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

David J. Armstrong, Maximilian N. Günther, James McCormac, Alexis M. S. Smith, Daniel Bayliss, François Bouchy, Matthew R. Burleigh, Sarah Casewell, Philipp Eigmüller, Edward Gillen, Michael R. Goad, Simon T. Hodgkin, James S. Jenkins, Tom Louden, Lionel Metrailler, Don Pollacco, Katja Poppenhaeger, Didier Queloz, Liam Raynard, Heike RauerStéphane Udry, Simon R. Walker, Christopher A. Watson, Richard G. West, Peter J. Wheatley

Research output: Contribution to journalArticlepeer-review

13 Citations (Scopus)
135 Downloads (Pure)


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.
Original languageEnglish
JournalMonthly Notices of the Royal Astronomical Society, Advance Access
Publication statusPublished - 18 May 2018


  • planets and satellites: detection
  • planets and satellites: general
  • methods: data analysis
  • methods: statistical


Dive into the research topics of 'Automatic vetting of planet candidates from ground based surveys: Machine learning with NGTS'. Together they form a unique fingerprint.

Cite this