out by three of the co-authors shows that the CNN classifier correctly categorises disky galaxies with rounder and blurred features, which humans often incorrectly visually classify as Ellipticals. As a part of the validation, we carry out one of the largest examination of non-parametric methods, including ∼100,000 galaxies with the same coverage of magnitude and redshift as the training set from our catalogue. We find that the Gini coefficient is the best single parameter discriminator between Ellipticals and Spirals for this data set.

Citation

Cheng, T.-Y., Conselice, C. J., Aragón-Salamanca, A., Aguena, M., Allam, S., Andrade-Oliveira, F., Annis, J., Bluck, A. F. L., Brooks, D., Burke, D. L., Kind, M. C., Carretero, J., Choi, A., Costanzi, M., da Costa, L. N., Pereira, M. E. S., De Vicente, J., Diehl, H. T., Drlica-Wagner, A., Eckert, K., …To, C. (2021). Galaxy Morphological Classification Catalogue of the Dark Energy Survey Year 3 data with Convolutional Neural Networks. Monthly Notices of the Royal Astronomical Society, 507(3), 4425-4444. https://doi.org/10.1093/mnras/stab2142

• Journal Article Type: Article
• Acceptance Date: Jul 22, 2021
• Online Publication Date: Jul 24, 2021
• Publication Date: 2021-11
• Deposit Date: Jul 26, 2021
• Publicly Available Date: Jul 26, 2021
• Journal: Monthly Notices of the Royal Astronomical Society
• Print ISSN: 0035-8711
• Electronic ISSN: 1365-2966
• Publisher: Oxford University Press
• Peer Reviewed: Peer Reviewed
• Volume: 507
• Issue: 3
• Pages: 4425-4444
• DOI: https://doi.org/10.1093/mnras/stab2142
• Keywords: Space and Planetary Science; Astronomy and Astrophysics
• Public URL: https://nottingham-repository.worktribe.com/output/5833143
• Publisher URL: https://academic.oup.com/mnras/article/507/3/4425/6327560
• Additional Information: This article has been accepted for publication in Monthly Notices of the Royal Astronomical Society ©The Author(s) 2021.; Published by Oxford University Press on behalf of Royal Astronomical Society. All rights reserved.