$Mesiri$:Mephisto Early Supernovae Ia Rapid Identifier

TL;DR

This paper introduces Mesiri, a deep learning tool that uses real-time multi-band color data from the Mephisto telescope to accurately identify early-time Type Ia supernovae, aiding in understanding their origins.

Contribution

The paper presents Mesiri, the first classification method utilizing real-time color information for early SNe Ia identification, achieving high accuracy with minimal observations.

Findings

Achieves 96.75% accuracy and 98.87% AUC with single-epoch data.

Real-time color outperforms pseudo-color in early classification.

BiLSTM architecture yields the best performance.

Abstract

The early time observations of Type Ia supernovae (SNe Ia) play a crucial role in investigating and resolving longstanding questions about progenitor stars and the explosion mechanisms of these events. Colors of supernovae (SNe) in the initial days after the explosion can help differentiate between different types of SNe. However, the use of true color information to identify SNe Ia at the early-time explosion is still in its infancy. The Multi-channel Photometric Survey Telescope (Mephisto) is a photometric survey telescope equipped with three CCD cameras, capable of simultaneously imaging the same patch of sky in three bands (\emph{u, g, i} or \emph{v, r, z}), yielding real-time colors of astronomical objects. In this paper, we introduce a new time-series classification tool named Mephisto Early Supernovae Ia Rapid Identifier (\emph{\texttt{Mesiri}}), which for the first time, utilizes real-time color information to distinguish early-time SNe Ia from core-collapse supernovae (CCSNe). \emph{\texttt{Mesiri}} is based on the deep learning approach and can achieve an accuracy of $96.75\pm0.79$\%, and AUC of $98.87\pm0.53$\% in case of single epoch random observation before the peak brightness. These values reach towards perfectness if additional data points on several night observations are considered. The classification with real-time color significantly outperforms that with pseudo-color, especially at the early time, i.e., with only a few points of observations. The architecture of BiLSTM shows the best performance than the others that have been tested in this work.