Classifying Image Sequences of Astronomical Transients with Deep Neural Networks

Abstract

Supervised classification of temporal sequences of astronomical images into meaningful transient astrophysical phenomena has been considered a hard problem because it requires the intervention of human experts. The classifier uses the expert's knowledge to find heuristic features to process the images, for instance, by performing image subtraction or by extracting sparse information such as flux time series, also known as light curves. We present a successful deep learning approach that learns directly from imaging data. Our method models explicitly the spatio-temporal patterns with Deep Convolutional Neural Networks and Gated Recurrent Units. We train these deep neural networks using 1.3 million real astronomical images from the Catalina Real-Time Transient Survey to classify the sequences into five different types of astronomical transient classes. The TAO-Net (for Transient Astronomical Objects Network) architecture outperforms the results from random forest classification on light curves by 10 percentage points as measured by the F1 score for each class; the average F1 over classes goes from $45\%$ with random forest classification to $55\%$ with TAO-Net. This achievement with TAO-Net opens the possibility to develop new deep learning architectures for early transient detection. We make available the training dataset and trained models of TAO-Net to allow for future extensions of this work.

arXiv comment11 pages, 7 figures. MNRAS accepted

References in corpus (17)

• The Zwicky Transient Facility: System Overview, Performance, and First Results
• The Man Behind the Curtain: X-rays Drive the UV through NIR Variability in the 2013 AGN Outburst in NGC 2617
• First Results from the Catalina Real-time Transient Survey
• ATLAS: A High-Cadence All-Sky Survey System
• SparsePak: A Formatted Fiber Field Unit for The WIYN Telescope Bench Spectrograph. I. Design, Construction, and Calibration
• The Palomar Transient Factory: System Overview, Performance and First Results
• PESSTO : survey description and products from the first data release by the Public ESO Spectroscopic Survey of Transient Objects
• On Machine-Learned Classification of Variable Stars with Sparse and Noisy Time-Series Data
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era
• Deep Recurrent Neural Networks for Supernovae Classification
• Optimizing spectroscopic follow-up strategies for supernova photometric classification with active learning
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• An analysis of feature relevance in the classification of astronomical transients with machine learning methods
• Deep Learning for Image Sequence Classification of Astronomical Events
• Optical Transient Object Classification in Wide Field Small Aperture Telescopes with Neural Networks
• MANTRA: A Machine Learning reference lightcurve dataset for astronomical transient event recognition

Cited by in corpus (14)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• GHOST: Using Only Host Galaxy Information to Accurately Associate and Distinguish Supernovae
• Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data
• An Infrared Search for Kilonovae with the WINTER Telescope. I. Binary Neutron Star Mergers
• Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves
• Spectroscopic Studies of Type Ia Supernovae Using LSTM Neural Networks
• ATAT: Astronomical Transformer for time series And Tabular data
• Identifying Transients in the Dark Energy Survey using Convolutional Neural Networks
• The classification of real and bogus transients using active learning and semi-supervised learning
• Multi-scale stamps for real-time classification of alert streams
• Astronomical image time series classification using CONVolutional attENTION (ConvEntion)
• Leveraging pre-trained vision Transformers for multi-band photometric light curve classification