Automatic vetting of planet candidates from ground based surveys: Machine learning with NGTS

Abstract

State of the art exoplanet transit surveys are producing ever increasing quantities of data. To make the best use of this resource, in detecting interesting planetary systems or in determining accurate planetary population statistics, requires new automated methods. Here we describe a machine learning algorithm that forms an integral part of the pipeline for the NGTS transit survey, demonstrating the efficacy of machine learning in selecting planetary candidates from multi-night ground based survey data. Our method uses a combination of random forests and self-organising-maps to rank planetary candidates, achieving an AUC score of 97.6\% in ranking 12368 injected planets against 27496 false positives in the NGTS data. We build on past examples by using injected transit signals to form a training set, a necessary development for applying similar methods to upcoming surveys. We also make the \texttt{autovet} code used to implement the algorithm publicly accessible. \texttt{autovet} is designed to perform machine learned vetting of planetary candidates, and can utilise a variety of methods. The apparent robustness of machine learning techniques, whether on space-based or the qualitatively different ground-based data, highlights their importance to future surveys such as TESS and PLATO and the need to better understand their advantages and pitfalls in an exoplanetary context.

arXiv commentAccepted for publication in MNRAS, 15 pages

References in corpus (57)

• Scikit-learn: Machine Learning in Python
• Analytic Lightcurves for Planetary Transit Searches
• Detection of Planetary Transits Across a Sun-like Star
• The WASP Project and the SuperWASP Cameras
• The false positive rate of Kepler and the occurrence of planets
• batman: BAsic Transit Model cAlculatioN in Python
• Kepler Presearch Data Conditioning II - A Bayesian Approach to Systematic Error Correction
• A box-fitting algorithm in the search for periodic transits
• Kepler Presearch Data Conditioning I - Architecture and Algorithms for Error Correction in Kepler Light Curves
• Wide-field millimagnitude photometry with HAT: A Tool for Extra-solar Planet Detection
• The Transiting Exoplanet Survey Satellite: Simulations of planet detections and astrophysical false positives
• Correcting systematic effects in a large set of photometric lightcurves
• ELODIE metallicity-biased search for transiting Hot Jupiters II. A very hot Jupiter transiting the bright K star HD189733
• TrES-1: The Transiting Planet of a Bright K0V Star
• False positive probabilties for all Kepler Objects of Interest: 1284 newly validated planets and 428 likely false positives
• The Kilodegree Extremely Little Telescope (KELT): A Small Robotic Telescope for Large-Area Synoptic Surveys
• Efficient identification of exoplanetary transit candidates from SuperWASP light curves
• A temperate rocky super-Earth transiting a nearby cool star
• On Machine-Learned Classification of Variable Stars with Sparse and Noisy Time-Series Data
• WASP-1b and WASP-2b: Two new transiting exoplanets detected with SuperWASP and SOPHIE
• HAT-P-1b: A Large-Radius, Low-Density Exoplanet Transiting one Member of a Stellar Binary
• 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)
• A fast hybrid algorithm for exoplanetary transit searches
• HATSouth: a global network of fully automated identical wide-field telescopes
• 197 Candidates and 104 Validated Planets in K2's First Five Fields
• PASTIS: Bayesian extrasolar planet validation. I. General framework, models, and performance
• The XO Project: Searching for Transiting Extra-solar Planet Candidates
• Transiting hot Jupiters from WASP-South, Euler and TRAPPIST: WASP-95b to WASP-101b
• Validation of Twelve Small Kepler Transiting Planets in the Habitable Zone
• Searching for Exoplanets Using Artificial Intelligence
• Predicting Solar Flares Using SDO/HMI Vector Magnetic Data Product and Random Forest Algorithm
• Using Machine Learning for Discovery in Synoptic Survey Imaging
• Global stellar variability study in the field-of-view of the Kepler satellite
• SOMz: photometric redshift PDFs with self organizing maps and random atlas
• K2 Variable Catalogue II: Machine Learning Classification of Variable Stars and Eclipsing Binaries in K2 Fields 0-4
• Automatic Classification of Kepler Planetary Transit Candidates
• Construction of a Calibrated Probabilistic Classification Catalog: Application to 50k Variable Sources in the All-Sky Automated Survey
• HATNet Field G205: Follow-Up Observations of 28 Transiting-Planet candidates and Confirmation of the Planet HAT-P-8b
• WASP-South transiting exoplanets: WASP-130b, WASP-131b, WASP-132b, WASP-139b, WASP-140b, WASP-141b & WASP-142b
• A Machine Learning Technique to Identify Transit Shaped Signals
• The automated classification of astronomical lightcurves using Kohonen self-organising maps
• DONUTS: A science frame autoguiding algorithm with sub-pixel precision, capable of guiding on defocused stars
• Rate and nature of false positives in the CoRoT exoplanet search
• Automated classification of variable stars for ASAS 1-2 data
• Supervised detection of anomalous light-curves in massive astronomical catalogs
• Transit Shapes and Self Organising Maps as a Tool for Ranking Planetary Candidates: Application to Kepler and K2
• Automated Classification of Periodic Variable Stars detected by the Wide-field Infrared Survey Explorer
• Automated classification of variable stars in the asteroseismology program of the Kepler space mission
• Automated Probabilistic Classification of Transients and Variables
• Centroid vetting of transiting planet candidates from the Next Generation Transit Survey
• SIDRA: a blind algorithm for signal detection in photometric surveys
• Disproval of the validated planets K2-78b, K2-82b, and K2-92b
• Three statistically validated K2 transiting warm Jupiter exoplanets confirmed as low-mass stars
• Photometric Classification of quasars from RCS-2 using Random Forest
• A New Yield Simulator for Transiting Planets and False Positives: Application to the Next Generation Transit Survey
• The Next Generation Transit Survey - Prototyping Phase

Cited by in corpus (20)

• Transit Least Squares: Optimized transit detection algorithm to search for periodic transits of small planets
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• A second terrestrial planet orbiting the nearby M dwarf LHS 1140
• 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
• Exoplanet Validation with Machine Learning: 50 new validated Kepler planets
• Classifying Exoplanet Candidates with Convolutional Neural Networks: Application to the Next Generation Transit Survey
• AutoRegressive Planet Search: Application to the Kepler Mission
• AutoRegressive Planet Search: Methodology
• Transit least-squares survey IV. Earth-like transiting planets expected from the PLATO mission
• Transit least-squares survey -- II. Discovery and validation of 17 new sub- to super-Earth-sized planets in multi-planet systems from K2
• Identifying Exoplanets with Deep Learning. V. Improved Light Curve Classification for TESS Full Frame Image Observations
• Nigraha: Machine-learning based pipeline to identify and evaluate planet candidates from TESS
• TSARDI: a Machine Learning data rejection algorithm for transiting exoplanet light curves
• Distinguishing a planetary transit from false positives: a Transformer-based classification for planetary transit signals
• DIAmante TESS AutoRegressive Planet Search (DTARPS): I. Analysis of 0.9 Million Light Curves
• ExoplANNET: A deep learning algorithm to detect and identify planetary signals in radial velocity data
• DIAmante TESS AutoRegressive Planet Search (DTARPS): II. Hundreds of New TESS Candidate Exoplanets
• DART-Vetter: A Deep LeARning Tool for automatic triage of exoplanet candidates
• Panopticon: a novel deep learning model to detect single transit events with no prior data filtering in PLATO light curves