RAPID: Early Classification of Explosive Transients using Deep Learning

We present RAPID (Real-time Automated Photometric IDentification), a novel timeseries classification tool capable of automatically identifying transients from within a day of the initial alert to the full lifetime of a light curve. Using a deep recurrent neural network with Gated Recurrent Units (GRUs), we present the first method specifically designed to provide early classifications of astronomical timeseries data, typing 12 different transient classes (including supernovae, kilonovae, and rare transients). Our classifier can process light curves with any phase coverage, and it does not rely on deriving computationally expensive features from the data, making RAPID well‐suited for processing the millions of alerts that ongoing and upcoming wide‐field surveys such as ZTF and LSST will produce. The classification accuracy improves over the lifetime of the transient as more photometric data becomes available. We have made RAPID available as a software package for machine learning‐based alert‐brokers to use for the autonomous and quick classification of several thousand light curves within a few second