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

TL;DR

This paper demonstrates the effective use of machine learning techniques, including majority voting of multiple models, to accurately identify optical transients in Subaru/HSC survey data, reducing false positives and enabling rapid detection of supernovae.

Contribution

The study introduces a novel transient selection method combining three ML models with majority voting, improving accuracy and speed in transient detection compared to traditional methods.

Findings

False positive rate of 1.0% at 90% true positive rate.

Successful detection and reporting of supernova candidates within a day.

Artificial object training enhances false candidate filtering, especially for faint sources.

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.