Improving galaxy morphologies for SDSS with Deep Learning

被引:255
|
作者
Sanchez, H. Dominguez [1 ,2 ]
Huertas-Company, M. [1 ,2 ,3 ]
Bernardi, M. [1 ]
Tuccillo, D. [2 ,4 ]
Fischer, J. L. [1 ]
机构
[1] Univ Penn, Dept Phys & Astron, 209 South 33rd St, Philadelphia, PA 19104 USA
[2] UPMC Univ Paris 06, Sorbonne Univ, PSL Res Univ, LERMA,Observ Paris,CNRS, F-75014 Paris, France
[3] Univ Paris Sorbonne Cite PSC, Univ Paris Denis Diderot, F-75205 Paris 13, France
[4] Mines ParisTech, 35 Rue St Honore, F-77305 Fontainebleau, France
关键词
methods; observational catalogues galaxies; structure; NEURAL-NETWORKS; ZOO; CLASSIFICATIONS; DEPENDENCE; EVOLUTION; CATALOG; NEARBY; END;
D O I
10.1093/mnras/sty338
中图分类号
P1 [天文学];
学科分类号
0704 ;
摘要
We present a morphological catalogue for similar to 670 000 galaxies in the Sloan Digital Sky Survey in two flavours: T-type, related to the Hubble sequence, and Galaxy Zoo 2 (GZ2 hereafter) classification scheme. By combining accurate existing visual classification catalogues with machine learning, we provide the largest and most accurate morphological catalogue up to date. The classifications are obtained with Deep Learning algorithms using Convolutional Neural Networks (CNNs). We use two visual classification catalogues, GZ2 and Nair & Abraham (2010), for training CNNs with colour images in order to obtain T-types and a series of GZ2 type questions (disc/features, edge-on galaxies, bar signature, bulge prominence, roundness, and mergers). We also provide an additional probability enabling a separation between pure elliptical (E) from SO, where the T-type model is not so efficient. For the T-type, our results show smaller offset and scatter than previous models trained with support vector machines. For the GZ2 type questions, our models have large accuracy (>97 per cent), precision and recall values (>90 per cent), when applied to a test sample with the same characteristics as the one used for training. The catalogue is publicly released with the paper.
引用
收藏
页码:3661 / 3676
页数:16
相关论文
共 50 条
  • [41] The hierarchical origin of galaxy morphologies
    Steinmetz, M
    Navarro, JF
    NEW ASTRONOMY, 2002, 7 (04): : 155 - 160
  • [42] ContextNet: Deep learning for Star Galaxy Classification
    Kennamer, Noble
    Kirkby, David
    Ihler, Alex
    Sanchez, Javier
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80
  • [43] Galaxy morphologies in the Hubble Ultra Deep Field: Dominance of linear structures at the detection limit
    Elmegreen, DM
    Elmegreen, BG
    Rubin, DS
    Schaffer, MA
    ASTROPHYSICAL JOURNAL, 2005, 631 (01): : 85 - 100
  • [44] Search for strong galaxy-galaxy lensing in SDSS-Ⅲ BOSS
    Xin-Lun Cheng
    Research in Astronomy and Astrophysics, 2020, 20 (01) : 8 - 20
  • [45] Large scale galaxy distribution in the SDSS.
    Doroshkevich, A
    Tucker, D
    Allam, S
    NEW ERA IN COSMOLOGY, 2002, 283 : 125 - 126
  • [46] The size and shape dependence of the SDSS galaxy bispectrum
    Nandi, Anindita
    Gill, Sukhdeep Singh
    Sarkar, Debanjan
    Shaw, Abinash Kumar
    Pandey, Biswajit
    Bharadwaj, Somnath
    NEW ASTRONOMY, 2024, 113
  • [47] The RASS-SDSS galaxy cluster survey
    Popesso, P
    Böhringer, H
    Voges, W
    Multiwavelength Mapping of Galaxy Formation and Evolution, 2005, : 444 - 445
  • [48] DISSECTING GALAXY COLORS WITH GALEX, SDSS, AND SPITZER
    Johnson, B. D.
    Schiminovich, D.
    Seibert, M.
    Treyer, M. A.
    Charlot, S.
    Heckman, T. M.
    Martin, D. C.
    Salim, S.
    Kauffmann, G.
    Bianchi, L.
    Donas, J.
    Friedman, P. G.
    Lee, Y-W
    Madore, B. F.
    Milliard, B.
    Morrissey, P.
    Neff, S. G.
    Rich, R. M.
    Szalay, A. S.
    Forster, K.
    Barlow, T. A.
    Conrow, T.
    Small, T.
    Wyder, T. K.
    ASTROPHYSICAL JOURNAL, 2006, 644 (02): : L109 - L112
  • [49] The intrinsic shape of galaxies in SDSS/Galaxy Zoo
    Rodriguez, Silvio
    Padilla, Nelson D.
    MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY, 2013, 434 (03) : 2153 - 2166
  • [50] Large scale structure in the SDSS galaxy survey
    Doroshkevich, A
    Tucker, DL
    Allam, S
    Way, MJ
    ASTRONOMY & ASTROPHYSICS, 2004, 418 (01): : 7 - 23