Deep Learning assessment of galaxy morphology in S-PLUS Data Release 1. Issue 2 (26th July 2021)

• Record Type: Journal Article
• Authors: Bom, C R; Cortesi, A; Lucatelli, G; Dias, L O; Schubert, P; Oliveira Schwarz, G B; Cardoso, N M; Lima, E V R; Mendes de Oliveira, C; Sodre, L; Smith Castelli, A V; Ferrari, F; Damke, G; Overzier, R; Kanaan, A; Ribeiro, T; Schoenell, W
• Is Part Of: Monthly notices of the Royal Astronomical Society. Volume 507:Issue 2(2021)
• Page Start: 1937
• Page End: 1955
• Publication Date: 2021-07-26
• Subjects: methods: miscellaneous -- techniques: image processing -- surveys -- galaxies: fundamental parameters -- galaxies: structure; Astronomy -- Periodicals; Periodicals; 520.5
• DOI: 10.1093/mnras/stab1981
• Languages: English
• ISSNs: 0035-8711

Abstract

ABSTRACT: The morphological diversity of galaxies is a relevant probe of galaxy evolution and cosmological structure formation, but the classification of galaxies in large sky surveys is becoming a significant challenge. We use data from the Stripe-82 area observed by the Southern Photometric Local Universe Survey (S-PLUS) in 12 optical bands, and present a catalogue of the morphologies of galaxies brighter than r = 17 mag determined both using a novel multiband morphometric fitting technique and Convolutional Neural Networks (CNNs) for computer vision. Using the CNNs, we find that, compared to our baseline results with three bands, the performance increases when using 5 broad and 3 narrow bands, but is poorer when using the full 12 band S-PLUS image set. However, the best result is still achieved with just three optical bands when using pre-trained network weights from an ImageNet data set. These results demonstrate the importance of using prior knowledge about neural network weights based on training in unrelated, extensive data sets, when available. Our catalogue contains 3274 galaxies in Stripe-82 that are not present in Galaxy Zoo 1 (GZ1), and we also provide our classifications for 4686 galaxies that were considered ambiguous in GZ1. Finally, we present a prospect of a novel way to take advantage of 12 band information for morphological classification using morphometric features, and we release a model that has been pre-trained on several bands that could be adapted for classifications using data from other surveys. The morphological catalogues are publicly available.