Optimizing automatic morphological classification of galaxies with machine learning and deep learning using Dark Energy Survey imaging

Cheng, Ting-Yun; Conselice, Christopher J.; Arag�n-Salamanca, Alfonso; Li, Nan; Bluck, Asa F.L.; Hartley, Will G.; Annis, James; Brooks, David; Doel, Peter; Garc�a-Bellido, Juan; James, David J.; Kuehn, Kyler; Kuropatkin, Nikolay; Smith, Mathew; Sobreira, Flavia; Tarle, Gregory

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 a investigation for maximising 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 _2,800 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 an 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 Es and Spirals.We confirm that _2.5% 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).

Citation

Cheng, T.-Y., Conselice, C. J., Aragón-Salamanca, A., Li, N., Bluck, A. F., Hartley, W. G., Annis, J., Brooks, D., Doel, P., García-Bellido, J., James, D. J., Kuehn, K., Kuropatkin, N., Smith, M., Sobreira, F., & Tarle, G. (2020). Optimizing automatic morphological classification of galaxies with machine learning and deep learning using Dark Energy Survey imaging. Monthly Notices of the Royal Astronomical Society, 493(3), 4209-4228. https://doi.org/10.1093/mnras/staa501

• Journal Article Type: Article
• Acceptance Date: Feb 13, 2020
• Online Publication Date: Feb 19, 2020
• Publication Date: Apr 1, 2020
• Deposit Date: Feb 20, 2020
• Publicly Available Date: Feb 20, 2020
• 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: 493
• Issue: 3
• Pages: 4209-4228
• DOI: https://doi.org/10.1093/mnras/staa501
• Keywords: Space and Planetary Science; Astronomy and Astrophysics
• Public URL: https://nottingham-repository.worktribe.com/output/3999753
• Publisher URL: https://academic.oup.com/mnras/article-abstract/493/3/4209/5740728?redirectedFrom=fulltext
• Additional Information: This is a pre-copyedited, author-produced PDF of an article accepted for publication in Monthly Notices of the Royal Astronomical Society following peer review. The version of record: Ting-Yun Cheng, Christopher J Conselice, Alfonso Aragón-Salamanca, Nan Li, Asa F L Bluck, Will G Hartley, James Annis, David Brooks, Peter Doel, Juan García-Bellido, David J James, Kyler Kuehn, Nikolay Kuropatkin, Mathew Smith, Flavia Sobreira, Gregory Tarle, Optimizing automatic morphological classification of galaxies with machine learning and deep learning using Dark Energy Survey imaging, Monthly Notices of the Royal Astronomical Society, Volume 493, Issue 3, April 2020, Pages 4209–4228, is available online at: https://doi.org/10.1093/mnras/staa501