Machine Learning and galaxy morphology: for what purpose?

Abstract

Classification of galaxies is traditionally associated with their morphologies through visual inspection of images. The amount of data to come renders this task inhuman and Machine Learning (mainly Deep Learning) has been called to the rescue for more than a decade. However, the results look mitigate and there seems to be a shift away from the paradigm of the traditional morphological classification of galaxies. In this paper, I want to show that the algorithms indeed are very sensitive to the features present in images, features that do not necessarily correspond to the Hubble or de Vaucouleurs vision of a galaxy. However, this does not preclude to get the correct insights into the physics of galaxies. I have applied a state-of-the-art ''traditional'' Machine Learning clustering tool, called Fisher-EM, a latent discriminant subspace Gaussian Mixture Model algorithm, to 4458 galaxies carefully classified into 18 types by the EFIGI project. The optimum number of clusters given by the Integrated Complete Likelihood criterion is 47. The correspondence with the EFIGI classification is correct, but it appears that the Fisher-EM algorithm gives a great importance to the distribution of light which translates to characteristics such as the bulge to disk ratio, the inclination or the presence of foreground stars. The discrimination of some physical parameters (bulge-to-total luminosity ratio, $(B--B)T$ , intrinsic diameter, presence of flocculence or dust, arm strength) is very comparable in the two classifications.

References in corpus (25)

• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• Galaxy Zoo 2: detailed morphological classifications for 304,122 galaxies from the Sloan Digital Sky Survey
• Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
• The EFIGI catalogue of 4458 nearby galaxies with detailed morphology
• Stellar structures, molecular gas, and star formation across the PHANGS sample of nearby galaxies
• Simultaneous model-based clustering and visualization in the Fisher discriminative subspace
• An automatic taxonomy of galaxy morphology using unsupervised machine learning
• Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
• Beyond the Hubble Sequence -- Exploring Galaxy Morphology with Unsupervised Machine Learning
• Multivariate Approaches to Classification in Extragalactic Astronomy
• A galaxy classification grid that better recognises early-type galaxy morphology
• The EFIGI catalogue of 4458 nearby galaxies with morphology II. Statistical properties along the Hubble sequence
• A six-parameter space to describe galaxy diversification
• Galaxy classification: a deep learning approach for classifying Sloan Digital Sky Survey images
• Unsupervised classification of SDSS galaxy spectra
• Synergies between low- and intermediate-redshift galaxy populations revealed with unsupervised machine learning
• Barlenses in the CALIFA survey: combining the photometric and stellar population analysis
• Unsupervised Classification of Galaxies. I. ICA feature selection
• The Systematics of Galaxy Morphology in the Comprehensive de Vaucouleurs revised Hubble-Sandage Classification System: Application to the EFIGI Sample
• Inside-out star formation quenching and the need for a revision of bulge-disk decomposition concepts for spiral galaxies
• The redshift evolution of the S0 fraction for $z<1$ in COSMOS
• The VIMOS Public Extragalactic Redshift Survey (VIPERS). Unsupervised classification with photometric redshifts: a method to accurately classify large galaxy samples without spectroscopic information
• Galaxy Image Classification using Hierarchical Data Learning with Weighted Sampling and Label Smoothing
• Unsupervised classification of CIGALE galaxy spectra
• The Classification of Optical Galaxy Morphology Using Unsupervised Learning Techniques