A one-armed CNN for exoplanet detection from light curves

TL;DR

This paper introduces Genesis, a simplified one-armed CNN for exoplanet detection from light curves, demonstrating comparable performance to more complex models while reducing parameters and exploring effects of validation methods and input resolution.

Contribution

The paper presents Genesis, a significantly simplified CNN architecture for exoplanet detection, and evaluates its performance, validation methods, and input resolution effects compared to existing models.

Findings

Genesis reduces model complexity by over 95% with minimal performance loss.

Monte Carlo cross-validation yields more realistic performance estimates, slightly lower than initial assessments.

Increasing input resolution decreases detection performance slightly, indicating a trade-off.

Abstract

We propose Genesis, a one-armed simplified Convolutional Neural Network (CNN)for exoplanet detection, and compare it to the more complex, two-armed CNN called Astronet. Furthermore, we examine how Monte Carlo cross-validation affects the estimation of the exoplanet detection performance. Finally, we increase the input resolution twofold to assess its effect on performance. The experiments reveal that (i)the reduced complexity of Genesis, i.e., a more than 95% reduction in the number of free parameters, incurs a small performance cost of about 0.5% compared to Astronet, (ii) Monte Carlo cross-validation provides a more realistic performance estimate that is almost 0.7% below the original estimate, and (iii) the twofold increase in input resolution decreases the average performance by about 0.5%. We conclude by arguing that further exploration of shallower CNN architectures may be beneficial in order to improve the generalizability of CNN-based exoplanet detection across surveys.