Identifying Planetary Transit Candidates in TESS Full-Frame Image Light Curves via Convolutional Neural Networks

Abstract

The Transiting Exoplanet Survey Satellite (TESS) mission measured light from stars in ~75% of the sky throughout its two year primary mission, resulting in millions of TESS 30-minute cadence light curves to analyze in the search for transiting exoplanets. To search this vast data trove for transit signals, we aim to provide an approach that is both computationally efficient and produces highly performant predictions. This approach minimizes the required human search effort. We present a convolutional neural network, which we train to identify planetary transit signals and dismiss false positives. To make a prediction for a given light curve, our network requires no prior transit parameters identified using other methods. Our network performs inference on a TESS 30-minute cadence light curve in ~5ms on a single GPU, enabling large scale archival searches. We present 181 new planet candidates identified by our network, which pass subsequent human vetting designed to rule out false positives. Our neural network model is additionally provided as open-source code for public use and extension.

arXiv commentUpdated to match AJ revision

References in corpus (21)

• Array Programming with NumPy
• Astropy: A Community Python Package for Astronomy
• Gaia Data Release 2. Summary of the contents and survey properties
• The Transiting Exoplanet Survey Satellite
• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• Fast and scalable Gaussian process modeling with applications to astronomical time series
• A box-fitting algorithm in the search for periodic transits
• Achieving better than 1 minute accuracy in the Heliocentric and Barycentric Julian Dates
• The NASA Exoplanet Archive: Data and Tools for Exoplanet Research
• The TESS Input Catalog and Candidate Target List
• The Transiting Exoplanet Survey Satellite: Simulations of planet detections and astrophysical false positives
• A Revised Exoplanet Yield from the Transiting Exoplanet Survey Satellite (TESS)
• EVEREST: Pixel Level Decorrelation of K2 Light curves
• eleanor: An open-source tool for extracting light curves from the TESS Full-Frame Images
• Detection of Hundreds of New Planet Candidates and Eclipsing Binaries in K2 Campaigns 0-8
• Discovery and Vetting of Exoplanets I: Benchmarking K2 Vetting Tools
• Two intermediate-mass transiting brown dwarfs from the TESS mission
• Transit Shapes and Self Organising Maps as a Tool for Ranking Planetary Candidates: Application to Kepler and K2
• HAT-P-67b: An Extremely Low Density Saturn Transiting an F-Subgiant Confirmed via Doppler Tomography
• Discovery of XO-6b: a hot Jupiter transiting a fast rotating F5 star on an oblique orbit
• Photometry of 10 Million Stars from the First Two Years of TESS Full Frame Images

Cited by in corpus (13)

• The TESS Grand Unified Hot Jupiter Survey. II. Twenty New Giant Planets
• The TESS Grand Unified Hot Jupiter Survey. I. Ten TESS Planets
• The TESS Triple-9 Catalog: 999 uniformly vetted candidate exoplanets
• Identify Light-Curve Signals with Deep Learning Based Object Detection Algorithm. I. Transit Detection
• The TESS Triple-9 Catalog II: a new set of 999 uniformly-vetted exoplanet candidates
• DIAmante TESS AutoRegressive Planet Search (DTARPS): I. Analysis of 0.9 Million Light Curves
• The GPU Phase Folding and Deep Learning Method for Detecting Exoplanet Transits
• DIAmante TESS AutoRegressive Planet Search (DTARPS): II. Hundreds of New TESS Candidate Exoplanets
• Short-Period Variables in TESS Full-Frame Image Light Curves Identified via Convolutional Neural Networks
• Confirmation of four hot Jupiters detected by TESS using follow-up spectroscopy from MaHPS at Wendelstein together with NEID and TRES
• Exoplanet Transit Candidate Identification in TESS Full-Frame Images via a Transformer-Based Algorithm
• Migration and Evolution of giant ExoPlanets (MEEP) II: Super-Jupiters and Lithium-rich Host Stars
• The Visual Survey Group: A Decade of Hunting Exoplanets and Unusual Stellar Events with Space-Based Telescopes