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

Owing to the current and upcoming extensive surveys studying the stellar variability, accurate and quicker methods are required for the astronomers to automate the classification of variable stars. The traditional approach of classification requires the calculation of the period of the observed ligh...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Saksham Bassi, Kaushal Sharma, Atharva Gomekar
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	deep learning convolutional neural networks long short term memory variable star classification big data and analytics Astronomy QB1-991 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/7bf217205b3848509c99a1ab94c52fe8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7bf217205b3848509c99a1ab94c52fe8
record_format	dspace
spelling	oai:doaj.org-article:7bf217205b3848509c99a1ab94c52fe82021-11-08T13:12:45ZClassification of Variable Stars Light Curves Using Long Short Term Memory Network2296-987X10.3389/fspas.2021.718139https://doaj.org/article/7bf217205b3848509c99a1ab94c52fe82021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fspas.2021.718139/fullhttps://doaj.org/toc/2296-987XOwing to the current and upcoming extensive surveys studying the stellar variability, accurate and quicker methods are required for the astronomers to automate the classification of variable stars. The traditional approach of classification requires the calculation of the period of the observed light curve and assigning different variability patterns of phase folded light curves to different classes. However, applying these methods becomes difficult if the light curves are sparse or contain temporal gaps. Also, period finding algorithms start slowing down and become redundant in such scenarios. In this work, we present 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. We apply the network to classify the time-series data obtained from the OGLE and the CRTS survey. We report the best average accuracy of 85% and F1 score of 0.71 for classifying five classes from the OGLE survey. We simultaneously apply other existing classification methods to our dataset and compare the results.Saksham BassiKaushal SharmaAtharva GomekarFrontiers Media S.A.articledeep learningconvolutional neural networkslong short term memoryvariable star classificationbig data and analyticsAstronomyQB1-991Geophysics. Cosmic physicsQC801-809ENFrontiers in Astronomy and Space Sciences, Vol 8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning convolutional neural networks long short term memory variable star classification big data and analytics Astronomy QB1-991 Geophysics. Cosmic physics QC801-809
spellingShingle	deep learning convolutional neural networks long short term memory variable star classification big data and analytics Astronomy QB1-991 Geophysics. Cosmic physics QC801-809 Saksham Bassi Kaushal Sharma Atharva Gomekar Classification of Variable Stars Light Curves Using Long Short Term Memory Network
description	Owing to the current and upcoming extensive surveys studying the stellar variability, accurate and quicker methods are required for the astronomers to automate the classification of variable stars. The traditional approach of classification requires the calculation of the period of the observed light curve and assigning different variability patterns of phase folded light curves to different classes. However, applying these methods becomes difficult if the light curves are sparse or contain temporal gaps. Also, period finding algorithms start slowing down and become redundant in such scenarios. In this work, we present 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. We apply the network to classify the time-series data obtained from the OGLE and the CRTS survey. We report the best average accuracy of 85% and F1 score of 0.71 for classifying five classes from the OGLE survey. We simultaneously apply other existing classification methods to our dataset and compare the results.
format	article
author	Saksham Bassi Kaushal Sharma Atharva Gomekar
author_facet	Saksham Bassi Kaushal Sharma Atharva Gomekar
author_sort	Saksham Bassi
title	Classification of Variable Stars Light Curves Using Long Short Term Memory Network
title_short	Classification of Variable Stars Light Curves Using Long Short Term Memory Network
title_full	Classification of Variable Stars Light Curves Using Long Short Term Memory Network
title_fullStr	Classification of Variable Stars Light Curves Using Long Short Term Memory Network
title_full_unstemmed	Classification of Variable Stars Light Curves Using Long Short Term Memory Network
title_sort	classification of variable stars light curves using long short term memory network
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/7bf217205b3848509c99a1ab94c52fe8
work_keys_str_mv	AT sakshambassi classificationofvariablestarslightcurvesusinglongshorttermmemorynetwork AT kaushalsharma classificationofvariablestarslightcurvesusinglongshorttermmemorynetwork AT atharvagomekar classificationofvariablestarslightcurvesusinglongshorttermmemorynetwork
_version_	1718442251956256768

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

Ejemplares similares