Convolutional Neural Networks for Transient Candidate Vetting in Large-Scale Surveys

TL;DR

This paper demonstrates that convolutional neural networks can effectively classify astronomical transient candidates and artifacts in large-scale sky surveys, achieving high accuracy and potentially eliminating the need for image subtraction in future pipelines.

Contribution

It introduces CNN-based models for transient candidate vetting that outperform existing systems and can operate without difference images, simplifying the detection pipeline.

Findings

Achieved 97.3% accuracy on real sources and 99.7% on bogus in test set.

Simple CNN architectures are competitive with state-of-the-art methods.

Deeper networks and preprocessing improve classification performance.

Abstract

Current synoptic sky surveys monitor large areas of the sky to find variable and transient astronomical sources. As the number of detections per night at a single telescope easily exceeds several thousand, current detection pipelines make intensive use of machine learning algorithms to classify the detected objects and to filter out the most interesting candidates. A number of upcoming surveys will produce up to three orders of magnitude more data, which renders high-precision classification systems essential to reduce the manual and, hence, expensive vetting by human experts. We present an approach based on convolutional neural networks to discriminate between true astrophysical sources and artefacts in reference-subtracted optical images. We show that relatively simple networks are already competitive with state-of-the-art systems and that their quality can further be improved via slightly deeper networks and additional preprocessing steps -- eventually yielding models outperforming state-of-the-art systems. In particular, our best model correctly classifies about 97.3% of all 'real' and 99.7% of all 'bogus' instances on a test set containing 1,942 'bogus' and 227 'real' instances in total. Furthermore, the networks considered in this work can also successfully classify these objects at hand without relying on difference images, which might pave the way for future detection pipelines not containing image subtraction steps at all.