Unveiling galaxy morphology through an unsupervised-supervised hybrid approach
Monthly Notices of the Royal Astronomical Society · 13.01.2024 · 528 (1) · 82-107
DOI: 10.1093/mnras/stad3934 ↗Kurz gefasst
Fachartikel in der Zeitschrift Monthly Notices of the Royal Astronomical Society, online erschienen am 21.12.2023. Verfasst von I Kolesnikov und 6 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: FAPESP.
Abstract (Originalsprache)
Galaxy morphology offers significant insights into the evolutionary pathways and underlying physics of galaxies. As astronomical data grow with surveys such as Euclid and Vera C. Rubin, there is a need for tools to classify and analyse the vast numbers of galaxies that will be observed. In this work, we introduce a novel classification technique blending unsupervised clustering based on morphological metrics with the scalability of supervised Convolutional Neural Networks. We delve into a comparative analysis between the well-known CAS (Concentration, Asymmetry, and Smoothness) metrics and our newly proposed EGG (Entropy, Gini, and Gradient Pattern Analysis). Our choice of the EGG system stems from its separation-oriented metrics, maximizing morphological class contrast. We leverage relationships between metrics and morphological classes, leading to an internal agreement between unsupervised clustering and supervised classification. Applying our methodology to the Sloan Digital Sky Survey data, we obtain ∼95 per cent of Overall Accuracy of purely unsupervised classification and when we replicate T-Type and visually classified galaxy catalogues with accuracy of ∼88 and ∼89 per cent, respectively, illustrating the method’s practicality. Furthermore, the application to Hubble Space Telescope data heralds the potential for unsupervised exploration of a higher redshift range. A notable achievement is our ∼95 per cent accuracy in unsupervised classification, a result that rivals when juxtaposed with Traditional Machine Learning and closely trails when compared to Deep Learning benchmarks.
Förderung
- FAPESP
Zitieren
APA
Kolesnikov, I., Sampaio, V. M., Carvalho, R. R. D., Conselice, C., Rembold, S. B., Mendes, C. L., & Rosa, R. R. (2024). Unveiling galaxy morphology through an unsupervised-supervised hybrid approach. Monthly Notices of the Royal Astronomical Society, 528(1), 82-107. https://doi.org/10.1093/mnras/stad3934
Vancouver
Kolesnikov I, Sampaio VM, Carvalho RRD, Conselice C, Rembold SB, Mendes CL, et al. Unveiling galaxy morphology through an unsupervised-supervised hybrid approach. Monthly Notices of the Royal Astronomical Society. 2024;528(1):82-107. doi:10.1093/mnras/stad3934
BibTeX
@article{Kolesnikov2024,
author = {Kolesnikov, I and Sampaio, V M and Carvalho, R R de and Conselice, C and Rembold, S B and Mendes, C L and Rosa, R R},
title = {Unveiling galaxy morphology through an unsupervised-supervised hybrid approach},
journal = {Monthly Notices of the Royal Astronomical Society},
year = {2024},
volume = {528},
number = {1},
pages = {82--107},
doi = {10.1093/mnras/stad3934}
}
EUVIMED