Galaxy morphological classification in deep-wide surveys via unsupervised machine learning

Abstract

Galaxy morphology is a fundamental quantity, that is essential not only for the full spectrum of galaxy-evolution studies, but also for a plethora of science in observational cosmology (e.g. as a prior for photometric-redshift measurements and as contextual data for transient lightcurve classifications). While a rich literature exists on morphological-classification techniques, the unprecedented data volumes, coupled, in some cases, with the short cadences of forthcoming 'Big-Data' surveys (e.g. from the LSST), present novel challenges for this field. Large data volumes make such datasets intractable for visual inspection (even via massively-distributed platforms like Galaxy Zoo), while short cadences make it difficult to employ techniques like supervised machine-learning, since it may be impractical to repeatedly produce training sets on short timescales. Unsupervised machine learning, which does not require training sets, is ideally suited to the morphological analysis of new and forthcoming surveys. Here, we employ an algorithm that performs clustering of graph representations, in order to group image patches with similar visual properties and objects constructed from those patches, like galaxies. We implement the algorithm on the Hyper-Suprime-Cam Subaru-Strategic-Program Ultra-Deep survey, to autonomously reduce the galaxy population to a small number (160) of 'morphological clusters', populated by galaxies with similar morphologies, which are then benchmarked using visual inspection. The morphological classifications (which we release publicly) exhibit a high level of purity, and reproduce known trends in key galaxy properties as a function of morphological type at z < 1 (e.g. stellar-mass functions, rest-frame colours and the position of galaxies on the star-formation main sequence). Our study demonstrates the power of unsupervised machine learning in performing accurate morphological analysis, which will become indispensable in this new era of deep-wide surveys.

Synergies between low- and intermediate-redshift galaxy populations revealed with unsupervised machine learning

“…A growing literature has emerged in recent years, reporting the results of the application of unsupervised techniques to various astrophysical contexts (see Baron 2019 andBall &Brunner 2010 for comprehensive reviews). Clustering has been used, for example, to partition galaxies on the basis of their pixel data (Hocking et al 2017(Hocking et al , 2018Martin et al 2020), their spectra (Sánchez Almeida et al 2010;de Souza et al 2017), their SEDs (Siudek et al 2018b,a), and their derived astrophysical features (Barchi et al 2016;Turner et al 2019). Dimensionality reduction, which can extract important or discriminative information from large ensembles of input features, has been used, for example, to produce simplified projections of galaxy samples based on their multi-wavelength photometry (Steinhardt et al 2020) and their estimated SEDs (Davidzon et al 2019;Hemmati et al 2019), and to classify their spectra (Yip et al 2004;Marchetti et al 2013).…”

Eigengalaxies: describing galaxy morphology using principal components in image space

“…There is some precedence for this in astronomy. For example, Martin et al (2020) follow Hocking et al (2018) in using growing neural gas and hierarchical clustering directly on pixel data to identify structurally distinct clusters. Almeida et al (2010) and Almeida & Prieto (2013) utilise k-means to classify spectra from SDSS into fewer base types.…”

“…Lahav et al 1995), there has been a recent explosion of studies that apply such techniques to the exploration of galaxy morphology, particularly in large survey datasets (e.g. Huertas-Company et al 2015;Ostrovski et al 2017;Schawinski et al 2017;Hocking et al 2018;Goulding et al 2018;Cheng et al 2019;Martin et al 2020).…”

Color Classification of Wooden Boards Based on Machine Vision and the Clustering Algorithm

“…To solve this problem, the clustering algorithms may be a reasonable solution, which has been used to process images in some applications. Reference [17] used the k-means algorithm to classify galaxies into morphological clusters by their visual similarity. In [18], the G-means algorithm was used for intrusion detection.…”

“…The mean squared distance is the average of the squared distances of samples to their closest cluster center. Silhouette scores [17] range from −1 to 1: a high silhouette score indicates that the object is well matched to its own cluster and distinct from neighboring clusters. The Calinski-Harabasz score of a clustering is in [0, +∞] and should be maximized [28].…”