Machine learning search for variable stars

@article{Pashchenko2017MachineLS,
  title={Machine learning search for variable stars},
  author={Ilya N Pashchenko and Kirill V. Sokolovsky and Panagiotis Gavras},
  journal={Monthly Notices of the Royal Astronomical Society},
  year={2017},
  volume={475},
  pages={2326-2343}
}
Photometric variability detection is often considered as a hypothesis testing problem: an object is variable if the null-hypothesis that its brightness is constant can be ruled out given the measurements and their uncertainties. Uncorrected systematic errors limit the practical applicability of this approach to high-amplitude variability and well-behaving data sets. Searching for a new variability detection technique that would be applicable to a wide range of variability types while being… 

Variable Star Classification Using Multi-View Metric Learning

Both the vector and matrix-variate versions of the multi-view learning framework perform favorably --- demonstrating the ability to discriminate variable star categories.

Machine Learning Applied to Star–Galaxy–QSO Classification and Stellar Effective Temperature Regression

This paper describes an application of the supervised machine-learning algorithm, random forests (RF), to the star/galaxy/QSO classification and the stellar effective temperature regression based on the combination of LAMOST and SDSS spectroscopic data.

Image-based Classification of Variable Stars: First Results from Optical Gravitational Lensing Experiment Data

An image-based Convolutional Neural Network is used to classify the different types of variable stars using images of phase-folded light curves from the Optical Gravitational Lensing Experiment (OGLE)-III survey for training, validating, and testing.

Protostellar classification using supervised machine learning algorithms

  • O. Miettinen
  • Computer Science
    Astrophysics and Space Science
  • 2018
This attempt to classify a sample of Orion YSOs into different classes, where each source has already been classified using multiwavelength SED analysis, using eight different learning algorithms, namely a decision tree, random forest, gradient boosting machine (GBM), logistic regression, naïve Bayes classifier, k$k$-nearest neighbour classifiers, support vector machine, and neural network.

Identification of Young Stellar Object candidates in the Gaia DR2 x AllWISE catalogue with machine learning methods

An all-sky probabilistic catalogue of Young Stellar Objects (YSOs) is made and the 3D structure of the Orion A star-forming complex is explored and the spatial distribution of the YSOs classified by the procedure is in agreement with recent results from the literature.

Variability search in M 31 using principal component analysis and the Hubble Source Catalogue

Principal Component Analysis (PCA) is being extensively used in Astronomy but not yet exhaustively exploited for variability search. The aim of this work is to investigate the effectiveness of using

Classification of Variable Stars Light Curves Using Long Short Term Memory Network

This work presents a new automated method, 1D CNN-LSTM, for classifying variable stars using a hybrid neural network of one-dimensional CNN and LSTM network which employs the raw time-series data from the variable stars.

VaST: A variability search toolkit

Classifying High-cadence Microlensing Light Curves. I. Defining Features

Microlensing is a powerful tool for discovering cold exoplanets, and the Roman Space Telescope microlensing survey will discover over 1000 such planets. Rapid, automated classification of Roman’s

References

SHOWING 1-10 OF 117 REFERENCES

Comparative performance of selected variability detection techniques in photometric time series data

Photometric measurements are prone to systematic errors presenting a challenge to low-amplitude variability detection. In search for a general-purpose variability detection technique able to recover

A package for the automated classification of periodic variable stars

A machine learning package for the classification of periodic variable stars finds that recall and precision do not vary significantly if there are more than 80 data points and the duration is more than a few weeks, and investigates how the performance varies with the number ofData points and duration of observations.

Machine learning techniques to select Be star candidates: An application in the OGLE-IVGaiasouth ecliptic pole field

A new robust set of features is proposed and evaluated using supervised classifiers in order to look for new Be star candidates in the OGLE-IV Gaia south ecliptic pole field and the random forest classifier outperformed the others.

DETECTING VARIABILITY IN MASSIVE ASTRONOMICAL TIME-SERIES DATA. II. VARIABLE CANDIDATES IN THE NORTHERN SKY VARIABILITY SURVEY

We present variability analysis of data from the Northern Sky Variability Survey (NSVS). Using the clustering method, which defines variable candidates as outliers from large clusters, we cluster

Robust variable star detection techniques suitable for automated searches: new results for NGC 1866

We describe sensitive techniques for identifying variable stars in multiepoch photometry lists made in two or more bandpasses or pairwise in a single bandpass. Our search strategy employs the

EXPLORING THE VARIABLE SKY WITH LINEAR. III. CLASSIFICATION OF PERIODIC LIGHT CURVES

We describe the construction of a highly reliable sample of ∼7000 optically faint periodic variable stars with light curves obtained by the asteroid survey LINEAR across 10,000 deg2 of the northern

The WFCAM multiwavelength Variable Star Catalog

Context. Stellar variability in the near-infrared (NIR) remains largely unexplored. The exploitation of public science archives with data-mining methods offers a perspective for a time-domain

A machine learned classifier for RR Lyrae in the VVV survey

This work describes a supervised machine-learned classifier constructed for assigning a score to a K s -band VVV light curve that indicates its likelihood of being ab -type RR Lyrae, and obtains a classifier based on the AdaBoost algorithm that achieves a harmonic mean between false positives and false negatives of ≈7% for typical VvV light-curve sets.

Detecting Variability in Massive Astronomical Time-Series Data I: application of an infinite Gaussian mixture model

A new framework to detect various types of variable objects within massive astronomical time-series data by using a non-parametric Bayesian clustering algorithm based on an infinite GaussianMixtureModel (GMM) and the Dirichlet Process is presented.

IMPROVED VARIABLE STAR SEARCH IN LARGE PHOTOMETRIC DATA SETS: NEW VARIABLES IN CoRoT FIELD LRa02 DETECTED BY BEST II

An empirical approach to treat systematic trends in photometric data based upon the analysis of variance statistics that can significantly decrease the rate of false detections is described.
...