Standard

Multi-output Deep Learning Framework for Solar Atmospheric Parameters Inferring from Stokes Profiles. / Knyazeva, Irina; Plotnikov, Andrey; Medvedeva, Tatiana; Makarenko, Nikolay.

Advances in Neural Computation, Machine Learning, and Cognitive Research 5 - Selected Papers from the 23rd International Conference on Neuroinformatics, 2021. ed. / Boris Kryzhanovsky; Witali Dunin-Barkowski; Vladimir Redko; Yury Tiumentsev; Valentin V. Klimov. Springer Nature, 2021. p. 299-307 (Studies in Computational Intelligence; Vol. 1008 SCI).

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

Harvard

Knyazeva, I, Plotnikov, A, Medvedeva, T & Makarenko, N 2021, Multi-output Deep Learning Framework for Solar Atmospheric Parameters Inferring from Stokes Profiles. in B Kryzhanovsky, W Dunin-Barkowski, V Redko, Y Tiumentsev & VV Klimov (eds), Advances in Neural Computation, Machine Learning, and Cognitive Research 5 - Selected Papers from the 23rd International Conference on Neuroinformatics, 2021. Studies in Computational Intelligence, vol. 1008 SCI, Springer Nature, pp. 299-307, 23rd International Conference on Neuroinformatics, 2021, Moscow, Russian Federation, 18/10/21. https://doi.org/10.1007/978-3-030-91581-0_40

APA

Knyazeva, I., Plotnikov, A., Medvedeva, T., & Makarenko, N. (2021). Multi-output Deep Learning Framework for Solar Atmospheric Parameters Inferring from Stokes Profiles. In B. Kryzhanovsky, W. Dunin-Barkowski, V. Redko, Y. Tiumentsev, & V. V. Klimov (Eds.), Advances in Neural Computation, Machine Learning, and Cognitive Research 5 - Selected Papers from the 23rd International Conference on Neuroinformatics, 2021 (pp. 299-307). (Studies in Computational Intelligence; Vol. 1008 SCI). Springer Nature. https://doi.org/10.1007/978-3-030-91581-0_40

Vancouver

Knyazeva I, Plotnikov A, Medvedeva T, Makarenko N. Multi-output Deep Learning Framework for Solar Atmospheric Parameters Inferring from Stokes Profiles. In Kryzhanovsky B, Dunin-Barkowski W, Redko V, Tiumentsev Y, Klimov VV, editors, Advances in Neural Computation, Machine Learning, and Cognitive Research 5 - Selected Papers from the 23rd International Conference on Neuroinformatics, 2021. Springer Nature. 2021. p. 299-307. (Studies in Computational Intelligence). https://doi.org/10.1007/978-3-030-91581-0_40

Author

Knyazeva, Irina ; Plotnikov, Andrey ; Medvedeva, Tatiana ; Makarenko, Nikolay. / Multi-output Deep Learning Framework for Solar Atmospheric Parameters Inferring from Stokes Profiles. Advances in Neural Computation, Machine Learning, and Cognitive Research 5 - Selected Papers from the 23rd International Conference on Neuroinformatics, 2021. editor / Boris Kryzhanovsky ; Witali Dunin-Barkowski ; Vladimir Redko ; Yury Tiumentsev ; Valentin V. Klimov. Springer Nature, 2021. pp. 299-307 (Studies in Computational Intelligence).

BibTeX

@inproceedings{c15d1bdcc0824b48ab3dfd1bf711a182,
title = "Multi-output Deep Learning Framework for Solar Atmospheric Parameters Inferring from Stokes Profiles",
abstract = "Spectropolarimetric observations are broadly used for the extraction of physical information in the field of solar physics. Inferring magnetic and thermodynamic information from these observations includes inversion problem solving. Assuming that spectropolarimetric profiles are produced by a given atmospheric model, it is required to find the best sets of parameters within such a model corresponding to particular observations. Standard optimization approach often requires large computational resources and even in this case still performs very slowly. Previously it was suggested to use different strategies with artificial neural networks to overcome problems with computational power. It was previously shown that neural networks could be a viable alternative to the standard least square approach, but they could not replace it. Most papers only cover Magnetic Fields Vector parameter inferring, whereas the commonly used solar atmosphere model includes 11 parameters. In this paper we provide an end-to-end deep learning framework for full parameter inferring as well as comparison of several approaches for multi-output predictions. For this purpose, we trained one common network to predict all parameters, a set of parameter-oriented independent networks to deal with each parameter, and finally a combination of the above: a set of parameter-oriented independent networks built upon several layers of the pretrained common network. Our results show that using a partly independent network built upon a pretrained network provides the best results and demonstrates better generalization performance.",
keywords = "Deep learning, Inverse problem, Magnetic fields, Multi-task learning, Spectral lines",
author = "Irina Knyazeva and Andrey Plotnikov and Tatiana Medvedeva and Nikolay Makarenko",
note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 23rd International Conference on Neuroinformatics, 2021 ; Conference date: 18-10-2021 Through 22-10-2021",
year = "2021",
doi = "10.1007/978-3-030-91581-0_40",
language = "English",
isbn = "9783030915803",
series = "Studies in Computational Intelligence",
publisher = "Springer Nature",
pages = "299--307",
editor = "Boris Kryzhanovsky and Witali Dunin-Barkowski and Vladimir Redko and Yury Tiumentsev and Klimov, {Valentin V.}",
booktitle = "Advances in Neural Computation, Machine Learning, and Cognitive Research 5 - Selected Papers from the 23rd International Conference on Neuroinformatics, 2021",
address = "Germany",

}

RIS

TY - GEN

T1 - Multi-output Deep Learning Framework for Solar Atmospheric Parameters Inferring from Stokes Profiles

AU - Knyazeva, Irina

AU - Plotnikov, Andrey

AU - Medvedeva, Tatiana

AU - Makarenko, Nikolay

N1 - Publisher Copyright: © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2021

Y1 - 2021

N2 - Spectropolarimetric observations are broadly used for the extraction of physical information in the field of solar physics. Inferring magnetic and thermodynamic information from these observations includes inversion problem solving. Assuming that spectropolarimetric profiles are produced by a given atmospheric model, it is required to find the best sets of parameters within such a model corresponding to particular observations. Standard optimization approach often requires large computational resources and even in this case still performs very slowly. Previously it was suggested to use different strategies with artificial neural networks to overcome problems with computational power. It was previously shown that neural networks could be a viable alternative to the standard least square approach, but they could not replace it. Most papers only cover Magnetic Fields Vector parameter inferring, whereas the commonly used solar atmosphere model includes 11 parameters. In this paper we provide an end-to-end deep learning framework for full parameter inferring as well as comparison of several approaches for multi-output predictions. For this purpose, we trained one common network to predict all parameters, a set of parameter-oriented independent networks to deal with each parameter, and finally a combination of the above: a set of parameter-oriented independent networks built upon several layers of the pretrained common network. Our results show that using a partly independent network built upon a pretrained network provides the best results and demonstrates better generalization performance.

AB - Spectropolarimetric observations are broadly used for the extraction of physical information in the field of solar physics. Inferring magnetic and thermodynamic information from these observations includes inversion problem solving. Assuming that spectropolarimetric profiles are produced by a given atmospheric model, it is required to find the best sets of parameters within such a model corresponding to particular observations. Standard optimization approach often requires large computational resources and even in this case still performs very slowly. Previously it was suggested to use different strategies with artificial neural networks to overcome problems with computational power. It was previously shown that neural networks could be a viable alternative to the standard least square approach, but they could not replace it. Most papers only cover Magnetic Fields Vector parameter inferring, whereas the commonly used solar atmosphere model includes 11 parameters. In this paper we provide an end-to-end deep learning framework for full parameter inferring as well as comparison of several approaches for multi-output predictions. For this purpose, we trained one common network to predict all parameters, a set of parameter-oriented independent networks to deal with each parameter, and finally a combination of the above: a set of parameter-oriented independent networks built upon several layers of the pretrained common network. Our results show that using a partly independent network built upon a pretrained network provides the best results and demonstrates better generalization performance.

KW - Deep learning

KW - Inverse problem

KW - Magnetic fields

KW - Multi-task learning

KW - Spectral lines

UR - http://www.scopus.com/inward/record.url?scp=85121582905&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-91581-0_40

DO - 10.1007/978-3-030-91581-0_40

M3 - Conference contribution

AN - SCOPUS:85121582905

SN - 9783030915803

T3 - Studies in Computational Intelligence

SP - 299

EP - 307

BT - Advances in Neural Computation, Machine Learning, and Cognitive Research 5 - Selected Papers from the 23rd International Conference on Neuroinformatics, 2021

A2 - Kryzhanovsky, Boris

A2 - Dunin-Barkowski, Witali

A2 - Redko, Vladimir

A2 - Tiumentsev, Yury

A2 - Klimov, Valentin V.

PB - Springer Nature

T2 - 23rd International Conference on Neuroinformatics, 2021

Y2 - 18 October 2021 through 22 October 2021

ER -

ID: 92451072