Machine-learning Selection of Optical Transients in Subaru/Hyper Suprime-Cam Survey

Abstract

We present an application of machine-learning (ML) techniques to source selection in the optical transient survey data with Hyper Suprime-Cam (HSC) on the Subaru telescope. Our goal is to select real transient events accurately and in a timely manner out of a large number of false candidates, obtained with the standard difference-imaging method. We have developed the transient selector which is based on majority voting of three ML machines of AUC Boosting, Random Forest, and Deep Neural Network. We applied it to our observing runs of Subaru-HSC in 2015 May and August, and proved it to be efficient in selecting optical transients. The false positive rate was 1.0% at the true positive rate of 90% in the magnitude range of 22.0--25.0 mag for the former data. For the latter run, we successfully detected and reported ten candidates of supernovae within the same day as the observation. From these runs, we learned the following lessons: (1) the training using artificial objects is effective in filtering out false candidates, especially for faint objects, and (2) combination of ML by majority voting is advantageous.

arXiv comment9 pages, 6 figures. Accepted for publication in PASJ

References in corpus (10)

• The Eighth Data Release of the Sloan Digital Sky Survey: First Data from SDSS-III
• A method for optimal image subtraction
• Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era
• Automated Transient Identification in the Dark Energy Survey
• Using Machine Learning for Discovery in Synoptic Survey Imaging
• Rapidly Rising Transients from Subaru Hyper Suprime-Cam Transient Survey
• Machine learning for transient discovery in Pan-STARRS1 difference imaging
• How to Find More Supernovae with Less Work: Object Classification Techniques for Difference Imaging
• Machine Learning Classification of SDSS Transient Survey Images
• An Effective Selection Method for Low-Mass Active Black Holes and First Spectroscopic Identification

Cited by in corpus (17)

• Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
• Analysing the 21cm signal from the Epoch of Reionization with artificial neural networks
• Autoregressive Times Series Methods for Time Domain Astronomy
• Phase diagram of disordered higher-order topological insulator: A machine learning study
• Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys
• Effective Image Differencing with ConvNets for Real-time Transient Hunting
• Convolutional Neural Networks for Transient Candidate Vetting in Large-Scale Surveys
• Data Compression for the Tomo-e Gozen with Low-rank Matrix Approximation
• Machine Learning for Observational Cosmology
• The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Selection of a performance metric for classification probabilities balancing diverse science goals
• Vetting the optical transient candidates detected by the GWAC network using convolutional neural networks
• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• Linear feature detection algorithm for astronomical surveys - I. Algorithm description
• Single-epoch supernova classification with deep convolutional neural networks
• Optical follow-up observation of Fast Radio Burst 151230
• Partial AUC Maximization via Nonlinear Scoring Functions
• Automated Transient Detection with Shapelet Analysis in Image-subtracted Data