Multiplicity Boost of Transit Signal Classifiers: Validation of 69 New Exoplanets using the Multiplicity Boost of ExoMiner

• Published in: The Astronomical journal 2023-07, Vol.166 (1), p.28
• Main Authors: Valizadegan, Hamed, Martinho, Miguel J. S., Jenkins, Jon M., Caldwell, Douglas A., Twicken, Joseph D., Bryson, Stephen T.
• Format: Article
• Language: English
• Subjects: Astronomy; Classifiers; Convolutional neural networks; Exoplanet astronomy; Exoplanet catalogs; Exoplanet detection methods; Exoplanet systems; Exoplanets; Extrasolar planets; Neural networks; Performance enhancement; Signal classification
• ISSN: 0004-6256; 1538-3881
• DOI: 10.3847/1538-3881/acd344

Most existing exoplanets are discovered using validation techniques rather than being confirmed by complementary observations. These techniques generate a score that is typically the probability of the transit signal being an exoplanet ( y ( x ) = exoplanet) given some information related to that signal (represented by x ). Except for the validation technique in Rowe et al. (2014), which uses multiplicity information to generate these probability scores, the existing validation techniques ignore the multiplicity boost information. In this work, we introduce a framework with the following premise: given an existing transit-signal vetter (classifier), improve its performance using multiplicity information. We apply this framework to several existing classifiers, which include vespa , Robovetter , AstroNet , ExoNet , GPC and RFC , and ExoMiner , to support our claim that this framework is able to improve the performance of a given classifier. We then use the proposed multiplicity boost framework for ExoMiner V1.2, which addresses some of the shortcomings of the original ExoMiner classifier, and validate 69 new exoplanets for systems with multiple Kepler Objects of Interests from the Kepler catalog.