Classifying galaxy spectra at 0.5<z<1 with self-organizing maps

Abstract

The spectrum of a galaxy contains information about its physical properties. Classifying spectra using templates helps elucidate the nature of a galaxy's energy sources. In this paper, we investigate the use of self-organizing maps in classifying galaxy spectra against templates. We trained semi-supervised self-organizing map networks using a set of templates covering the wavelength range from far ultraviolet to near infrared. The trained networks were used to classify the spectra of a sample of 142 galaxies with 0.5 < z < 1 and the results compared to classifications performed using K-means clustering, a supervised neural network, and chi-squared minimization. Spectra corresponding to quiescent galaxies were more likely to be classified similarly by all methods while starburst spectra showed more variability. Compared to classification using chi-squared minimization or the supervised neural network, the galaxies classed together by the self-organizing map had more similar spectra. The class ordering provided by the one-dimensional self-organizing maps corresponds to an ordering in physical properties, a potentially important feature for the exploration of large datasets.

MNRAS in press; 19 pages, 22 figures

References in corpus (15)

• An Ultraviolet-to-Radio Broadband Spectral Atlas of Nearby Galaxies
• Galaxy Types in the Sloan Digital Sky Survey Using Supervised Artificial Neural Networks
• An Artificial Neural Network Approach to Classification of Galaxy Spectra
• SOMz: photometric redshift PDFs with self organizing maps and random atlas
• Wide Field Imaging. I. Applications of Neural Networks to object detection and star/galaxy classification
• An Artificial Neural Network Approach For Ranking Quenching Parameters In Central Galaxies
• Reclassification of gamma-ray bursts
• The automated classification of astronomical lightcurves using Kohonen self-organising maps
• Classifying Broad Absorption Line Quasars: Metrics, Issues and a New Catalogue Constructed from SDSS DR5
• The infra-red luminosities of ~332,000 SDSS galaxies predicted from artificial neural networks and the Herschel Stripe 82 survey
• Classification and analysis of emission-line galaxies using mean field independent component analysis
• On the redshift of the very high energy γ-ray BL Lac object S2 0109+22
• An Optical Analysis of the Merging Cluster Abell 3888
• Insights into Quasar UV Spectra Using Unsupervised Clustering Analysis
• Redshift determination through weighted phase correlation: a linearithmic implementation

Cited by in corpus (12)

• Period spacings of $\gamma$ Doradus pulsators in the Kepler field: detection methods and application to 22 slow rotators
• Horizon-AGN virtual observatory -- 2: Template-free estimates of galaxy properties from colours
• Data mining techniques on astronomical spectra data. I : Clustering Analysis
• Autoencoding Galaxy Spectra I: Architecture
• Mapping the Diversity of Galaxy Spectra with Deep Unsupervised Machine Learning
• Unsupervised classification of SDSS galaxy spectra
• On the fundamentality of the radial acceleration relation for late-type galaxy dynamics
• An astronomical image content-based recommendation system using combined deep learning models in a fully unsupervised mode
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• CzSL: Learning from citizen science, experts and unlabelled data in astronomical image classification
• Galaxy Manifold: Characterizing and understanding galaxies with two parameters
• A machine learning approach to assessing the presence of substructure in quasar host galaxies using the Hyper Suprime-Cam Subaru Strategic Program