Standard

Deep-learning approach for McIntosh-based classification of solar active regions using HMI and MDI images. / Knyazeva, Irina; Rybintsev, Andrey; Ohinko, Timur; Makarenko, Nikolay.

Advances in Neural Computation, Machine Learning, and Cognitive Research III - Selected Papers from the XXI International Conference on Neuroinformatics, 2019. ред. / Boris Kryzhanovsky; Witali Dunin-Barkowski; Vladimir Redko; Yury Tiumentsev. Springer Nature, 2020. стр. 239-245 (Studies in Computational Intelligence; Том 856).

Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование

Harvard

Knyazeva, I, Rybintsev, A, Ohinko, T & Makarenko, N 2020, Deep-learning approach for McIntosh-based classification of solar active regions using HMI and MDI images. в B Kryzhanovsky, W Dunin-Barkowski, V Redko & Y Tiumentsev (ред.), Advances in Neural Computation, Machine Learning, and Cognitive Research III - Selected Papers from the XXI International Conference on Neuroinformatics, 2019. Studies in Computational Intelligence, Том. 856, Springer Nature, стр. 239-245, 21st International Conference on Neuroinformatics, 2019, Dolgoprudny, Российская Федерация, 7/10/19. https://doi.org/10.1007/978-3-030-30425-6_28

APA

Knyazeva, I., Rybintsev, A., Ohinko, T., & Makarenko, N. (2020). Deep-learning approach for McIntosh-based classification of solar active regions using HMI and MDI images. в B. Kryzhanovsky, W. Dunin-Barkowski, V. Redko, & Y. Tiumentsev (Ред.), Advances in Neural Computation, Machine Learning, and Cognitive Research III - Selected Papers from the XXI International Conference on Neuroinformatics, 2019 (стр. 239-245). (Studies in Computational Intelligence; Том 856). Springer Nature. https://doi.org/10.1007/978-3-030-30425-6_28

Vancouver

Knyazeva I, Rybintsev A, Ohinko T, Makarenko N. Deep-learning approach for McIntosh-based classification of solar active regions using HMI and MDI images. в Kryzhanovsky B, Dunin-Barkowski W, Redko V, Tiumentsev Y, Редакторы, Advances in Neural Computation, Machine Learning, and Cognitive Research III - Selected Papers from the XXI International Conference on Neuroinformatics, 2019. Springer Nature. 2020. стр. 239-245. (Studies in Computational Intelligence). https://doi.org/10.1007/978-3-030-30425-6_28

Author

Knyazeva, Irina ; Rybintsev, Andrey ; Ohinko, Timur ; Makarenko, Nikolay. / Deep-learning approach for McIntosh-based classification of solar active regions using HMI and MDI images. Advances in Neural Computation, Machine Learning, and Cognitive Research III - Selected Papers from the XXI International Conference on Neuroinformatics, 2019. Редактор / Boris Kryzhanovsky ; Witali Dunin-Barkowski ; Vladimir Redko ; Yury Tiumentsev. Springer Nature, 2020. стр. 239-245 (Studies in Computational Intelligence).

BibTeX

@inproceedings{8b645ab31e804b30859ce7d91231b943,
title = "Deep-learning approach for McIntosh-based classification of solar active regions using HMI and MDI images",
abstract = "Solar active regions (ARs) are the primary source of solar flares. There are plenty of studies where the statistical relationship between ARs magnetic field complexity and solar flares are shown. Usually, the complexity of ARs described with different numerical magnetic field parameters and characteristics calculated on top of them. Also, there is well known and widely adapted McIntosh classification scheme of sunspot groups, consists of three letters abbreviation. Solar Monitor{\textquoteright}s flare prediction system{\textquoteright}s based on this classification. Up to date, the classification is done manual once a day by the specialist. In this paper, we describe an automatic system based on convolutional neural networks. For neural network training, we used images from two big magnetogram databases (HMI and MDI images) covered together period from 1996 to the 2018 years. Our results show that the automated classification of Solar ARs is possible with a moderate success rate, which allows to use it in practical tasks.",
keywords = "Deep learning, Image classification, McIntosh classification, Neural networks, Solar active regions",
author = "Irina Knyazeva and Andrey Rybintsev and Timur Ohinko and Nikolay Makarenko",
note = "Funding Information: We gratefully acknowledge financial support of Institute of Information and Computational Technologies (Grant AR05134227, Kazakhstan). Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2020. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; 21st International Conference on Neuroinformatics, 2019 ; Conference date: 07-10-2019 Through 11-10-2019",
year = "2020",
doi = "10.1007/978-3-030-30425-6_28",
language = "English",
isbn = "9783030304249",
series = "Studies in Computational Intelligence",
publisher = "Springer Nature",
pages = "239--245",
editor = "Boris Kryzhanovsky and Witali Dunin-Barkowski and Vladimir Redko and Yury Tiumentsev",
booktitle = "Advances in Neural Computation, Machine Learning, and Cognitive Research III - Selected Papers from the XXI International Conference on Neuroinformatics, 2019",
address = "Germany",

}

RIS

TY - GEN

T1 - Deep-learning approach for McIntosh-based classification of solar active regions using HMI and MDI images

AU - Knyazeva, Irina

AU - Rybintsev, Andrey

AU - Ohinko, Timur

AU - Makarenko, Nikolay

N1 - Funding Information: We gratefully acknowledge financial support of Institute of Information and Computational Technologies (Grant AR05134227, Kazakhstan). Publisher Copyright: © Springer Nature Switzerland AG 2020. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.

PY - 2020

Y1 - 2020

N2 - Solar active regions (ARs) are the primary source of solar flares. There are plenty of studies where the statistical relationship between ARs magnetic field complexity and solar flares are shown. Usually, the complexity of ARs described with different numerical magnetic field parameters and characteristics calculated on top of them. Also, there is well known and widely adapted McIntosh classification scheme of sunspot groups, consists of three letters abbreviation. Solar Monitor’s flare prediction system’s based on this classification. Up to date, the classification is done manual once a day by the specialist. In this paper, we describe an automatic system based on convolutional neural networks. For neural network training, we used images from two big magnetogram databases (HMI and MDI images) covered together period from 1996 to the 2018 years. Our results show that the automated classification of Solar ARs is possible with a moderate success rate, which allows to use it in practical tasks.

AB - Solar active regions (ARs) are the primary source of solar flares. There are plenty of studies where the statistical relationship between ARs magnetic field complexity and solar flares are shown. Usually, the complexity of ARs described with different numerical magnetic field parameters and characteristics calculated on top of them. Also, there is well known and widely adapted McIntosh classification scheme of sunspot groups, consists of three letters abbreviation. Solar Monitor’s flare prediction system’s based on this classification. Up to date, the classification is done manual once a day by the specialist. In this paper, we describe an automatic system based on convolutional neural networks. For neural network training, we used images from two big magnetogram databases (HMI and MDI images) covered together period from 1996 to the 2018 years. Our results show that the automated classification of Solar ARs is possible with a moderate success rate, which allows to use it in practical tasks.

KW - Deep learning

KW - Image classification

KW - McIntosh classification

KW - Neural networks

KW - Solar active regions

UR - http://www.scopus.com/inward/record.url?scp=85072823889&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/a7c3d14d-1ab4-316e-869d-ac917be4db65/

U2 - 10.1007/978-3-030-30425-6_28

DO - 10.1007/978-3-030-30425-6_28

M3 - Conference contribution

AN - SCOPUS:85072823889

SN - 9783030304249

T3 - Studies in Computational Intelligence

SP - 239

EP - 245

BT - Advances in Neural Computation, Machine Learning, and Cognitive Research III - Selected Papers from the XXI International Conference on Neuroinformatics, 2019

A2 - Kryzhanovsky, Boris

A2 - Dunin-Barkowski, Witali

A2 - Redko, Vladimir

A2 - Tiumentsev, Yury

PB - Springer Nature

T2 - 21st International Conference on Neuroinformatics, 2019

Y2 - 7 October 2019 through 11 October 2019

ER -

ID: 71884620