Identifying Potential Exomoon Signals with Convolutional Neural Networks

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.

arXiv comment14 pages, 13 figures, 1 table. Accepted for publication in Monthly Notices of the Royal Astronomical Society, 15 September 2021

References in corpus (30)

• Array Programming with NumPy
• Astropy: A Community Python Package for Astronomy
• The NumPy array: a structure for efficient numerical computation
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Efficient, uninformative sampling of limb darkening coefficients for two-parameter laws
• Revised Stellar Properties of Kepler Targets for the Quarter 1-16 Transit Detection Run
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Selection, Prioritization, and Characteristics of Kepler Target Stars
• Stellar Limb-Darkening Coefficients for CoRot and Kepler
• Transit Timing Observations from Kepler. IX. Catalog of the Full Long-Cadence Data Set
• Transit Timing Observations from Kepler. VIII Catalog of Transit Timing Measurements of the First Twelve Quarters
• Evidence for a Large Exomoon Orbiting Kepler-1625b
• Photometric Amplitude Distribution of Stellar Rotation of Kepler KOIs-Indication for Spin-Orbit Alignment of Cool Stars and High Obliquity for Hot Stars
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• Searching for Exoplanets Using Artificial Intelligence
• HEK VI: On the Dearth of Galilean Analogs in Kepler and the Exomoon Candidate Kepler-1625b I
• The Hunt for Exomoons with Kepler (HEK): II. Analysis of Seven Viable Satellite-Hosting Planet Candidates
• The Hunt for Exomoons with Kepler (HEK): V. A Survey of 41 Planetary Candidates for Exomoons
• On the detection of Exomoons: A search in Kepler data for the orbital sampling effect and the scatter peak
• Identifying Exoplanets with Deep Learning III: Automated Triage and Vetting of TESS Candidates
• Identifying Exoplanets with Deep Learning II: Two New Super-Earths Uncovered by a Neural Network in K2 Data
• The fate of moons of close-in giant exoplanets
• Shallow Transits - Deep Learning I: Feasibility Study of Deep Learning to Detect Periodic Transits of Exoplanets
• Rapid Classification of TESS Planet Candidates with Convolutional Neural Networks
• Resonant Removal of Exomoons During Planetary Migration
• LUNA: An algorithm for generating dynamic planet-moon transits
• Modeling the Orbital Sampling Effect of Extrasolar Moons
• Transits of Inclined Exomoons - Hide and Seek and an Application to Kepler-1625
• Impossible moons -- Transit timing effects that cannot be due to an exomoon
• Detection of exomoons in simulated light curves with a regularized convolutional neural network

Cited by in corpus (3)

• Exomoons as sources of white dwarf pollution
• Exploring Long-period Architectures: Four New Planet Candidates from Kepler with Periods >342 days
• Photometric Search for Exomoons by using Convolutional Neural Networks