Review Article
BibTex RIS Cite

Machine Learning Applications in Astronomy

Year 2021, Volume: 2 Issue: 1, 13 - 20, 30.06.2021

Abstract

With the developing technology, the variety and capacity of data collection tools in astronomy have also improved. With the increase in the amount of data collected, the number of data mining, big data applications, machine learning and artificial intelligence applications in this field is increasing day by day. The most important part in the calculations in astronomy is revealing and evaluating the structure of the data. Machine learning stands out in these calculations and has an important application area nowadays. The most common supervised and unsupervised machine learning methods used in astronomy are Support Vector Machines, Random Forests and also Artificial Neural Network for supervised learning and Self-Classifying/Organizing Map, Principal Component Analysis for unsupervised learning methods, respectively. Different machine learning methods find applications in more than one subsections, from the classification of celestial objects, to the evaluation of their observational properties, and to the evaluation of their models. Striking applications among these are; classification of galaxies, determination of variable stars, solar physics researches, exoplanet discoveries, and revealing of stellar parameters and modelling of stellar interior structure and evolution. This study presents a compilation of recent articles in astronomy in the last five years to create a Turkish material in astroinformatics and astrostatistics.

References

  • Agarwal, D. ve ark.: FETCH: A deep-learning based classifier for fast transient classification. (2020) MNRAS 497 1661.
  • An, F. X. ve ark.: Multi-wavelength Properties of Radio-and Machine-learning-identified Counterparts to Submillimeter Sources in S2COSMOS. (2019) The Astrophysical Journal 886(1) 48.
  • Aschwanden, M. J.: A Code for Automated Tracing of Coronal Loops Approaching Visual Perception. (2010) Solar Physics 262(2) 399–423.
  • Azari A. R. ve ark.: Integrating Machine Learning for Planetary Science: Perspectives for the Next Decade Planetary Science and Astrobiology Decadal Survey (2020) 2023-2032 arXiv:2007.15129.
  • Barchi, P. H., da Costa, F. G., Sautter, R., Moura, T. C., Stalder, D. H., Rosa, R. R., de Carvalho, R. R.: Improving galaxy morphology with machine learning. (2017) arXiv preprint arXiv:1705.06818.
  • Baron, D.: Machine Learning in Astronomy: a practical overview (2019) eprint arXiv:1904.07248.
  • Bellinger, E. P., Angelou, G. C., Hekker, S., Basu, S., Ball, W. H., Guggenberger, E. : Fundamental Parameters of Main-Sequence Stars in an Instant with Machine Learning. ApJ (2016) 830(1) 31 2016.
  • Bellinger, E. P., Kanbur, S. M., Bhardwaj, A., Marconi, M.: When a Period Is Not a Full Stop: Light Curve Structure Reveals Fundamental Parameters of Cepheid and RR Lyrae Stars. (2019) MNRAS 491 4752.
  • Bellutta, D.: The Fog of War: A Machine Learning Approach to Forecasting Weather on Mars (2017) ArXiv:1706.08915.
  • Borne, K. D.: Astroinformatics: data-oriented astronomy research and education, Earth Science Informatics (2010) 3(1-2) 5–17.
  • Breton, S. N., Bugnet, L., Santos, A. R. G., Saux, A. L., Mathur, S., Palle, P. L., Garcia, R. A.: Determining surface rotation periods of solar-like stars observed by the Kepler mission using machine learning techniques. (2019) arXiv preprint arXiv:1906.09609.
  • Bugnet, L., García, R. A., Davies, G. R., Mathur, S., Corsaro, E., Hall, O. J., Rendle, B. M.: FliPer: A global measure of power density to estimate surface gravities ofmain-sequence solar-like stars and red giants. Astronomy \& Astrophysics (2018) 620.
  • Cantat-Gaudin, T. ve ark.: Gaia DR2 unravels incompleteness of nearby cluster population: new open clusters in the direction of Perseus. Astronomy \& Astrophysics 624 (2019) A126.
  • Cohn, J. D., Battaglia, N.: Multiwavelength cluster mass estimates and machine learning (2020) MNRAS 491 1175. Community, T. S. ve ark.: SunPy-Python for Solar Physics (2015) arXiv:1505.02563.
  • Colak, T., Qahwaji, R.: Automated solar activity prediction: a hybrid computer platform using machine learning and solar imaging for automated prediction of solar flares (2009) Space Weather 7(6).
  • Cruz, J. A. ve Wishart, D. S.: Applications of Machine Learning in Cancer Prediction and Prognosis. (2006) Cancer Informatics 2 117693510600200.
  • Djorgovski, S. G., Mahabal, A., Donalek, C., Graham, M., Drake, A., Turmon, M., Fuchs, T.: Automated Real-Time Classification and Decision Making in Massive Data Streams from Synoptic Sky Surveys. (2014) IEEE 10th International Conference on e-Science.doi:10.1109/escience.2014.7.
  • Elliott, J., de Souza, R. S., Krone-Martins, A. ve ark.: Using gamma regression for photometric redshifts of survey galaxies In The Universe of Digital Sky Surveys (2016) pp.91-96 Springer Cham.
  • Feigelson, E. D. ve Babu, G. J.: Modern Statistical Methods for Astronomy With R Applications. Cambridge University Press (2012).
  • Garofalo, M., Botta A., Ventre, G.: Astrophysics and Big Data: Challenges, Methods, and Tools. Astroinformatics Proceedings of the IAU Symposium Volume 325 (2017) pp. 345-348
  • Gomes, Z., Jarvis, M. J., Almosallam, I. A., Roberts, S. J.: Improving photometric redshift estimation using GPz: size information, post processing, and improved photometry MNRAS (2017) 475(1) 331–342.
  • Heinis, S. ve ark.: Of Genes and Machines: Application of a Combination of Machine Learning Tools to Astronomy Data Sets. Astrophysical Journal Volume 821 Issue 2 (2016) article id. 86 pp 10.
  • Hendriks, L., ve Aerts, C.: Deep Learning Applied to the Asteroseismic Modeling of Stars with Coherent Oscillation Modes. (2019) PASP 131(1004) 108001.
  • Huppenkothen, D., Heil, L. M., Hogg, D. W., Mueller, A.: Exploring the Long-Term Evolution of GRS 1915+ 105. (2016) arXiv preprint arXiv:1611.01332.
  • Jones, D. E., Stenning, D. C., Ford, E. B., Wolpert, R. L., Loredo, T. J., Dumusque, X.: Improving Exoplanet Detection Power: Multivariate Gaussian Process Models for Stellar Activity. (2017) arXiv preprint 1711.01318.
  • Kelly, B. C., Bechtold, J., Siemiginowska, A.: Are the variations in quasar optical flux driven by thermal fluctuations? AJ (2009) 698(1) 895.
  • Kremer, J. ve ark.: Big Universe, “Big Data: Machine Learning and Image Analysis for Astronomy IEEE Intelligent Systems (2017) vol. 32 no. pp. 16-22.
  • La Plante, P., Ntampaka, M.: Machine Learning Applied to the Reionization History of the Universe in the 21 cm Signal. ApJ (2019) 880(2) 110.
  • Lahav, O.: Artificial neural networks as non-linear extensions of statistical methods in astronomy. Vistas in Astronomy 38 (1994) 251–IN2.
  • Longo, G., Merényi, E., Tiňo, P.: Foreword to the Focus Issue on Machine Intelligence in Astronomy and Astrophysics. PASP V 131 I (2019) 1004. pp 100101.
  • Mahabal, A. ve ark.: Deep-learnt classification of light curves. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI) (2017) pp. 1-8. IEEE.
  • McMillan, P. J.: Mass models of the Milky Way. MNRAS (2011) 414(3) 2446-2457.
  • Norris, R. P.: Discovering the Unexpected in Astronomical Survey Data. (2017) PASA 34. doi:10.1017/pasa.2016.63
  • Pashchenko, I. N., Sokolovsky, K. V., Gavras, P.: Machine learning search for variable stars. (2017) MNRAS 475(2) 2326–2343.
  • Pawlak, M. ve ark.: The ASAS-SN Catalog of Variable Stars IV: Periodic Variables in the APOGEE Survey. (2019) MNRAS 487 5932.
  • Pieringer, C., Pichara, K., Catelan, M., Protopapas, P.: An Algorithm for the Visualization of Relevant Patterns in Astronomical Light Curves. (2019) MNRAS 484 3071.
  • Roberts, D. A. ve ark.: Objectively Determining States of the Solar Wind Using Machine Learning (2020) ApJ 889(2) 153.
  • Saha, S. ve ark.: ASTROMLSKIT: A New Statistical Machine Learning Toolkit: A Platform for Data Analytics in Astronomy (2015) eprint arXiv:1504.07865 2015.
  • Saux, A. L., Bugnet, L., Mathur, S., Breton, S. N., Garcia, R. A.: Automatic classification of K2 pulsating stars using machine learning techniques. (2019) ArXiv:1906.09611.
  • Sharma K. ve ark.: Stellar spectral interpolation using machine learning MNRAS (2020) Volume 496 Issue 4 p. 5002-5006.
  • Siemiginowska, A. ve ark.: The Next Decade of Astroinformatics and Astrostatistics. Astro2020: Decadal Survey on Astronomy and Astrophysics science white papers no. 355Bulletin of the American Astronomical Society (2019) Vol. 51 Issue 3 id. 355.
  • Stenning, D. C., Lee, T. C. M., van Dyk, D. A., Kashyap, V., Sandell, J., Young, C. A.: Morphological feature extraction for statistical learning with applications to solar image data. Statistical Analysis and Data Mining (2013) 6(4) 329–345.
  • Tyson, A. ve ark.: The Large-aperture Synoptic Survey Telescope. The New Era of Wide Field Astronomy ASP Conference Series. 232. San Francisco: Astronomical Society of the Pacific. (2001) p. 347. ISBN 1-58381-065-X
  • Warner, B. ve Misra, M.: Understanding Neural Networks as Statistical Tools. The American Statistician (1996) 50(4) 284–293.
  • Vernin, J. ve ark.: European Extremely Large Telescope Site Characterization I: Overview. PASP (2011) 123 (909): 1334–1346
  • Vilalta, R.: Transfer Learning in Astronomy: A New Machine-Learning Paradigm. Journal of Physics: Conference Series. (2018) Volume 1085. Issue 5.
  • Vretinaris, S., Stergioulas, N., Bauswein, A.: Empirical relations for gravitational-wave asteroseismology of binary neutron star mergers”. Physical Review D (2020) 101(8) 084039.
  • Yeşilyaprak C. ve Yerli, S.K.: Atatürk Üniversitesi Astrofizik Araştırma Teleskobu (ATA50); Doğu Anadolu Gözlemevi (DAG). Türkiye’deki Teleskoplarla Bilim Sempozyumu. 14-15 Mayıs 2012 – İstanbul Üni. İstanbul (2012).

Astronomi Alanında Makine Öğrenmesi Uygulamaları

Year 2021, Volume: 2 Issue: 1, 13 - 20, 30.06.2021

Abstract

Gelişen teknoloji ile birlikte astronomi alanında veri toplama araçlarının çeşitliliği ve kapasitesi de gelişti. Toplanan veri miktarının artması ile birlikte bu alandaki veri madenciliği, büyük veri uygulamaları, makine öğrenmesi ve yapay zeka uygulamalarının sayısı her geçen gün artıyor. Astronomi alanındaki hesaplamalarda da en önemli kısım verinin yapısının ortaya çıkarılması ve değerlendirilmesidir. Makine öğrenmesi günümüzde bu hesaplamalarda ön plana çıkarak önemli bir uygulama alanı bulunuyor. Bu alanda kullanılan en yaygın makine öğrenmesi yöntemleri denetimli öğrenmede Destek Vektör Makineleri (Support Vector Machines), Rastgele Orman (Random Forests) ve Yapay Sinir Ağları(Artificial Neural Network) iken denetimsiz öğrenmede Kendi Kendine Sınıflandırma/Düzenleme Haritası (Self-Classifying/Organizing Map), Temel Bileşen Çözümlemesi (Pricipal Component Analysis) ’dir. Birbirinden farklı makine öğrenmesi yöntemleri gökcisimlerinin sınıflandırılmasından, gözlemsel özelliklerinin değerlendirilmesine ve modellerle uyum değerlendirmesine kadar birden fazla alt başlıkta uygulama buluyor. Bunlar arasında ön plana çıkan çarpıcı örnekler; gökadaların sınıflandırılması, güneş fiziği araştırmaları , değişen yıldız türlerinin belirlenmesi, yeni gezegen keşifleri ve yıldızların temel parametrelerinin belirlenmesiyle yıldız iç yapı ve evrimlerinin ortaya çıkarılması ve modellenmesi üzerinedir. Bu çalışma astroenformatik ve astroistatistik alanında Türkçe kaynak oluşturmak adına son beş yıl içerisinde astronomi alanında güncel yazılmış makalelerden bir derleme sunmaktadır.

References

  • Agarwal, D. ve ark.: FETCH: A deep-learning based classifier for fast transient classification. (2020) MNRAS 497 1661.
  • An, F. X. ve ark.: Multi-wavelength Properties of Radio-and Machine-learning-identified Counterparts to Submillimeter Sources in S2COSMOS. (2019) The Astrophysical Journal 886(1) 48.
  • Aschwanden, M. J.: A Code for Automated Tracing of Coronal Loops Approaching Visual Perception. (2010) Solar Physics 262(2) 399–423.
  • Azari A. R. ve ark.: Integrating Machine Learning for Planetary Science: Perspectives for the Next Decade Planetary Science and Astrobiology Decadal Survey (2020) 2023-2032 arXiv:2007.15129.
  • Barchi, P. H., da Costa, F. G., Sautter, R., Moura, T. C., Stalder, D. H., Rosa, R. R., de Carvalho, R. R.: Improving galaxy morphology with machine learning. (2017) arXiv preprint arXiv:1705.06818.
  • Baron, D.: Machine Learning in Astronomy: a practical overview (2019) eprint arXiv:1904.07248.
  • Bellinger, E. P., Angelou, G. C., Hekker, S., Basu, S., Ball, W. H., Guggenberger, E. : Fundamental Parameters of Main-Sequence Stars in an Instant with Machine Learning. ApJ (2016) 830(1) 31 2016.
  • Bellinger, E. P., Kanbur, S. M., Bhardwaj, A., Marconi, M.: When a Period Is Not a Full Stop: Light Curve Structure Reveals Fundamental Parameters of Cepheid and RR Lyrae Stars. (2019) MNRAS 491 4752.
  • Bellutta, D.: The Fog of War: A Machine Learning Approach to Forecasting Weather on Mars (2017) ArXiv:1706.08915.
  • Borne, K. D.: Astroinformatics: data-oriented astronomy research and education, Earth Science Informatics (2010) 3(1-2) 5–17.
  • Breton, S. N., Bugnet, L., Santos, A. R. G., Saux, A. L., Mathur, S., Palle, P. L., Garcia, R. A.: Determining surface rotation periods of solar-like stars observed by the Kepler mission using machine learning techniques. (2019) arXiv preprint arXiv:1906.09609.
  • Bugnet, L., García, R. A., Davies, G. R., Mathur, S., Corsaro, E., Hall, O. J., Rendle, B. M.: FliPer: A global measure of power density to estimate surface gravities ofmain-sequence solar-like stars and red giants. Astronomy \& Astrophysics (2018) 620.
  • Cantat-Gaudin, T. ve ark.: Gaia DR2 unravels incompleteness of nearby cluster population: new open clusters in the direction of Perseus. Astronomy \& Astrophysics 624 (2019) A126.
  • Cohn, J. D., Battaglia, N.: Multiwavelength cluster mass estimates and machine learning (2020) MNRAS 491 1175. Community, T. S. ve ark.: SunPy-Python for Solar Physics (2015) arXiv:1505.02563.
  • Colak, T., Qahwaji, R.: Automated solar activity prediction: a hybrid computer platform using machine learning and solar imaging for automated prediction of solar flares (2009) Space Weather 7(6).
  • Cruz, J. A. ve Wishart, D. S.: Applications of Machine Learning in Cancer Prediction and Prognosis. (2006) Cancer Informatics 2 117693510600200.
  • Djorgovski, S. G., Mahabal, A., Donalek, C., Graham, M., Drake, A., Turmon, M., Fuchs, T.: Automated Real-Time Classification and Decision Making in Massive Data Streams from Synoptic Sky Surveys. (2014) IEEE 10th International Conference on e-Science.doi:10.1109/escience.2014.7.
  • Elliott, J., de Souza, R. S., Krone-Martins, A. ve ark.: Using gamma regression for photometric redshifts of survey galaxies In The Universe of Digital Sky Surveys (2016) pp.91-96 Springer Cham.
  • Feigelson, E. D. ve Babu, G. J.: Modern Statistical Methods for Astronomy With R Applications. Cambridge University Press (2012).
  • Garofalo, M., Botta A., Ventre, G.: Astrophysics and Big Data: Challenges, Methods, and Tools. Astroinformatics Proceedings of the IAU Symposium Volume 325 (2017) pp. 345-348
  • Gomes, Z., Jarvis, M. J., Almosallam, I. A., Roberts, S. J.: Improving photometric redshift estimation using GPz: size information, post processing, and improved photometry MNRAS (2017) 475(1) 331–342.
  • Heinis, S. ve ark.: Of Genes and Machines: Application of a Combination of Machine Learning Tools to Astronomy Data Sets. Astrophysical Journal Volume 821 Issue 2 (2016) article id. 86 pp 10.
  • Hendriks, L., ve Aerts, C.: Deep Learning Applied to the Asteroseismic Modeling of Stars with Coherent Oscillation Modes. (2019) PASP 131(1004) 108001.
  • Huppenkothen, D., Heil, L. M., Hogg, D. W., Mueller, A.: Exploring the Long-Term Evolution of GRS 1915+ 105. (2016) arXiv preprint arXiv:1611.01332.
  • Jones, D. E., Stenning, D. C., Ford, E. B., Wolpert, R. L., Loredo, T. J., Dumusque, X.: Improving Exoplanet Detection Power: Multivariate Gaussian Process Models for Stellar Activity. (2017) arXiv preprint 1711.01318.
  • Kelly, B. C., Bechtold, J., Siemiginowska, A.: Are the variations in quasar optical flux driven by thermal fluctuations? AJ (2009) 698(1) 895.
  • Kremer, J. ve ark.: Big Universe, “Big Data: Machine Learning and Image Analysis for Astronomy IEEE Intelligent Systems (2017) vol. 32 no. pp. 16-22.
  • La Plante, P., Ntampaka, M.: Machine Learning Applied to the Reionization History of the Universe in the 21 cm Signal. ApJ (2019) 880(2) 110.
  • Lahav, O.: Artificial neural networks as non-linear extensions of statistical methods in astronomy. Vistas in Astronomy 38 (1994) 251–IN2.
  • Longo, G., Merényi, E., Tiňo, P.: Foreword to the Focus Issue on Machine Intelligence in Astronomy and Astrophysics. PASP V 131 I (2019) 1004. pp 100101.
  • Mahabal, A. ve ark.: Deep-learnt classification of light curves. In 2017 IEEE Symposium Series on Computational Intelligence (SSCI) (2017) pp. 1-8. IEEE.
  • McMillan, P. J.: Mass models of the Milky Way. MNRAS (2011) 414(3) 2446-2457.
  • Norris, R. P.: Discovering the Unexpected in Astronomical Survey Data. (2017) PASA 34. doi:10.1017/pasa.2016.63
  • Pashchenko, I. N., Sokolovsky, K. V., Gavras, P.: Machine learning search for variable stars. (2017) MNRAS 475(2) 2326–2343.
  • Pawlak, M. ve ark.: The ASAS-SN Catalog of Variable Stars IV: Periodic Variables in the APOGEE Survey. (2019) MNRAS 487 5932.
  • Pieringer, C., Pichara, K., Catelan, M., Protopapas, P.: An Algorithm for the Visualization of Relevant Patterns in Astronomical Light Curves. (2019) MNRAS 484 3071.
  • Roberts, D. A. ve ark.: Objectively Determining States of the Solar Wind Using Machine Learning (2020) ApJ 889(2) 153.
  • Saha, S. ve ark.: ASTROMLSKIT: A New Statistical Machine Learning Toolkit: A Platform for Data Analytics in Astronomy (2015) eprint arXiv:1504.07865 2015.
  • Saux, A. L., Bugnet, L., Mathur, S., Breton, S. N., Garcia, R. A.: Automatic classification of K2 pulsating stars using machine learning techniques. (2019) ArXiv:1906.09611.
  • Sharma K. ve ark.: Stellar spectral interpolation using machine learning MNRAS (2020) Volume 496 Issue 4 p. 5002-5006.
  • Siemiginowska, A. ve ark.: The Next Decade of Astroinformatics and Astrostatistics. Astro2020: Decadal Survey on Astronomy and Astrophysics science white papers no. 355Bulletin of the American Astronomical Society (2019) Vol. 51 Issue 3 id. 355.
  • Stenning, D. C., Lee, T. C. M., van Dyk, D. A., Kashyap, V., Sandell, J., Young, C. A.: Morphological feature extraction for statistical learning with applications to solar image data. Statistical Analysis and Data Mining (2013) 6(4) 329–345.
  • Tyson, A. ve ark.: The Large-aperture Synoptic Survey Telescope. The New Era of Wide Field Astronomy ASP Conference Series. 232. San Francisco: Astronomical Society of the Pacific. (2001) p. 347. ISBN 1-58381-065-X
  • Warner, B. ve Misra, M.: Understanding Neural Networks as Statistical Tools. The American Statistician (1996) 50(4) 284–293.
  • Vernin, J. ve ark.: European Extremely Large Telescope Site Characterization I: Overview. PASP (2011) 123 (909): 1334–1346
  • Vilalta, R.: Transfer Learning in Astronomy: A New Machine-Learning Paradigm. Journal of Physics: Conference Series. (2018) Volume 1085. Issue 5.
  • Vretinaris, S., Stergioulas, N., Bauswein, A.: Empirical relations for gravitational-wave asteroseismology of binary neutron star mergers”. Physical Review D (2020) 101(8) 084039.
  • Yeşilyaprak C. ve Yerli, S.K.: Atatürk Üniversitesi Astrofizik Araştırma Teleskobu (ATA50); Doğu Anadolu Gözlemevi (DAG). Türkiye’deki Teleskoplarla Bilim Sempozyumu. 14-15 Mayıs 2012 – İstanbul Üni. İstanbul (2012).
There are 48 citations in total.

Details

Primary Language Turkish
Subjects Astronomical Sciences (Other)
Journal Section Articles
Authors

Mustafa Özkan 0000-0002-6006-3172

Cenk Kayhan 0000-0001-9198-2289

Publication Date June 30, 2021
Submission Date March 12, 2021
Acceptance Date April 19, 2021
Published in Issue Year 2021 Volume: 2 Issue: 1

Cite

TJAA is a publication of Turkish Astronomical Society (TAD).