Detection of exomoons in simulated light curves with a regularized convolutional neural network

TL;DR

This paper presents a regularized 1D convolutional neural network designed to classify photometric transit light curves and detect exomoons, outperforming classical methods and showing promise for future analysis of real data.

Contribution

The study introduces a novel regularization technique for CNNs using total variation loss to improve exomoon detection in light curves.

Findings

The network achieves accuracy comparable or superior to standard solutions.

It significantly outperforms classical exomoon detection methods.

Regularization enhances robustness against noise and stellar variability.

Abstract

Many moons have been detected around planets in our Solar System, but none has been detected unambiguously around any of the confirmed extrasolar planets. We test the feasibility of a supervised convolutional neural network to classify photometric transit light curves of planet-host stars and identify exomoon transits, while avoiding false positives caused by stellar variability or instrumental noise. Convolutional neural networks are known to have contributed to improving the accuracy of classification tasks. The network optimization is typically performed without studying the effect of noise on the training process. Here we design and optimize a 1D convolutional neural network to classify photometric transit light curves. We regularize the network by the total variation loss in order to remove unwanted variations in the data features. Using numerical experiments, we demonstrate the benefits of our network, which produces results comparable to or better than the standard network solutions. Most importantly, our network clearly outperforms a classical method used in exoplanet science to identify moon-like signals. Thus the proposed network is a promising approach for analyzing real transit light curves in the future.