ABC-SN: Attention Based Classifier for Supernova Spectra
Abstract
While significant advances have been made in photometric classification ahead of the millions of transient events and hundreds of supernovae (SNe) each night that the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST) will discover, classifying SNe spectroscopically remains the best way to determine most subtypes of SNe. Traditional spectrum classification tools use template matching techniques (Blondin & Tonry 2007) and require significant human supervision. Two deep learning spectral classifiers, DASH (Muthukrishna et al. 2019) and SNIascore (Fremling et al. 2021) define the state of the art, but SNIascore is a binary classifier devoted to maximizing the purity of the SN Ia-norm sample, while DASH is no longer maintained and the original work suffers from contamination of multi-epoch spectra in the training and test sets. We have explored several neural network architectures in order to create a new automated method for classifying SN subtypes, settling on an attention-based model we call ABC-SN. We benchmark our results against an updated version of DASH, thus providing the community with an up-to-date general purpose SN classifier. Our dataset includes ten different SN subtypes including subtypes of SN Ia, core collapse and interacting SNe. We find that ABC-SN outperforms DASH, and we discuss the possibility that modern SN spectra datasets contain label noise which limit the performance of all classifiers.