Classification of Eclipsing Binary Light Curves with Deep Learning Neural Network Algorithms

Yıl 2025, Cilt: 6 Sayı: 1, 18 - 27, 30.06.2025

Burak Ulaş

https://doi.org/10.55064/tjaa.1708479

Öz

We present an image classification algorithm utilising a deep learning convolutional neural network architecture, which categorises the morphologies of eclipsing binary systems based on their light curves. The algorithm trains the machine with light curve images generated from the observational data of eclipsing binary stars in contact, detached and semi-detached morphologies, whose light curves are provided by Kepler, ASAS and CALEB catalogues. The structure of the architecture is explained, the parameters of the network layers and the resulting metrics are discussed. Our results show that the algorithm, which is selected among 132 neural network architectures, estimates the morphological classes of an independent validation dataset, 705 true data, with an accuracy of 92%.

Anahtar Kelimeler

(stars:) binaries: eclipsing , methods: data analysis , techniques: image processing

Derin Öğrenme Sinir Ağı Algoritmaları ile İkili Işık Eğrilerinin Sınıflandırılması

Öz

Bu çalışmada, gözlemsel ışık eğrilerini kullanarak değen, ayrık ve yarı-ayrık yapıya sahip çift yıldız sistemlerini sınıflandıran bir görüntü sınıflandırma algoritması sunulmuştur. Algoritma, Kepler, ASAS ve CALEB kataloglarından alınan çift yıldız sistemlerine ait ışık eğrilerinden üretilen görüntülerle eğitilmiş bir derin öğrenme evrişimsel sinir ağı (Convolutional Neural Network, CNN) mimarisi temellidir. Modelin mimari yapısı açıklanmış, ağ katmanlarının parametreleri ve elde edilen performans metrikleri tartışılmıştır. Sonuçlar, 132 farklı sinir ağı mimarisi arasından seçilen algoritmanın, 705 gözlemsel veriden oluşan bağımsız bir doğrulama veri kümesi üzerinde yapısal sınıflandırmayı %92 doğrulukla tahmin edebildiğini göstermektedir.

Anahtar Kelimeler

(stars:) binaries: eclipsing , methods: data analysis , techniques: image processing

Kaynakça

• Abadi M., et al., 2015, TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems, https://www.tensorflow.org/
• Basha S. S., Dubey S. R., Pulabaigari V., Mukherjee S., 2020, Neurocomputing (doi:https://doi.org/10.1016/j.neucom.2019.10.008), 378, 112
• Birky J., Davenport J., Brandt T., 2020, in American Astronomical Society Meeting Abstracts \#235. p. 170.20
• Bódi A., Hajdu T., 2021, ApJS (doi:10.3847/1538-4365/ac082c), 255, 1
• Bradstreet D. H., 2005, Society for Astronomical Sciences Annual Symposium, 24, 23, ADS:https://ui.adsabs.harvard.edu/abs/2005SASS...24...23B
• Bradstreet D. H., Steelman D. P., Sanders S. J., Hargis J. R., 2004, in American Astronomical Society Meeting Abstracts \#204. p. 05.01
• Chollet F., et al., 2015, Keras, https://keras.io
• Christlein V., Spranger L., Seuret M., Nicolaou A., Král P., Maier A., 2019, in 2019 International Conference on Document Analysis and Recognition (ICDAR). pp 1090--1096, doi:10.1109/ICDAR.2019.00177
• Cokina M., Maslej-Krešň'akov'a V., Butka P., Parimucha S., 2021a, Astronomy and Computing (doi:https://doi.org/10.1016/j.ascom.2021.100488), p. 100488
• Cokina M., Fedurco M., Parimucha S., 2021b, A\&A (doi:10.1051/0004-6361/202039171), 652, A156
• Cortes C., Mohri M., Rostamizadeh A., 2009, in Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. UAI '09. AUAI Press, Arlington, Virginia, USA, p. 109–116
• Dai Z., Liu H., Le Q. V., Tan M., 2021, preprint, , ADS:https://ui.adsabs.harvard.edu/abs/2021arXiv210604803D
• Fukushima K., 1980, Biological Cybernetics, 36, 193
• Gavrikov P., 2020, visualkeras, https://github.com/paulgavrikov/visualkeras
• G\'eron A., 2017, Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, 1st edn. O'Reilly Media, Inc., p. 357
• Goodfellow I. J., Bengio Y., Courville A., 2016, Deep Learning. MIT Press, Cambridge, MA, USA, p. 171
• Guinan E. F., 1993, in Leung K.-C., Nha I.-S., eds, Astronomical Society of the Pacific Conference Series Vol. 38, New Frontiers in Binary Star Research. p. 1
• Harris D., Harris S., 2007, Digital Design and Computer Architecture. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, p. 82
• Harris C. R., et al., 2020, Nature (doi:10.1038/s41586-020-2649-2), 585, 357
• Healy B. F., et al., 2024, ApJS (doi:10.3847/1538-4365/ad33c6), 272, 14
• Hunter J. D., 2007, Computing in Science \& Engineering (doi:10.1109/MCSE.2007.55), 9, 90
• Jenkins J. M., et al., 2010, ApJ (doi:10.1088/2041-8205/713/2/L87), 713, L87
• Juran J. M., Godfrey A. B., 1999, Juran's quality handbook. 5e, McGraw Hill, http://books.google.de/books?id=beVTAAAAMAAJ
• Kingma D. P., Ba J., 2015, in Bengio Y., LeCun Y., eds, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. p. 1, http://arxiv.org/abs/1412.6980
• Kirk B., et al., 2016, The Astronomical Journal (doi:10.3847/0004-6256/151/3/68), 151, 68
• Kochoska A., Conroy K., Hambleton K., Prša A., 2020, Contributions of the Astronomical Observatory Skalnat\'e Pleso (doi:10.31577/caosp.2020.50.2.539), 50
• Kopal Z., 1955, Annales d'Astrophysique, 18, 379, ADS:https://ui.adsabs.harvard.edu/abs/1955AnAp...18..379K
• Krizhevsky A., Sutskever I., Hinton G. E., 2012, in Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1. NIPS'12. Curran Associates Inc., Red Hook, NY, USA, p. 1097–1105
• Lecun Y., Bottou L., Bengio Y., Haffner P., 1998, Proceedings of the IEEE (doi:10.1109/5.726791), 86, 2278
• Matijevič G., Prša A., Orosz J. A., Welsh W. F., Bloemen S., Barclay T., 2012, The Astronomical Journal (doi:10.1088/0004-6256/143/5/123), 143, 123
• Moore H., 1897, The ANNALS of the American Academy of Political and Social Science (doi:10.1177/000271629700900314), 9, 128
• Murphy K. P., 2012, Machine Learning. MIT Press, London, England, p. 247
• Parimucha S., Gajdoš P., Markus Y., Kudak V., 2024, Contributions of the Astronomical Observatory Skalnate Pleso (doi:10.31577/caosp.2024.54.2.167), 54, 167
• Pedregosa F., et al., 2011, Journal of Machine Learning Research, 12, 2825
• Pineau J., Vincent-Lamarre P., Sinha K., Larivière V., Beygelzimer A., d'Alché-Buc F., Fox E., Larochelle H., 2020, preprint, (arXiv:2003.12206), ADS:https://ui.adsabs.harvard.edu/abs/2020arXiv200312206P
• Pojmanski G., 1997, Acta Astronomica, 47, 467, ADS:https://ui.adsabs.harvard.edu/abs/1997AcA....47..467P
• Pojmanski G., 2002, AcA, 52, 397, ADS:https://ui.adsabs.harvard.edu/abs/2002AcA....52..397P
• Popper D. M., Etzel P. B., 1981, AJ (doi:10.1086/112862), 86, 102
• Prsa A., Wrona M., 2024, in American Astronomical Society Meeting Abstracts. p. 423.07
• Prša A., Guinan E. F., Devinney E. J., DeGeorge M., Bradstreet D. H., Giammarco J. M., Alcock C. R., Engle S. G., 2008, The Astrophysical Journal (doi:10.1086/591783), 687, 542
• Prša A., Zwitter T., 2005, ApJ (doi:10.1086/430591), 628, 426
• Ricker G. R., et al., 2015, Journal of Astronomical Telescopes, Instruments, and Systems (doi:10.1117/1.JATIS.1.1.014003), 1, 014003
• Ruder S., 2016, ArXiv, abs/1609.04747
• Sammut C., Webb G. I., eds, 2017, Loss. Springer US, Boston, MA, p. 781, doi:10.1007/978-1-4899-7687-1-499
• Shorten C., Khoshgoftaar T., 2019, Journal of Big Data (doi:https://doi.org/10.1186/s40537-019-0197-0), 6, 60
• Southworth J., Smalley B., Maxted P. F. L., Claret A., Etzel P. B., 2005, MNRAS (doi:10.1111/j.1365-2966.2005.09462.x), 363, 529
• Srivastava N., Hinton G., Krizhevsky A., Sutskever I., Salakhutdinov R., 2014, Journal of Machine Learning Research:http://jmlr.org/papers/v15/srivastava14a.html, 15, 1929
• Szklenár T., Bódi A., Tarczay-Nehéz D., Vida K., Mezo G., Szabó R., 2022, ApJ (doi:10.3847/1538-4357/ac8df3), 938, 37
• The Pandas Development Team 2020, pandas-dev/pandas: Pandas, doi:10.5281/zenodo.3509134, https://doi.org/10.5281/zenodo.3509134
• Ting K. M., 2010, in Sammut C., Webb G. I., eds, , Encyclopedia of Machine Learning. Springer US, Boston, MA, p. 781, doi:10.1007/978-0-387-30164-8_652, https://doi.org/10.1007/978-0-387-30164-8_652
• Tsoumakas G., Vlahavas I., 2007, in Kok J. N., Koronacki J., Mantaras R. L. d., Matwin S., Mladenič D., Skowron A., eds, Machine Learning: ECML 2007. Springer Berlin Heidelberg, Berlin, Heidelberg, pp 406--417
• Udalski A., Szymanski M., Kubiak M., Pietrzynski G., Wozniak P., Zebrun K., 1998, Acta Astron., 48, 147, ADS:https://ui.adsabs.harvard.edu/abs/1998AcA....48..147U
• Ulaş B., 2020, preprint, , ADS:https://ui.adsabs.harvard.edu/abs/2020arXiv201208435U
• Van Rossum G., 2020, The Python Library Reference, release 3.8.2. Python Software Foundation
• Van Rossum G., Drake F. L., 2009, Python 3 Reference Manual. CreateSpace, Scotts Valley, CA
• Wes McKinney 2010, in Stéfan van der Walt Jarrod Millman eds, Proceedings of the 9th Python in Science Conference. pp 56 -- 61, doi:10.25080/Majora-92bf1922-00a
• Wilson R. E., Devinney E. J., 1971, ApJ (doi:10.1086/150986), 166, 605
• Wyrzykowski L., et al., 2003, Acta Astron., 53, 1, ADS:https://ui.adsabs.harvard.edu/abs/2003AcA....53....1W
• Yao Y., Rosasco L., Caponnetto A., 2007, Constr. Approx, pp 289--315
• Zhou Z., Huang H., Fang B., 2021, Journal of Computer and Communications (doi:10.4236/jcc.2021.911001), 09, 1