Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope (LSST), given that spectroscopic confirmation of type for all supernovae discovered with these surveys will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques fitting parametric models to curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k-nearest neighbors, support vector machines, artificial neural networks and boosted decision trees. We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly-used area under the Receiver Operating Characteristic curve (AUC) as a metric, we find that the SALT2 fits and the wavelet approach, with the boosted decision trees algorithm, each achieves an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, suggesting that spectroscopic follow-up is best focused on fewer objects at a broad range of redshifts than on many bright objects. Importantly, we find that by using either one of the two best feature extraction methods (SALT2 model fits and wavelet decomposition) and a boosted decision tree algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.
↧