Rapid Classification of TESS Planet Candidates with Convolutional Neural Networks

Abstract

Accurately and rapidly classifying exoplanet candidates from transit surveys is a goal of growing importance as the data rates from space-based survey missions increases. This is especially true for NASA's TESS mission which generates thousands of new candidates each month. Here we created the first deep learning model capable of classifying TESS planet candidates. We adapted the neural network model of Ansdell et al. (2018) to TESS data. We then trained and tested this updated model on 4 sectors of high-fidelity, pixel-level simulations data created using the Lilith simulator and processed using the full TESS SPOC pipeline. We find our model performs very well on our simulated data, with 97% average precision and 92% accuracy on planets in the 2-class model. This accuracy is also boosted by another ~4% if planets found at the wrong periods are included. We also performed 3- and 4-class classification of planets, blended & target eclipsing binaries, and non-astrophysical false positives, which have slightly lower average precision and planet accuracies, but are useful for follow-up decisions. When applied to real TESS data, 61% of TCEs coincident with currently published TOIs are recovered as planets, 4% more are suggested to be EBs, and we propose a further 200 TCEs as planet candidates.

arXiv comment11 pages, 10 figures, Submitted to A&A

References in corpus (25)

• Astropy: A Community Python Package for Astronomy
• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• Planetary Candidates Observed by Kepler, III: Analysis of the First 16 Months of Data
• The TESS Input Catalog and Candidate Target List
• The Transiting Exoplanet Survey Satellite: Simulations of planet detections and astrophysical false positives
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Kepler Data Validation I -- Architecture, Diagnostic Tests, and Data Products for Vetting Transiting Planet Candidates
• A Revised Exoplanet Yield from the Transiting Exoplanet Survey Satellite (TESS)
• Planetary Candidates Observed by Kepler VI: Planet Sample from Q1-Q16 (47 Months)
• Kepler Data Validation II -- Transit Model Fitting and Multiple-Planet Search
• Planetary Candidates Observed by Kepler IV: Planet Sample From Q1-Q8 (22 Months)
• TESS Discovery of a Transiting Super-Earth in the $\pi$ Mensae System
• Planetary Candidates Observed by Kepler V: Planet Sample from Q1-Q12 (36 Months)
• TESS Discovery of an ultra-short-period planet around the nearby M dwarf LHS 3844
• Planet Hunters: The First Two Planet Candidates Identified by the Public using the Kepler Public Archive Data
• Automatic Classification of Kepler Planetary Transit Candidates
• TESS full orbital phase curve of the WASP-18b system
• HD 202772A B: A Transiting Hot Jupiter Around A Bright, Mildly Evolved Star In A Visual Binary Discovered By Tess
• Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning
• Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys
• Shallow Transits - Deep Learning I: Feasibility Study of Deep Learning to Detect Periodic Transits of Exoplanets
• Chi-Square Discriminators for Transiting Planet Detection in Kepler Data
• Identifying False Alarms in the Kepler Planet Candidate Catalog
• A TESS Dress Rehearsal: Planetary Candidates and Variables from K2 Campaign 17
• HATS-31b Through HATS-35b: Five Transiting Hot Jupiters Discovered by the HATSouth Survey

Cited by in corpus (26)

• ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier that Validates 301 New Exoplanets
• Exoplanet Validation with Machine Learning: 50 new validated Kepler planets
• Alleviating the transit timing variation bias in transit surveys. I. RIVERS: Method and detection of a pair of resonant super-Earths around Kepler-1705
• The evolution of barred galaxies in the EAGLE simulations
• Transit least-squares survey IV. Earth-like transiting planets expected from the PLATO mission
• Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data
• Identifying Exoplanets with Deep Learning. V. Improved Light Curve Classification for TESS Full Frame Image Observations
• Automated identification of transiting exoplanet candidates in NASA Transiting Exoplanets Survey Satellite (TESS) data with machine learning methods
• Detrending Exoplanetary Transit Light Curves with Long Short-Term Memory Networks
• Identify Light-Curve Signals with Deep Learning Based Object Detection Algorithm. I. Transit Detection
• Nigraha: Machine-learning based pipeline to identify and evaluate planet candidates from TESS
• Distinguishing a planetary transit from false positives: a Transformer-based classification for planetary transit signals
• AGN X-ray Spectroscopy with Neural Networks
• Identifying Exoplanets with Deep Learning. IV. Removing Stellar Activity Signals from Radial Velocity Measurements Using Neural Networks
• DIAmante TESS AutoRegressive Planet Search (DTARPS): I. Analysis of 0.9 Million Light Curves
• Identifying Potential Exomoon Signals with Convolutional Neural Networks
• The GPU Phase Folding and Deep Learning Method for Detecting Exoplanet Transits
• ExoplANNET: A deep learning algorithm to detect and identify planetary signals in radial velocity data
• Hunting for exocomet transits in the TESS database using the Random Forest method
• Companion Mass Limits for 17 Binary Systems Obtained with Binary Differential Imaging and MagAO/Clio
• Exoplanet Transit Candidate Identification in TESS Full-Frame Images via a Transformer-Based Algorithm
• Heartbeat Stars Recognition Based on Recurrent Neural Networks: Method and Validation
• Photometric Search for Exomoons by using Convolutional Neural Networks
• Radio Galaxy Zoo: Giant Radio Galaxy Classification using Multi-Domain Deep Learning
• Multiband neural network classification of ZTF light curves as LSST proxies
• Shallow Transits -- Deep Learning II: Identify Individual Exoplanetary Transits in Red Noise using Deep Learning