Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection

Abstract

We introduce Deep-HiTS, a rotation invariant convolutional neural network (CNN) model for classifying images of transients candidates into artifacts or real sources for the High cadence Transient Survey (HiTS). CNNs have the advantage of learning the features automatically from the data while achieving high performance. We compare our CNN model against a feature engineering approach using random forests (RF). We show that our CNN significantly outperforms the RF model reducing the error by almost half. Furthermore, for a fixed number of approximately 2,000 allowed false transient candidates per night we are able to reduce the miss-classified real transients by approximately 1/5. To the best of our knowledge, this is the first time CNNs have been used to detect astronomical transient events. Our approach will be very useful when processing images from next generation instruments such as the Large Synoptic Survey Telescope (LSST). We have made all our code and data available to the community for the sake of allowing further developments and comparisons at https://github.com/guille-c/Deep-HiTS.

References in corpus (12)

• Scikit-learn: Machine Learning in Python
• The Sloan Digital Sky Survey: Technical Summary
• The Man Behind the Curtain: X-rays Drive the UV through NIR Variability in the 2013 AGN Outburst in NGC 2617
• The Dark Energy Camera
• The Dark Energy Survey: more than dark energy - an overview
• LSST Science Book, Version 2.0
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
• 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
• The High Cadence Transient Survey (HiTS) - I. Survey design and supernova shock breakout constraints

Cited by in corpus (60)

• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Design and operation of the ATLAS Transient Science Server
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• The Automatic Learning for the Rapid Classification of Events (ALeRCE) Alert Broker
• Real-bogus classification for the Zwicky Transient Facility using deep learning
• Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Autoregressive Times Series Methods for Time Domain Astronomy
• Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier
• Detecting outliers in astronomical images with deep generative networks
• Detection of Bars in Galaxies using a Deep Convolutional Neural Network
• DASH: Deep Learning for the Automated Spectral Classification of Supernovae and their Hosts
• Machine Learning Techniques for Stellar Light Curve Classification
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• Deep multi-survey classification of variable stars
• Deep Learning for Image Sequence Classification of Astronomical Events
• Testing Convolutional Neural Networks for finding strong gravitational lenses in KiDS
• Effective Image Differencing with ConvNets for Real-time Transient Hunting
• Deep Learning for Strong Lensing Search: Tests of the Convolutional Neural Networks and New Candidates from KiDS DR3
• Transient-optimised real-bogus classification with Bayesian Convolutional Neural Networks -- sifting the GOTO candidate stream
• Introducing the Search for Intermediate-mass Black-hole In Nearby Galaxy (SIBLING) Survey
• Automatic Classification of Galaxy Morphology: a rotationally invariant supervised machine learning method based on the UML-dataset
• Unsupervised Classification of Variable Stars
• Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
• The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Selection of a performance metric for classification probabilities balancing diverse science goals
• Optical Transient Object Classification in Wide Field Small Aperture Telescopes with Neural Networks
• Deriving star cluster parameters with convolutional neural networks. I. Age, mass, and size
• The High Cadence Transient Survey (HITS): Compilation and characterization of light-curve catalogs
• Multiband galaxy morphologies for CLASH: a convolutional neural network transferred from CANDELS
• MeerCRAB: MeerLICHT Classification of Real and Bogus Transients using Deep Learning
• The VVV Infrared Variability Catalog (VIVA-I)
• ATAT: Astronomical Transformer for time series And Tabular data
• Machine Learning for Transient Recognition in Difference Imaging With Minimum Sampling Effort
• Finding Strong Gravitational Lenses Through Self-Attention
• A classification algorithm for time-domain novelties in preparation for LSST alerts: Application to variable stars and transients detected with DECam in the Galactic Bulge
• deepSIP: Linking Type Ia Supernova Spectra to Photometric Quantities with Deep Learning
• Asteroids' Size Distribution and Colors from HiTS
• 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
• The effect of phased recurrent units in the classification of multiple catalogs of astronomical lightcurves
• Streaming Classification of Variable Stars
• Identification of Grand-design and Flocculent Spirals from SDSS using Convolutional Neural network
• Shedding Light on Low Surface Brightness Galaxies in Dark Energy Survey with Transformers
• Enhanced Rotational Invariant Convolutional Neural Network for Supernovae Detection
• SAGUARO: Time-domain Infrastructure for the Fourth Gravitational-wave Observing Run and Beyond
• Preparation for CSST: Star-galaxy Classification using a Rotationally Invariant Supervised Machine Learning Method
• Identifying Transients in the Dark Energy Survey using Convolutional Neural Networks
• AGNet: Weighing Black Holes with Deep Learning
• DanceCam: atmospheric turbulence mitigation in wide-field astronomical images with short-exposure video streams
• Asteroids in the High cadence Transient Survey
• Self-Supervised Clustering on Image-Subtracted Data with Deep-Embedded Self-Organizing Map
• Determination of the relative inclination and the viewing angle of an interacting pair of galaxies using convolutional neural networks
• TOROS Optical follow-up of the Advanced LIGO-VIRGO O2 second observational campaign
• Eliminating artefacts in Polarimetric Images using Deep Learning
• Multi-scale stamps for real-time classification of alert streams
• DES to HSC: Detecting low surface brightness galaxies in the Abell 194 cluster using transfer learning
• Transformers as Strong Lens Detectors- From Simulation to Surveys
• AGNet: Weighing Black Holes with Machine Learning
• La Serena School for Data Science: multidisciplinary hands-on education in the era of big data
• Phenomenological classification of the Zwicky Transient Facility astronomical event alerts