Exoplanet Validation with Machine Learning: 50 new validated Kepler planets

Abstract

Over 30% of the ~4000 known exoplanets to date have been discovered using 'validation', where the statistical likelihood of a transit arising from a false positive (FP), non-planetary scenario is calculated. For the large majority of these validated planets calculations were performed using the vespa algorithm (Morton et al. 2016). Regardless of the strengths and weaknesses of vespa, it is highly desirable for the catalogue of known planets not to be dependent on a single method. We demonstrate the use of machine learning algorithms, specifically a gaussian process classifier (GPC) reinforced by other models, to perform probabilistic planet validation incorporating prior probabilities for possible FP scenarios. The GPC can attain a mean log-loss per sample of 0.54 when separating confirmed planets from FPs in the Kepler threshold crossing event (TCE) catalogue. Our models can validate thousands of unseen candidates in seconds once applicable vetting metrics are calculated, and can be adapted to work with the active TESS mission, where the large number of observed targets necessitates the use of automated algorithms. We discuss the limitations and caveats of this methodology, and after accounting for possible failure modes newly validate 50 Kepler candidates as planets, sanity checking the validations by confirming them with vespa using up to date stellar information. Concerning discrepancies with vespa arise for many other candidates, which typically resolve in favour of our models. Given such issues, we caution against using single-method planet validation with either method until the discrepancies are fully understood.

arXiv commentAccepted by MNRAS (advance access version: https://academic.oup.com/mnras/advance-article-abstract/doi/10.1093/mnras/staa2498/5894933)

References in corpus (56)

• Scikit-learn: Machine Learning in Python
• Gaia Data Release 2. Summary of the contents and survey properties
• The Transiting Exoplanet Survey Satellite
• Variational Inference: A Review for Statisticians
• A Survey of Stellar Families: Multiplicity of Solar-Type Stars
• The K2 Mission: Characterization and Early results
• The WASP Project and the SuperWASP Cameras
• Mind your Ps and Qs: the Interrelation between Period (P) and Mass-ratio (Q) Distributions of Binary Stars
• SparsePak: A Formatted Fiber Field Unit for The WIYN Telescope Bench Spectrograph. I. Design, Construction, and Calibration
• Kepler Presearch Data Conditioning II - A Bayesian Approach to Systematic Error Correction
• The NASA Exoplanet Archive: Data and Tools for Exoplanet Research
• Kepler Input Catalog: Photometric Calibration and Stellar Classification
• Kepler Presearch Data Conditioning I - Architecture and Algorithms for Error Correction in Kepler Light Curves
• Overview of the Kepler Science Processing Pipeline
• Validation of Kepler's Multiple Planet Candidates. III: Light Curve Analysis & Announcement of Hundreds of New Multi-planet Systems
• False positive probabilties for all Kepler Objects of Interest: 1284 newly validated planets and 428 likely false positives
• Planetary Candidates Observed by Kepler. VIII. A Fully Automated Catalog With Measured Completeness and Reliability Based on Data Release 25
• The Kilodegree Extremely Little Telescope (KELT): A Small Robotic Telescope for Large-Area Synoptic Surveys
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Terrestrial Planet Occurrence Rates for the Kepler GK Dwarf Sample
• Kepler Data Validation I -- Architecture, Diagnostic Tests, and Data Products for Vetting Transiting Planet Candidates
• Revised Radii of Kepler Stars and Planets Using Gaia Data Release 2
• Revised Stellar Properties of Kepler Targets for the Q1-17 (DR25) Transit Detection Run
• The Next Generation Transit Survey (NGTS)
• SOPHIE velocimetry of Kepler transit candidates XVII. The physical properties of giant exoplanets within 400 days of period
• An Efficient Automated Validation Procedure for Exoplanet Transit Candidates
• On the Low False Positive Probabilities of Kepler Planet Candidates
• Validation of Kepler's Multiple Planet Candidates. II: Refined Statistical Framework and Descriptions of Systems of Special Interest
• PASTIS: Bayesian extrasolar planet validation. I. General framework, models, and performance
• System description and first light-curves of HAT, an autonomous observatory for variability search
• Vetting of 384 TESS Objects of Interest with TRICERATOPS and Statistical Validation of 12 Planet Candidates
• Validation of Twelve Small Kepler Transiting Planets in the Habitable Zone
• TESS Spots a Compact System of Super-Earths around the Naked-Eye Star HR 858
• Automatic Classification of Kepler Planetary Transit Candidates
• Measuring the Recoverability of Close Binaries in Gaia DR2 with the Robo-AO Kepler Survey
• Detection of Potential Transit Signals in 17 Quarters of Kepler Data: Results of the Final Kepler Mission Transiting Planet Search (DR25)
• Characterization of the L 98-59 multi-planetary system with HARPS: two confirmed terrestrial planets and a mass upper limit on the third
• Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning
• Improving the Accuracy of Planet Occurrence Rates from Kepler using Approximate Bayesian Computation
• 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
• Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys
• Discovery and Vetting of Exoplanets I: Benchmarking K2 Vetting Tools
• The contribution of secondary eclipses as astrophysical false positives to exoplanet transit surveys
• Rapid Classification of TESS Planet Candidates with Convolutional Neural Networks
• Transit Shapes and Self Organising Maps as a Tool for Ranking Planetary Candidates: Application to Kepler and K2
• Detection of Potential Transit Signals in 17 Quarters of Kepler Mission Data
• Chi-Square Discriminators for Transiting Planet Detection in Kepler Data
• Near-resonance in a system of sub-Neptunes from TESS
• Classifying Exoplanet Candidates with Convolutional Neural Networks: Application to the Next Generation Transit Survey
• Disproval of the validated planets K2-78b, K2-82b, and K2-92b
• AutoRegressive Planet Search: Application to the Kepler Mission
• Automatic vetting of planet candidates from ground based surveys: Machine learning with NGTS
• The Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC): Selection of a performance metric for classification probabilities balancing diverse science goals
• Re-Evaluating Small Long-Period Confirmed Planets From Kepler
• Two Super-Earths in the 3:2 MMR around KOI-1599

Cited by in corpus (17)

• Gaia DR3 astrometric orbit determination with Markov Chain Monte Carlo and Genetic Algorithms. Systems with stellar, substellar, and planetary mass companions
• ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier that Validates 301 New Exoplanets
• A PSF-based Approach to TESS High quality data Of Stellar clusters (PATHOS) -- IV. Candidate exoplanets around stars in open clusters: frequency and age-planetary radius distribution
• Alleviating the transit timing variation bias in transit surveys. I. RIVERS: Method and detection of a pair of resonant super-Earths around Kepler-1705
• Variational Inference as an alternative to MCMC for parameter estimation and model selection
• Automated identification of transiting exoplanet candidates in NASA Transiting Exoplanets Survey Satellite (TESS) data with machine learning methods
• Updated Catalog of Kepler Planet Candidates: Focus on Accuracy and Orbital Periods
• Multiplicity Boost Of Transit Signal Classifiers: Validation of 69 New Exoplanets Using The Multiplicity Boost of ExoMiner
• The AstraLux-TESS high-spatial resolution imaging survey. Search for stellar companions of 215 planet candidates from TESS
• Machine learning prediction for mean motion resonance behaviour -- The planar case
• exoMMR: a New Python Package to Confirm and Characterize Mean Motion Resonances
• YOUNG Star detrending for Transiting Exoplanet Recovery (YOUNGSTER) II: Using Self-Organising Maps to explore young star variability in Sectors 1-13 of TESS data
• K2-399 b is not a planet. The Saturn that wandered through the Neptune desert is actually a hierarchical eclipsing binary
• Large-step neural network for learning the symplectic evolution from partitioned data
• Studying habitability of the exoplanets Kepler-504 b, Kepler-315 b, and Kepler-315 c
• Exploring Long-period Architectures: Four New Planet Candidates from Kepler with Periods >342 days
• TFAW survey II: 6 Newly Validated Planets and 13 Planet Candidates from K2