Insights into quasar UV spectra using unsupervised clustering analysis

Machine learning can provide powerful tools to detect patterns in multi-dimensional parameter space. We use K-means -a simple yet powerful unsupervised clustering algorithm which picks out structure in unlabeled data- to study a sample of quasar UV spectra from the Quasar Catalog of the 10th Data Release of the Sloan Digital Sky Survey of Paris et al. (2014). Detecting patterns in large datasets helps us gain insights into the physical conditions and processes giving rise to the observed properties of quasars. We use K-means to find clusters in the parameter space of the equivalent width (EW), the blue- and red-half-width at half-maximum (HWHM) of the Mg II 2800 A line, the C IV 1549 A line, and the C III] 1908 A blend in samples of Broad Absorption-Line (BAL) and non-BAL quasars at redshift 1.6-2.1. Using this method, we successfully recover correlations well-known in the UV regime such as the anti-correlation between the EW and blueshift of the C IV emission line and the shape of the ionizing Spectra Energy distribution (SED) probed by the strength of He II and the Si III]/C III] ratio. We find this to be particularly evident when the properties of C III] are used to find the clusters, while those of Mg II proved to be less strongly correlated with the properties of the other lines in the spectra such as the width of C IV or the Si III]/C III] ratio. We conclude that unsupervised clustering methods (such as K-means) are powerful methods for finding "natural" binning boundaries in multidimensional datasets and discuss caveats and future work.