TSARDI

A Machine Learning data rejection algorithm for transiting exoplanet light curves

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We present TSARDI, an efficient rejection algorithm designed to improve the transit detection efficiency in data collected by large-scale surveys. TSARDI is based on theMachine Learning clustering algorithm DBSCAN, and its purpose is to serve as a robust and adaptable filter aiming to identify unwanted noise points left over from data detrending processes. TSARDI is an unsupervised method, which can treat each light curve individually; there is no need of previous knowledge of any other field light curves. We conduct a simulated transit search by injecting planets on real data obtained by the QES project and show that TSARDI leads to an overall transit detection efficiency increase of ~11 per cent, compared to results obtained from the same sample, but using a standard sigma-clip algorithm. For the brighter end of our sample (host star magnitude < 12), TSARDI achieves a detection efficiency of ~80 per cent of injected planets. While our algorithm has been developed primarily for the field of exoplanets, it is easily adaptable and extendable for use in any time series.

Original languageEnglish
Pages (from-to)1624-1630
Number of pages7
JournalMonthly Notices of the Royal Astronomical Society
Volume481
Issue number2
DOIs
Publication statusPublished - 1 Dec 2018

Fingerprint

machine learning
extrasolar planets
rejection
light curve
transit
planets
planet
clips
learning
time series
filter
filters
stars
detection

Keywords

  • Methods: data analysis
  • Planetary Systems
  • Techniques: photometric

ASJC Scopus subject areas

  • Astronomy and Astrophysics
  • Space and Planetary Science

Cite this

TSARDI : A Machine Learning data rejection algorithm for transiting exoplanet light curves. / Mislis, Dimitrios; Pyrzas, S.; Al-Subai, Khalid.

In: Monthly Notices of the Royal Astronomical Society, Vol. 481, No. 2, 01.12.2018, p. 1624-1630.

Research output: Contribution to journalArticle

@article{52eae07ae6ec493c8609f00cce0a3922,
title = "TSARDI: A Machine Learning data rejection algorithm for transiting exoplanet light curves",
abstract = "We present TSARDI, an efficient rejection algorithm designed to improve the transit detection efficiency in data collected by large-scale surveys. TSARDI is based on theMachine Learning clustering algorithm DBSCAN, and its purpose is to serve as a robust and adaptable filter aiming to identify unwanted noise points left over from data detrending processes. TSARDI is an unsupervised method, which can treat each light curve individually; there is no need of previous knowledge of any other field light curves. We conduct a simulated transit search by injecting planets on real data obtained by the QES project and show that TSARDI leads to an overall transit detection efficiency increase of ~11 per cent, compared to results obtained from the same sample, but using a standard sigma-clip algorithm. For the brighter end of our sample (host star magnitude < 12), TSARDI achieves a detection efficiency of ~80 per cent of injected planets. While our algorithm has been developed primarily for the field of exoplanets, it is easily adaptable and extendable for use in any time series.",
keywords = "Methods: data analysis, Planetary Systems, Techniques: photometric",
author = "Dimitrios Mislis and S. Pyrzas and Khalid Al-Subai",
year = "2018",
month = "12",
day = "1",
doi = "10.1093/mnras/sty2361",
language = "English",
volume = "481",
pages = "1624--1630",
journal = "Monthly Notices of the Royal Astronomical Society",
issn = "0035-8711",
publisher = "Oxford University Press",
number = "2",

}

TY - JOUR

T1 - TSARDI

T2 - A Machine Learning data rejection algorithm for transiting exoplanet light curves

AU - Mislis, Dimitrios

AU - Pyrzas, S.

AU - Al-Subai, Khalid

PY - 2018/12/1

Y1 - 2018/12/1

N2 - We present TSARDI, an efficient rejection algorithm designed to improve the transit detection efficiency in data collected by large-scale surveys. TSARDI is based on theMachine Learning clustering algorithm DBSCAN, and its purpose is to serve as a robust and adaptable filter aiming to identify unwanted noise points left over from data detrending processes. TSARDI is an unsupervised method, which can treat each light curve individually; there is no need of previous knowledge of any other field light curves. We conduct a simulated transit search by injecting planets on real data obtained by the QES project and show that TSARDI leads to an overall transit detection efficiency increase of ~11 per cent, compared to results obtained from the same sample, but using a standard sigma-clip algorithm. For the brighter end of our sample (host star magnitude < 12), TSARDI achieves a detection efficiency of ~80 per cent of injected planets. While our algorithm has been developed primarily for the field of exoplanets, it is easily adaptable and extendable for use in any time series.

AB - We present TSARDI, an efficient rejection algorithm designed to improve the transit detection efficiency in data collected by large-scale surveys. TSARDI is based on theMachine Learning clustering algorithm DBSCAN, and its purpose is to serve as a robust and adaptable filter aiming to identify unwanted noise points left over from data detrending processes. TSARDI is an unsupervised method, which can treat each light curve individually; there is no need of previous knowledge of any other field light curves. We conduct a simulated transit search by injecting planets on real data obtained by the QES project and show that TSARDI leads to an overall transit detection efficiency increase of ~11 per cent, compared to results obtained from the same sample, but using a standard sigma-clip algorithm. For the brighter end of our sample (host star magnitude < 12), TSARDI achieves a detection efficiency of ~80 per cent of injected planets. While our algorithm has been developed primarily for the field of exoplanets, it is easily adaptable and extendable for use in any time series.

KW - Methods: data analysis

KW - Planetary Systems

KW - Techniques: photometric

UR - http://www.scopus.com/inward/record.url?scp=85054086398&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054086398&partnerID=8YFLogxK

U2 - 10.1093/mnras/sty2361

DO - 10.1093/mnras/sty2361

M3 - Article

VL - 481

SP - 1624

EP - 1630

JO - Monthly Notices of the Royal Astronomical Society

JF - Monthly Notices of the Royal Astronomical Society

SN - 0035-8711

IS - 2

ER -