info:eu-repo/semantics/article
Machine learning on difference image analysis: A comparison of methods for transient detection
Fecha
2019-07Registro en:
Sánchez, Bruno Orlando; Dominguez Romero, Mariano Javier de Leon; Lares Harbin Latorre, Marcelo; Beroiz, Martin Isidro Ramon; Cabral, Juan Bautista; et al.; Machine learning on difference image analysis: A comparison of methods for transient detection; Elsevier; Astronomy and Computing; 28; 7-2019; 1-17; 100284
2213-1337
CONICET Digital
CONICET
Autor
Sánchez, Bruno Orlando
Dominguez Romero, Mariano Javier de Leon
Lares Harbin Latorre, Marcelo
Beroiz, Martin Isidro Ramon
Cabral, Juan Bautista
Gurovich, Sebastian
Quiñones, Cecilia
Artola, Rodolfo Alfredo
Colazo, Carlos A.
Schneiter, Ernesto Matías
Girardini, Carla
Tornatore, Marina
Nilo Castellón, José Luis
Garcia Lambas, Diego Rodolfo
Díaz, Mario Coma
Resumen
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 to 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. These 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 on 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.