Deep Learning for Image Sequence Classification of Astronomical Events

Abstract

We propose a new sequential classification model for astronomical objects based on a recurrent convolutional neural network (RCNN) which uses sequences of images as inputs. This approach avoids the computation of light curves or difference images. This is the first time that sequences of images are used directly for the classification of variable objects in astronomy. The second contribution of this work is the image simulation process. We generate synthetic image sequences that take into account the instrumental and observing conditions, obtaining a realistic, set of movies for each astronomical object. The simulated dataset is used to train our RCNN classifier. This approach allows us to generate datasets to train and test our RCNN model for different astronomical surveys and telescopes. We aim at building a simulated dataset whose distribution is close enough to the real dataset, so that a fine tuning could match the distributions between real and simulated dataset. To test the RCNN classifier trained with the synthetic dataset, we used real-world data from the High cadence Transient Survey (HiTS) obtaining an average recall of 85%, improved to 94% after performing fine tuning with 10 real samples per class. We compare the results of our model with those of a light curve random forest classifier. The proposed RCNN with fine tuning has a similar performance on the HiTS dataset compared to the light curve classifier, trained on an augmented training set with 10 real samples per class. The RCNN approach presents several advantages in an alert stream classification scenario, such as a reduction of the data pre-processing, faster online evaluation and easier performance improvement using a few real data samples. These results encourage us to use this method for alert brokers systems that will process alert streams generated by new telescopes such as the Large Synoptic Survey Telescope.

arXiv comment20 pages, 20 figures (corrected compilation errors). This is an Accepted Manuscript version of an article accepted for publication in Publications of the Astronomical Society of the Pacific. Nether the Astronomical Society of the Pacific nor IOP Publishing Ltd is responsible for any errors or omissions in this version of the manuscript or any version derived from it

References in corpus (29)

• Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant
• Sloan Digital Sky Survey IV: Mapping the Milky Way, Nearby Galaxies, and the Distant Universe
• The High-Z Supernova Search: Measuring Cosmic Deceleration and Global Cur vature of the Universe Using Type Ia Supernovae
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• K-corrections and spectral templates of Type Ia supernovae
• Light Curve Templates and Galactic Distribution of RR Lyrae Stars from Sloan Digital Sky Survey Stripe 82
• The delay of shock breakout due to circumstellar material seen in most Type II Supernovae
• Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era
• A recurrent neural network for classification of unevenly sampled variable stars
• Using Machine Learning for Discovery in Synoptic Survey Imaging
• Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
• Deep Recurrent Neural Networks for Supernovae Classification
• Two-Stream RNN/CNN for Action Recognition in 3D Videos
• Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
• The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database
• Light-curve and spectral properties of ultra-stripped core-collapse supernovae leading to binary neutron stars
• Cepheid Variables in the Flared Outer Disk of our Galaxy
• Deep CFHT Photometric Survey of the Entire M33 Galaxy I: Catalogue of 36000 Variable Point Sources
• Lightcurve Classification in Massive Variability Surveys
• The High Cadence Transient Survey (HiTS) - I. Survey design and supernova shock breakout constraints
• Discovery of distant RR Lyrae stars in the Milky Way using DECam
• Effective Image Differencing with ConvNets for Real-time Transient Hunting
• Lightcurve Classification in Massive Variability Surveys II: Transients towards the Large Magellanic Cloud
• Automatic Classification of Variable Stars in Catalogs with missing data
• The M33 Synoptic Stellar Survey. II. Mira Variables
• Automatic Survey-Invariant Variable Star Classification
• The High Cadence Transient Survey (HITS): Compilation and characterization of light-curve catalogs
• Uncertain classification of Variable Stars: handling observational GAPS and noise

Cited by in corpus (31)

• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy
• Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier
• GHOST: Using Only Host Galaxy Information to Accurately Associate and Distinguish Supernovae
• Classifying Kepler light curves for 12,000 A and F stars using supervised feature-based machine learning
• Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data
• Background Rejection in Atmospheric Cherenkov Telescopes using Recurrent Convolutional Neural Networks
• Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves
• Classifying Image Sequences of Astronomical Transients with Deep Neural Networks
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• Real-Time Value-Driven Data Augmentation in the Era of LSST
• Foreword to the Focus Issue on Machine Learning in Astronomy and Astrophysics
• ATAT: Astronomical Transformer for time series And Tabular data
• Star formation and morphological properties of galaxies in the Pan-STARRS $3\pi$ survey- I. A machine learning approach to galaxy and supernova classification
• What's the Difference? The potential for Convolutional Neural Networks for transient detection without template subtraction
• Automatic classification of eclipsing binary stars using deep learning methods
• Evolution strategies: Application in hybrid quantum-classical neural networks
• The effect of phased recurrent units in the classification of multiple catalogs of astronomical lightcurves
• Identifying Light-curve Signals with a Deep Learning Based Object Detection Algorithm. II. A General Light Curve Classification Framework
• O'TRAIN: a robust and flexible Real/Bogus classifier for the study of the optical transient sky
• The PAU Survey: Background light estimation with deep learning techniques
• Multi-scale stamps for real-time classification of alert streams
• Informative Bayesian model selection for RR Lyrae star classifiers
• Astronomical image time series classification using CONVolutional attENTION (ConvEntion)
• Leveraging pre-trained vision Transformers for multi-band photometric light curve classification
• Uncertainty estimation for time series classification: Exploring predictive uncertainty in transformer-based models for variable stars
• Classifying sequences by combining context-free grammars and OWL ontologies
• Informative regularization for a multi-layer perceptron RR Lyrae classifier under data shift