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

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.

arXiv comment15 pages, 15 figures, 3 tables

References in corpus (18)

• Scikit-learn: Machine Learning in Python
• Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant
• Measurements of Omega and Lambda from 42 High-Redshift Supernovae
• The High-Z Supernova Search: Measuring Cosmic Deceleration and Global Cur vature of the Universe Using Type Ia Supernovae
• A method for optimal image subtraction
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Exploring the Optical Transient Sky with the Palomar Transient Factory
• SkyMapper and the Southern Sky Survey
• Identifying Elusive Electromagnetic Counterparts to Gravitational Wave Mergers: an end-to-end simulation
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• 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
• Machine learning for transient discovery in Pan-STARRS1 difference imaging
• Pan-STARRS and PESSTO search for an optical counterpart to the LIGO gravitational wave source GW150914
• Machine Learning Classification of SDSS Transient Survey Images
• Machine-learning Selection of Optical Transients in Subaru/Hyper Suprime-Cam Survey
• The SkyMapper Transient Survey

Cited by in corpus (28)

• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Unsupervised star, galaxy, qso classification: Application of HDBSCAN
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• Deep multi-survey classification of variable stars
• Transient-optimised real-bogus classification with Bayesian Convolutional Neural Networks -- sifting the GOTO candidate stream
• Deep Learning Based Detection of Cosmological Diffuse Radio Sources
• Machine Learning for Observational Cosmology
• Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data
• Vetting the optical transient candidates detected by the GWAC network using convolutional neural networks
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• MeerCRAB: MeerLICHT Classification of Real and Bogus Transients using Deep Learning
• Machine Learning for Transient Recognition in Difference Imaging With Minimum Sampling Effort
• The Palomar Transient Factory Sky2Night programme
• What's the Difference? The potential for Convolutional Neural Networks for transient detection without template subtraction
• MANTRA: A Machine Learning reference lightcurve dataset for astronomical transient event recognition
• O'TRAIN: a robust and flexible Real/Bogus classifier for the study of the optical transient sky
• The mini-GWAC optical follow-up of the gravitational wave alerts: results from the O2 campaign and prospects for the upcoming O3 run
• Target Detection Framework for Lobster Eye X-Ray Telescopes with Machine Learning Algorithms
• SAGUARO: Time-domain Infrastructure for the Fourth Gravitational-wave Observing Run and Beyond
• Convolutional Neural Networks for Spectroscopic Redshift Estimation on Euclid Data
• Deep-learning Real/Bogus classification for the Tomo-e Gozen transient survey
• Identifying Transients in the Dark Energy Survey using Convolutional Neural Networks
• DanceCam: atmospheric turbulence mitigation in wide-field astronomical images with short-exposure video streams
• Self-Supervised Clustering on Image-Subtracted Data with Deep-Embedded Self-Organizing Map
• TOROS Optical follow-up of the Advanced LIGO-VIRGO O2 second observational campaign
• Multiband neural network classification of ZTF light curves as LSST proxies