Identifying Potential Exomoon Signals with Convolutional Neural Networks

TL;DR

This paper develops and tests convolutional neural networks to identify potential exomoon signals in Kepler data, achieving high accuracy and precision, and applies the method to real light curves to find candidate signals.

Contribution

The study introduces an ensemble of CNNs trained on synthetic data for exomoon detection in Kepler light curves, demonstrating high accuracy and applying it to real data for candidate identification.

Findings

Achieved up to 88% classification accuracy with individual CNNs.

Reaching 97% precision in exomoon identification in validation.

Found a small fraction of transits with moon-like signals in Kepler data.

Abstract

Targeted observations of possible exomoon host systems will remain difficult to obtain and time-consuming to analyze in the foreseeable future. As such, time-domain surveys such as Kepler, K2 and TESS will continue to play a critical role as the first step in identifying candidate exomoon systems, which may then be followed-up with premier ground- or space-based telescopes. In this work, we train an ensemble of convolutional neural networks (CNNs) to identify candidate exomoon signals in single-transit events observed by Kepler. Our training set consists of ${\sim}$27,000 examples of synthetic, planet-only and planet+moon single transits, injected into Kepler light curves. We achieve up to 88\% classification accuracy with individual CNN architectures and 97\% precision in identifying the moons in the validation set when the CNN ensemble is in total agreement. We then apply the CNN ensemble to light curves from 1880 Kepler Objects of Interest with periods $>10$ days ($\sim$57,000 individual transits), and further test the accuracy of the CNN classifier by injecting planet transits into each light curve, thus quantifying the extent to which residual stellar activity may result in false positive classifications. We find a small fraction of these transits contain moon-like signals, though we caution against strong inferences of the exomoon occurrence rate from this result. We conclude by discussing some ongoing challenges to utilizing neural networks for the exomoon search.