O'TRAIN: a robust and flexible Real/Bogus classifier for the study of the optical transient sky

TL;DR

This paper introduces O'TRAIN, a convolutional neural network-based classifier designed to accurately distinguish real astronomical transients from bogus detections across diverse telescopes and detection pipelines, enhancing transient survey reliability.

Contribution

The paper presents a robust, flexible CNN model for real/bogus classification applicable to various telescopes and detection pipelines, with high accuracy and adaptability.

Findings

Achieved 93-98% classification accuracy across different datasets.

Successfully trained on diverse images with varying pixel scales.

Proven effective on multiple telescopes and detection pipelines.

Abstract

The scientific interest in studying high-energy transient phenomena in the Universe has largely grown for the last decade. Now, multiple ground-based survey projects have emerged to continuously monitor the optical (and multi-messenger) transient sky at higher image cadences and cover always larger portions of the sky every night. These novel approaches lead to a huge increase of the global alert rates which need to be handled with care especially by keeping the false alarms as low as possible. Therefore, the standard transient detection pipelines previously designed for narrow field of view instruments must now integrate more sophisticated tools to deal with the growing number and diversity of alerts and false alarms. Deep machine learning algorithms have now proven their efficiency in recognizing patterns in images. We explore this method to provide a robust and flexible algorithm that could be included in any kind of transient detection pipeline. We built a Convolutional Neural Network (CNN) algorithm in order to perform a real/bogus classification task on transient candidate cutouts (subtraction residuals) provided by different kinds of optical telescopes. The training involved human-supervised labeling of the cutouts, which had been split in two balanced data sets with \textit{True} and \textit{False} point-like source candidates. We tested our CNN model on the candidates produced by two different transient detection pipelines. We show that our CNN algorithm can be successfully trained on a large diversity of images having very different pixel scales. Tested on optical images from four different telescopes and utilising two different transient detection pipelines, our CNN model provides robust real/bogus classification performance accuracy from 93% up to 98% of well classified candidates.