Deep-learning classification of eclipsing binaries

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985815%3A_____%2F24%3A00585883" target="_blank" >RIV/67985815:_____/24:00585883 - isvavai.cz</a>

Výsledek na webu

<a href="https://hdl.handle.net/11104/0353524" target="_blank" >https://hdl.handle.net/11104/0353524</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.31577/caosp.2024.54.2.167" target="_blank" >10.31577/caosp.2024.54.2.167</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Deep-learning classification of eclipsing binaries

Popis výsledku v původním jazyce

We present a deep-learning model for the classification of eclipsing binaries. Our classifier provides a tool for the categorization of light curves of eclipsing binaries into four classes: detached systems with and without spots, and over-contact systems with and without spots. The classifier was trained on 200 000 synthetic light curves created using ELISa code. We randomly selected 100 light curves from the GAIA catalogue, which were fitted for evaluation purposes, and their morphologies were determined. We tested several classifiers and found that the best-performing classifier combined a Long Short-Term Memory (LSTM) layer and two one-dimensional convolutional neural networks. The precision from the evaluation set was 97% compared with the predicted precision of 94% for the validation of synthetic data. Our classifier is more likely to successfully process data from subsequent large observational surveys.n

Název v anglickém jazyce

Deep-learning classification of eclipsing binaries

Popis výsledku anglicky

We present a deep-learning model for the classification of eclipsing binaries. Our classifier provides a tool for the categorization of light curves of eclipsing binaries into four classes: detached systems with and without spots, and over-contact systems with and without spots. The classifier was trained on 200 000 synthetic light curves created using ELISa code. We randomly selected 100 light curves from the GAIA catalogue, which were fitted for evaluation purposes, and their morphologies were determined. We tested several classifiers and found that the best-performing classifier combined a Long Short-Term Memory (LSTM) layer and two one-dimensional convolutional neural networks. The precision from the evaluation set was 97% compared with the predicted precision of 94% for the validation of synthetic data. Our classifier is more likely to successfully process data from subsequent large observational surveys.n

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10308 - Astronomy (including astrophysics,space science)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Contributions of the Astronomical Observatory Skalnaté Pleso

ISSN

1335-1842

e-ISSN

1336-0337

Svazek periodika

54

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

SK - Slovenská republika

Počet stran výsledku

4

Strana od-do

167-170

Kód UT WoS článku

001178776600019

EID výsledku v databázi Scopus

2-s2.0-85193014109