The Library

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

Tools

Armstrong, David J., Günther,, Maximilian N. , McCormac, J. J., Smith, Alexis M. S., Bayliss, Daniel D. R., Bouchy, François , Burleigh, Matthew R., Casewell, Sarah, Eigmüller, Philipp , Gillen, Edward et al.

(2018) Automatic vetting of planet candidates from ground based surveys : machine learning with NGTS. Monthly Notices of the Royal Astronomical Society, 478 (3). pp. 4225-4237. doi:10.1093/mnras/sty1313

Preview

PDF
WRAP-automatic-vetting-planet-candidates-surveys-machine-learning-Armstrong-2018.pdf - Accepted Version - Requires a PDF viewer.
Download (1484Kb) | Preview

Official URL: https://doi.org/10.1093/mnras/sty1313

Request Changes to record.

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 autovet code used to implement the algorithm publicly accessible. 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.

Item Type:

Journal Article

Subjects:

Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
Q Science > QB Astronomy

Divisions:

Faculty of Science > Physics

Library of Congress Subject Headings (LCSH):

Extrasolar planets, Astronomy -- Data processing, Machine learning, Algorithms

Journal or Publication Title:

Monthly Notices of the Royal Astronomical Society

Publisher:

Oxford University Press

ISSN:

0035-8711

Official Date:

21 August 2018

Dates:

Date	Event
21 August 2018	Published
18 May 2018	Available
14 May 2018	Accepted

Volume:

478

Number:

Page Range:

pp. 4225-4237

DOI:

10.1093/mnras/sty1313

Status:

Peer Reviewed

Publication Status:

Published

Publisher Statement:

This article has been published in a revised form in Monthly Notices of the Royal Astronomical Society https://doi.org/10.1093/mnras/sty1313. This version is free to view and download for private research and study only. Not for re-distribution, re-sale or use in derivative works. © 2018 The Author(s) Published by Oxford University Press on behalf of the Royal Astronomical Society

Access rights to Published version:

Restricted or Subscription Access

RIOXX Funder/Project Grant:

Project/Grant ID	RIOXX Funder Name	Funder ID
ST/M001962/1	[STFC] Science and Technology Facilities Council	http://dx.doi.org/10.13039/501100000271
ST/P000495/1	[STFC] Science and Technology Facilities Council	http://dx.doi.org/10.13039/501100000271
1490409	[STFC] Science and Technology Facilities Council	http://dx.doi.org/10.13039/501100000271
UNSPECIFIED	Isaac Newton Trust	http://dx.doi.org/10.13039/501100004815
UNSPECIFIED	[FONDECYT] Fondo Nacional de Desarrollo Científico y Tecnológico	http://dx.doi.org/10.13039/501100002850
UNSPECIFIED	[CONICYT] Comisión Nacional de Investigación Científica y Tecnológica	http://dx.doi.org/10.13039/501100002848