Photometric Search for Exomoons by using Convolutional Neural Networks

TL;DR

This paper demonstrates that convolutional neural networks trained on synthetic and real light curves can efficiently detect large exomoons, potentially revolutionizing the search process in upcoming space missions.

Contribution

It introduces a deep learning approach using CNNs trained on combined synthetic and observed data for exomoon detection, offering a more efficient alternative to classical methods.

Findings

CNNs can detect exomoons ≥ 2-3 Earth radii in Kepler data.

Deep learning reduces computational requirements for exomoon searches.

Method is applicable to future missions like PLATO.

Abstract

Until now, there is no confirmed moon beyond our solar system (exomoon). Exomoons offer us new possibly habitable places which might also be outside the classical habitable zone. But until now, the search for exomoons needs much computational power because classical statistical methods are employed. It is shown that exomoon signatures can be found by using deep learning and Convolutional Neural Networks (CNNs), respectively, trained with synthetic light curves combined with real light curves with no transits. It is found that CNNs trained by combined synthetic and observed light curves may be used to find moons bigger or equal to roughly 2-3 earth radii in the Kepler data set or comparable data sets. Using neural networks in future missions like Planetary Transits and Oscillation of stars (PLATO) might enable the detection of exomoons.