Machine Learning on Difference Image Analysis: A comparison of methods for transient detection

Abstract

We present a comparison of several Difference Image Analysis (DIA) techniques, in combination with Machine Learning (ML) algorithms, applied to the identification of optical transients associated with gravitational wave events. Each technique is assessed based on the scoring metrics of Precision, Recall, and their harmonic mean F1, measured on the DIA results as standalone techniques, and also in the results after the application of ML algorithms, on transient source injections over simulated and real data. This simulations cover a wide range of instrumental configurations, as well as a variety of scenarios of observation conditions, by exploring a multi dimensional set of relevant parameters, allowing us to extract general conclusions related to the identification of transient astrophysical events. The newest subtraction techniques, and particularly the methodology published in Zackay et al. (2016) are implemented in an Open Source Python package, named properimage, suitable for many other astronomical image analyses. This together with the ML libraries we describe, provides an effective transient detection software pipeline. Here we study the effects of the different ML techniques, and the relative feature importances for classification of transient candidates, and propose an optimal combined strategy. This constitutes the basic elements of pipelines that could be applied in searches of electromagnetic counterparts to GW sources.

18 pages, 8 figures, 2 tables, accepted for publication in Astronomy & Computing

References in corpus (22)

• Astropy: A Community Python Package for Astronomy
• Observation of Gravitational Waves from a Binary Black Hole Merger
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• Multi-messenger Observations of a Binary Neutron Star Merger
• GW170104: Observation of a 50-Solar-Mass Binary Black Hole Coalescence at Redshift 0.2
• A method for optimal image subtraction
• The Palomar Transient Factory: System Overview, Performance and First Results
• Exploring the Optical Transient Sky with the Palomar Transient Factory
• Opacities and Spectra of the r-process Ejecta from Neutron Star Mergers
• Radioactivity and thermalization in the ejecta of compact object mergers and their impact on kilonova light curves
• Proper image subtraction - optimal transient detection, photometry and hypothesis testing
• A New Algorithm For Difference Image Analysis
• Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era
• Observations of the first electromagnetic counterpart to a gravitational wave source by the TOROS collaboration
• A List of Galaxies for Gravitational Wave Searches
• How to coadd images? I. Optimal source detection and photometry using ensembles of images
• Effective Image Differencing with ConvNets for Real-time Transient Hunting
• How to coadd images? II. A coaddition image that is optimal for any purpose in the background dominated noise limit
• Difference Image Analysis of Defocused Observations with CSTAR
• GW150914: First search for the electromagnetic counterpart of a gravitational-wave event by the TOROS collaboration
• Difference image analysis: Automatic kernel design using information criteria
• Corral Framework: Trustworthy and Fully Functional Data Intensive Parallel Astronomical Pipelines

Cited by in corpus (15)

• Using Deep Learning to Localize Gravitational Wave Sources
• Vetting the optical transient candidates detected by the GWAC network using convolutional neural networks
• Stellar Spectral Interpolation using Machine Learning
• What's the Difference? The potential for Convolutional Neural Networks for transient detection without template subtraction
• The effect of phased recurrent units in the classification of multiple catalogs of astronomical lightcurves
• The mini-GWAC optical follow-up of the gravitational wave alerts: results from the O2 campaign and prospects for the upcoming O3 run
• Reliable Photometric Membership (RPM) of Galaxies in Clusters. I. A Machine Learning Method and its Performance in the Local Universe
• Reconstruction of binary black hole harmonics in LIGO using deep learning
• No Glitch in the Matrix: Robust Reconstruction of Gravitational Wave Signals Under Noise Artifacts
• Variability and transient search in the SUDARE-VOICE field: a new method to extract the light curves
• TOROS Optical follow-up of the Advanced LIGO-VIRGO O2 second observational campaign
• Image plane detection of FRB121102 with the MeerKAT radio telescope
• Physical Parameters of Stars in NGC 6397 Using ANN-Based Interpolation and Full Spectrum Fitting
• State Space Modelling for detecting and characterising Gravitational Waves afterglows
• Machine Learning Confirms GW231123 is a "Lite" Intermediate Mass Black Hole Merger