SNIascore: Deep Learning Classification of Low-Resolution Supernova Spectra

Abstract

We present SNIascore, a deep-learning based method for spectroscopic classification of thermonuclear supernovae (SNe Ia) based on very low-resolution (R $\sim 100$) data. The goal of SNIascore is fully automated classification of SNe Ia with a very low false-positive rate (FPR) so that human intervention can be greatly reduced in large-scale SN classification efforts, such as that undertaken by the public Zwicky Transient Facility (ZTF) Bright Transient Survey (BTS). We utilize a recurrent neural network (RNN) architecture with a combination of bidirectional long short-term memory and gated recurrent unit layers. SNIascore achieves a $<0.6\%$ FPR while classifying up to $90\%$ of the low-resolution SN Ia spectra obtained by the BTS. SNIascore simultaneously performs binary classification and predicts the redshifts of secure SNe Ia via regression (with a typical uncertainty of $<0.005$ in the range from $z=0.01$ to $z=0.12$). For the magnitude-limited ZTF BTS survey ($\approx 70\%$ SNe Ia), deploying SNIascore reduces the amount of spectra in need of human classification or confirmation by $\approx 60\%$. Furthermore, SNIascore allows SN Ia classifications to be automatically announced in real-time to the public immediately following a finished observation during the night.

arXiv comment12 pages, 5 figures, 2 tables, accepted for publication in ApJL

References in corpus (23)

• Adam: A Method for Stochastic Optimization
• Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• The Zwicky Transient Facility: Data Processing, Products, and Archive
• ATLAS: A High-Cadence All-Sky Survey System
• The Zwicky Transient Facility: Science Objectives
• The Zwicky Transient Facility: Surveys and Scheduler
• Berkeley Supernova Ia Program I: Observations, Data Reduction, and Spectroscopic Sample of 582 Low-Redshift Type Ia Supernovae
• The Zwicky Transient Facility: Observing System
• The Zwicky Transient Facility Bright Transient Survey. II. A Public Statistical Sample for Exploring Supernova Demographics
• The SED Machine: a robotic spectrograph for fast transient classification
• Optical Spectra of 73 Stripped-Envelope Core-Collapse Supernovae
• The Spectral SN-GRB Connection: Systematic Spectral Comparisons between Type Ic Supernovae, and broad-lined Type Ic Supernovae with and without Gamma-Ray Bursts
• Real-bogus classification for the Zwicky Transient Facility using deep learning
• Type II supernova spectral diversity I: Observations, sample characterization and spectral line evolution
• The GROWTH Marshal: A Dynamic Science Portal for Time-Domain Astronomy
• A Fully Automated Integral Field Spectrograph Pipeline for the SEDMachine: pysedm
• RAPID: Early Classification of Explosive Transients using Deep Learning
• Analyzing the Largest Spectroscopic Dataset of Stripped Supernovae to Improve Their Identifications and Constrain Their Progenitors
• Transient processing and analysis using $\text{AMPEL}$: Alert Management, Photometry and Evaluation of Lightcurves
• DASH: Deep Learning for the Automated Spectral Classification of Supernovae and their Hosts
• Optimal Classification and Outlier Detection for Stripped-Envelope Core-Collapse Supernovae
• Towards An Integrated Optical Transient Utility

Cited by in corpus (6)

• A radio-detected Type Ia supernova with helium-rich circumstellar material
• Data mining techniques on astronomical spectra data. II : Classification Analysis
• Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
• SCAT Uncovers ATLAS's First Tidal Disruption Event ATLAS18mlw: A Faint and Fast TDE in a Quiescent Balmer Strong Galaxy
• Evaluating the feasibility of interpretable machine learning for globular cluster detection
• Neural Symplectic Integrator with Hamiltonian Inductive Bias for the Gravitational $N$-body Problem