Galaxy classification: A machine learning analysis of GAMA catalogue data

NEUROCOMPUTING

卷:342

Article

Nolte, Aleke¹  Wang, Lingyu^2,3  Bilicki, Maciej^4,5  Holwerda, Benne^4,6  Biehl, Michael¹ 

[1] Univ Groningen, Bernoulli Inst Math Comp Sci & Artificial Intelli, POB 407, NL-9700 AK Groningen, Netherlands

[2] Univ Groningen, Kapteyn Astron Inst, Landleven 12, NL-9747 AD Groningen, Netherlands

[3] SRON Netherlands Inst Space Res, Utrecht, Netherlands

[4] Leiden Univ, Leiden Observ, POB 9513, NL-2300 RA Leiden, Netherlands

[5] Polish Acad Sci, Ctr Theoret Phys, Al Lotnikow 32-46, PL-02668 Warsaw, Poland

[6] Univ Louisville, Dept Phys & Astron, 102 Nat Sci Bldg, Louisville, KY 40292 USA

关键词: Learning Vector Quantization;    Relevance learning;    Galaxy classification;    Random Forests;   

DOI  :  10.1016/j.neucom.2018.12.076

来源: Elsevier

【 摘 要 】

We present a machine learning analysis of five labelled galaxy catalogues from the Galaxy And Mass Assembly (GAMA): The SersicCatVIKING and SersicCatUKIDSS catalogues containing morphological features, the GaussFitSimple catalogue containing spectroscopic features, the MagPhys catalogue including physical parameters for galaxies, and the Lambdar catalogue, which contains photometric measurements. Extending work previously presented at the ESANN 2018 conference - in an analysis based on Generalized Relevance Matrix Learning Vector Quantization and Random Forests - we find that neither the data from the individual catalogues nor a combined dataset based on all 5 catalogues fully supports the visualinspection-based galaxy classification scheme employed to categorise the galaxies. In particular, only one class, the Little Blue Spheroids, is consistently separable from the other classes. To aid further insight into the nature of the employed visual-based classification scheme with respect to physical and morphological features, we present the galaxy parameters that are discriminative for the achieved class distinctions. (C) 2019 Elsevier B.V. All rights reserved.

【 授权许可】

Free