Photometric Search for Exomoons by using Convolutional Neural Networks

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.

arXiv comment11 pages, 4 figures

References in corpus (24)

• TensorFlow: A system for large-scale machine learning
• The PLATO 2.0 Mission
• REBOUND: An open-source multi-purpose N-body code for collisional dynamics
• Mass-Radius Relationships for Solid Exoplanets
• The Hunt for Exomoons with Kepler (HEK): I. Description of a New Observational Project
• Evidence for a Large Exomoon Orbiting Kepler-1625b
• Evidence of an Upper Bound on the Masses of Planets and its Implications for Giant Planet Formation
• Exomoon habitability constrained by illumination and tidal heating
• The Roche limit for close-orbiting planets: Minimum density, composition constraints, and application to the 4.2-hour planet KOI 1843.03
• Automatic Classification of Kepler Planetary Transit Candidates
• The Hunt for Exomoons with Kepler (HEK): V. A Survey of 41 Planetary Candidates for Exomoons
• The potential for tidally heated icy and temperate moons around exoplanets
• Identifying Exoplanets with Deep Learning II: Two New Super-Earths Uncovered by a Neural Network in K2 Data
• An alternative interpretation of the exomoon candidate signal in the combined Kepler and Hubble data of Kepler-1625
• Rapid Classification of TESS Planet Candidates with Convolutional Neural Networks
• Planet-Planet Occultations in TRAPPIST-1 and Other Exoplanet Systems
• How to determine an exomoon's sense of orbital motion
• Revisiting the exomoon candidate signal around Kepler-1625b
• SIDRA: a blind algorithm for signal detection in photometric surveys
• Classifying Exoplanet Candidates with Convolutional Neural Networks: Application to the Next Generation Transit Survey
• Next Generation of Telescopes or Dynamics Required to Determine if Exo-Moons have Prograde or Retrograde Orbits
• The subsurface habitability of small, icy exomoons
• Identifying Potential Exomoon Signals with Convolutional Neural Networks
• Astrophysical Simulations and Data Analyses on the Formation, Detection, and Habitability of Moons Around Extrasolar Planets