Identifying Exoplanets with Deep Learning II: Two New Super-Earths Uncovered by a Neural Network in K2 Data

Abstract

For years, scientists have used data from NASA's Kepler Space Telescope to look for and discover thousands of transiting exoplanets. In its extended K2 mission, Kepler observed stars in various regions of sky all across the ecliptic plane, and therefore in different galactic environments. Astronomers want to learn how the population of exoplanets are different in these different environments. However, this requires an automatic and unbiased way to identify the exoplanets in these regions and rule out false positive signals that mimic transiting planet signals. We present a method for classifying these exoplanet signals using deep learning, a class of machine learning algorithms that have become popular in fields ranging from medical science to linguistics. We modified a neural network previously used to identify exoplanets in the Kepler field to be able to identify exoplanets in different K2 campaigns, which range in galactic environments. We train a convolutional neural network, called AstroNet-K2, to predict whether a given possible exoplanet signal is really caused by an exoplanet or a false positive. AstroNet-K2 is highly successful at classifying exoplanets and false positives, with accuracy of 98% on our test set. It is especially efficient at identifying and culling false positives, but for now, still needs human supervision to create a complete and reliable planet candidate sample. We use AstroNet-K2 to identify and validate two previously unknown exoplanets. Our method is a step towards automatically identifying new exoplanets in K2 data and learning how exoplanet populations depend on their galactic birthplace.

arXiv comment18 pages, 9 figures, 3 tables, accepted to AJ. The full version of Table 3 is included in the LaTeX package

References in corpus (48)

• emcee: The MCMC Hammer
• Gaia Data Release 2. Summary of the contents and survey properties
• The Gaia mission
• Analytic Lightcurves for Planetary Transit Searches
• The K2 Mission: Characterization and Early results
• batman: BAsic Transit Model cAlculatioN in Python
• A box-fitting algorithm in the search for periodic transits
• Efficient, uninformative sampling of limb darkening coefficients for two-parameter laws
• On the Unique Solution of Planet and Star Parameters from an Extrasolar Planet Transit Light Curve
• Most 1.6 Earth-Radius Planets are not Rocky
• A Technique for Extracting Highly Precise Photometry for the Two-Wheeled Kepler Mission
• Constraining the Age-Activity Relation for Cool Stars: The SDSS DR5 Low-Mass Star Spectroscopic Sample
• A disintegrating minor planet transiting a white dwarf
• 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
• 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
• Three regimes of extrasolar planets inferred from host star metallicities
• An Efficient Automated Validation Procedure for Exoplanet Transit Candidates
• Planetary Candidates Observed by Kepler. VII. The First Fully Uniform Catalog Based on The Entire 48 Month Dataset (Q1-Q17 DR24)
• Planetary Candidates from the First Year of the K2 Mission
• 197 Candidates and 104 Validated Planets in K2's First Five Fields
• TESS Discovery of a Transiting Super-Earth in the $\pi$ Mensae System
• Zodiacal Exoplanets in Time (ZEIT) III: A short-period planet orbiting a pre-main-sequence star in the Upper Scorpius OB Association
• 275 Candidates and 149 Validated Planets Orbiting Bright Stars in K2 Campaigns 0-10
• The K2-ESPRINT Project. I. Discovery of the Disintegrating Rocky Planet K2-22b with a Cometary Head and Leading Tail
• Searching for Exoplanets Using Artificial Intelligence
• Automatic Classification of Kepler Planetary Transit Candidates
• Transfer learning for galaxy morphology from one survey to another
• Exoplanets around Low-mass Stars Unveiled by K2
• Zodiacal Exoplanets in Time (ZEIT) VIII: A Two Planet System in Praesepe from K2 Campaign 16
• Chemical gradients in the Milky Way from the RAVE data. I. Dwarf stars
• K2 Discovers a Busy Bee: An Unusual Transiting Neptune Found in the Beehive Cluster
• Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning
• 60 Validated Planets from K2 Campaigns 5-8
• 44 Validated Planets from K2 Campaign 10
• Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys
• A Machine Learning Technique to Identify Transit Shaped Signals
• Qatar-2: A K dwarf orbited by a transiting hot Jupiter and a more massive companion in an outer orbit
• The occurrence of planets and other substellar bodies around white dwarfs using K2
• Shallow Transits - Deep Learning I: Feasibility Study of Deep Learning to Detect Periodic Transits of Exoplanets
• A Compact Multi-Planet System With A Significantly Misaligned Ultra Short Period Planet
• Transit Shapes and Self Organising Maps as a Tool for Ranking Planetary Candidates: Application to Kepler and K2
• Three Small Planets Transiting a Hyades Star
• Zodiacal Exoplanets in Time (ZEIT) VII: A Temperate Candidate Super-Earth in the Hyades Cluster
• Automatic vetting of planet candidates from ground based surveys: Machine learning with NGTS
• Supervised Learning Detection of Sixty Non-Transiting Hot Jupiter Candidates
• Probing TRAPPIST-1-like systems with K2

Cited by in corpus (33)

• ExoMiner: A Highly Accurate and Explainable Deep Learning Classifier that Validates 301 New Exoplanets
• Identifying Exoplanets with Deep Learning III: Automated Triage and Vetting of TESS Candidates
• A Hybrid Deep Learning Approach to Cosmological Constraints From Galaxy Redshift Surveys
• Exoplanet Validation with Machine Learning: 50 new validated Kepler planets
• Classifying Exoplanet Candidates with Convolutional Neural Networks: Application to the Next Generation Transit Survey
• 37 New Validated Planets in Overlapping K2 Campaigns
• Scaling K2. IV. A Uniform Planet Sample for Campaigns 1-8 and 10-18
• Scaling K2. II. Assembly of a Fully Automated C5 Planet Candidate Catalog Using EDI-Vetter
• The Random Transiter -- EPIC 249706694/HD 139139
• 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
• A Machine Learning approach for correcting radial velocities using physical observables
• 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
• Improving Earth-like planet detection in radial velocity using deep learning
• The K2 & TESS Synergy II: Revisiting 26 systems in the TESS Primary Mission
• Identifying Exoplanets with Deep Learning. IV. Removing Stellar Activity Signals from Radial Velocity Measurements Using Neural Networks
• The GPU Phase Folding and Deep Learning Method for Detecting Exoplanet Transits
• Identifying Potential Exomoon Signals with Convolutional Neural Networks
• Searching for Possible Exoplanet Transits from BRITE Data through a Machine Learning Technique
• ExoplANNET: A deep learning algorithm to detect and identify planetary signals in radial velocity data
• Using a neural network approach to accelerate disequilibrium chemistry calculations in exoplanet atmospheres
• Search for exocomets transits in Kepler light curves: Ten new transits identified
• Unsupervised Domain Adaptation for Constraining Star Formation Histories
• DART-Vetter: A Deep LeARning Tool for automatic triage of exoplanet candidates
• Scaling K2. V. Statistical Validation of 60 New Exoplanets From K2 Campaigns 2-18
• TFAW survey II: 6 Newly Validated Planets and 13 Planet Candidates from K2
• Multiband neural network classification of ZTF light curves as LSST proxies
• Mimicking the halo-galaxy connection using machine learning
• Photometric Search for Exomoons by using Convolutional Neural Networks
• Shallow Transits -- Deep Learning II: Identify Individual Exoplanetary Transits in Red Noise using Deep Learning
• A one-armed CNN for exoplanet detection from light curves
• Panopticon: a novel deep learning model to detect single transit events with no prior data filtering in PLATO light curves