Skip to main content

Research Repository

Advanced Search

Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys

Schanche, N; Collier Cameron, A; Hébrard, G; Nielsen, L; Triaud, A H M J; Almenara, J M; Alsubai, K A; Anderson, D R; Armstrong, D J; Barros, S C C; Bouchy, F; Boumis, P; Brown, D J A; Faedi, F; Hay, K; Hebb, L; Kiefer, F; Mancini, L; Maxted, P F L; Palle, E; Pollacco, D L; Queloz, D; Smalley, B; Udry, S; West, R; Wheatley, P J

Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys Thumbnail


Authors

N Schanche

A Collier Cameron

G Hébrard

L Nielsen

A H M J Triaud

J M Almenara

K A Alsubai

D R Anderson

D J Armstrong

S C C Barros

F Bouchy

P Boumis

D J A Brown

F Faedi

K Hay

L Hebb

F Kiefer

L Mancini

E Palle

D L Pollacco

D Queloz

S Udry

R West

P J Wheatley



Abstract

Since the start of the Wide Angle Search for Planets (WASP) program, more than 160 transiting exoplanets have been discovered in the WASP data. In the past, possible transit-like events identified by the WASP pipeline have been vetted by human inspection to eliminate false alarms and obvious false positives. The goal of the present paper is to assess the effectiveness of machine learning as a fast, automated, and reliable means of performing the same functions on ground-based wide-field transit-survey data without human intervention. To this end, we have created training and test datasets made up of stellar light curves showing a variety of signal types including planetary transits, eclipsing binaries, variable stars, and non-periodic signals. We use a combination of machine learning methods including Random Forest Classifiers (RFCs) and Convolutional Neural Networks (CNNs) to distinguish between the different types of signals. The final algorithms correctly identify planets in the test data ~90% of the time, although each method on its own has a significant fraction of false positives. We find that in practice, a combination of different methods offers the best approach to identifying the most promising exoplanet transit candidates in data from WASP, and by extension similar transit surveys.

Citation

Schanche, N., Collier Cameron, A., Hébrard, G., Nielsen, L., Triaud, A. H. M. J., Almenara, J. M., …Wheatley, P. J. Machine-learning Approaches to Exoplanet Transit Detection and Candidate Validation in Wide-field Ground-based Surveys. https://doi.org/10.1093/mnras/sty3146. Manuscript submitted for publication

Journal Article Type Article
Publicly Available Date May 26, 2023
Peer Reviewed Peer Reviewed
Volume 483
Issue 4
Pages 5534-5547
DOI https://doi.org/10.1093/mnras/sty3146
Keywords Earth and Planetary Astrophysics; Instrumentation and Methods for Astrophysics

Files






You might also like



Downloadable Citations