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

B. SÁNCHEZ; M.J. DOMINGUEZ; M. LARES; M. BEROIZ; J.B. CABRAL; S. GUROVICH; C. QUIÑONES; R. ARTOLA; C. COLAZO; M. SCHNEITER; C. GIRARDINI; M. TORNATORE; NILO CASTELLÓN; D. GARCı́A LAMBAS; M. C. DIAZ

Astronomy and Computing

Elsevier

Año: 2019

2213-1337

We present a comparison of several Difference Image Analysis techniques, in combination with Machine Learning(ML) algorithms, applied to the identification of optical transients associated to gravitational wave events. Eachtechnique is assessed based on the number of false positives and false negatives that it generates, using simulatedand real data. The newest subtraction techniques are implemented on an Open Source Python package, namedproperimage, which is naturally extendable and easy to implement on other astronomical image analyses. Thistogether, with the ML libraries we describe, provides an effective transient detection software pipeline. Here we studythe effects of the different ML techniques for classification of transient candidates, and propose an optimal combinedstrategy. This constitutes the basic elements of pipelines that currently being applied in searches of electromagneticcounterparts to GW sources.