elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Classifying exoplanet candidates with convolutional neural networks: application to the Next Generation Transit Survey

Chaushev, Alexander and Raynard, Liam and Goad, Michael R. and Eigmüller, Philipp and Armstrong, David J. and Briegal, Joshua T. and Burleigh, Matthew R. and Casewell, Sarah L. and Gill, Samuel and Jenkins, James S. and Nielsen, Louise D. and Watson, Christopher A. and West, Richard G. and Wheatley, Peter J. and Udry, Stephane and Vines, Jose I. (2019) Classifying exoplanet candidates with convolutional neural networks: application to the Next Generation Transit Survey. Monthly Notices of the Royal Astronomical Society, 488 (4), pp. 5232-5250. Oxford University Press. DOI: 10.1093/mnras/stz2058 ISSN 0035-8711

[img] PDF - Published version
12MB

Abstract

Vetting of exoplanet candidates in transit surveys is a manual process, which suffers from a large number of false positives and a lack of consistency. Previous work has shown that convolutional neural networks (CNN) provide an efficient solution to these problems. Here, we apply a CNN to classify planet candidates from the Next Generation Transit Survey (NGTS). For training data sets we compare both real data with injected planetary transits and fully simulated data, as well as how their different compositions affect network performance. We show that fewer hand labelled light curves can be utilized, while still achieving competitive results. With our best model, we achieve an area under the curve (AUC) score of (95.6± {0.2}){{ per cent}} and an accuracy of (88.5± {0.3}){{ per cent}} on our unseen test data, as well as (76.5± {0.4}){{ per cent}} and (74.6± {1.1}){{ per cent}} in comparison to our existing manual classifications. The neural network recovers 13 out of 14 confirmed planets observed by NGTS, with high probability. We use simulated data to show that the overall network performance is resilient to mislabelling of the training data set, a problem that might arise due to unidentified, low signal-to-noise transits. Using a CNN, the time required for vetting can be reduced by half, while still recovering the vast majority of manually flagged candidates. In addition, we identify many new candidates with high probabilities which were not flagged by human vetters.

Item URL in elib:https://elib.dlr.de/131546/
Document Type:Article
Title:Classifying exoplanet candidates with convolutional neural networks: application to the Next Generation Transit Survey
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Chaushev, AlexanderCenter for Astronomy and Astrophysics, TU Berlin, Hardenbergstr. 36, D-10623 Berlin, GermanyUNSPECIFIED
Raynard, LiamDepartment of Physics and Astronomy, University of Leicester, University Road, Leicester LE1 7RH, UKhttps://orcid.org/0000-0001-6472-9122
Goad, Michael R.Department of Physics and Astronomy, University of Leicester, University Road, Leicester LE1 7RH, UKUNSPECIFIED
Eigmüller, PhilippPhilipp.Eigmueller (at) dlr.dehttps://orcid.org/0000-0003-4096-0594
Armstrong, David J.Department of Physics, University of Warwick, Gibbet Hill Road, Coventry CV4 7AL, UK Centre for Exoplanets and Habitability, University of Warwick, Gibbet Hill Road, Coventry CV4 7AL, UKhttps://orcid.org/0000-0002-5080-4117
Briegal, Joshua T.Cavendish Laboratory, J.J. Thomson Avenue, Cambridge CB3 0HE, UKUNSPECIFIED
Burleigh, Matthew R.Department of Physics and Astronomy, University of Leicester, University Road, Leicester LE1 7RH, UKUNSPECIFIED
Casewell, Sarah L.Department of Physics and Astronomy, University of Leicester, University Road, Leicester LE1 7RH, UKUNSPECIFIED
Gill, SamuelDepartment of Physics, University of Warwick, Gibbet Hill Road, Coventry CV4 7AL, UK Centre for Exoplanets and Habitability, University of Warwick, Gibbet Hill Road, Coventry CV4 7AL, UKUNSPECIFIED
Jenkins, James S.Departamento de Astronomia, Universidad de Chile, Casilla 36-D, Santiago, Chile; Centro de Astrofísica y Tecnologías Afines (CATA), Casilla 36-D, Santiago, ChileUNSPECIFIED
Nielsen, Louise D.Observatoire Astronomique de l'Université de Genève, 51 Ch. des Maillettes, CH-1290 Versoix, SwitzerlandUNSPECIFIED
Watson, Christopher A.Astrophysics Research Centre, School of Mathematics and Physics, Queen's University Belfast, Belfast BT7 1NN, UKUNSPECIFIED
West, Richard G.Department of Physics, University of Warwick, Gibbet Hill Road, Coventry CV4 7AL, UK; Centre for Exoplanets and Habitability, University of Warwick, Gibbet Hill Road, Coventry CV4 7AL, UKUNSPECIFIED
Wheatley, Peter J.University of Warwick, Department of Physics, Gibbet Hill Road, Coventry, CV4 7AL, UKUNSPECIFIED
Udry, StephaneObservatoire Astronomique de l'Université de Genève, 51 Ch. des Maillettes, CH-1290 Versoix, SwitzerlandUNSPECIFIED
Vines, Jose I.Departamento de Astronomía, Universidad de Chile, Casilla 36-D, Santiago, ChileUNSPECIFIED
Date:October 2019
Journal or Publication Title:Monthly Notices of the Royal Astronomical Society
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
Volume:488
DOI :10.1093/mnras/stz2058
Page Range:pp. 5232-5250
Publisher:Oxford University Press
ISSN:0035-8711
Status:Published
Keywords:methods: data analysis, techniques: photometric, planets and satellites: detection, Astrophysics - Earth and Planetary Astrophysics, Astrophysics - Instrumentation and Methods for Astrophysics
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Space Science and Exploration
DLR - Research area:Raumfahrt
DLR - Program:R EW - Erforschung des Weltraums
DLR - Research theme (Project):R - Project PLATO
Location: Berlin-Adlershof
Institutes and Institutions:Institute of Planetary Research > Extrasolar Planets and Atmospheres
Deposited By: Eigmüller, Dr. Philipp
Deposited On:02 Dec 2019 15:01
Last Modified:02 Dec 2019 15:01

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.