Automatic Burst Detection in Solar Radio Spectrograms Using Deep Learning: deARCE Method
-
Published:2023-06
Issue:6
Volume:298
Page:
-
ISSN:0038-0938
-
Container-title:Solar Physics
-
language:en
-
Short-container-title:Sol Phys
Author:
Bussons Gordo JavierORCID, Fernández Ruiz MarioORCID, Prieto Mateo ManuelORCID, Alvarado Díaz JorgeORCID, Chávez de la O FranciscoORCID, Ignacio Hidalgo J.ORCID, Monstein ChristianORCID
Abstract
AbstractWe present in detail an automatic radio-burst detection system, based on the convolutional neural network, for use with any kind of solar spectrogram. A full methodology for model training, performance evaluation, and feedback to the model generator has been developed with special emphasis on i) robustness tests against stochastic and overfitting effects, ii) specific metrics adapted to the unbalanced nature of the solar-burst scenario, iii) tunable parameters for probability-threshold optimization, and iv) burst-coincidence cross match among e-Callisto stations and with external observatories (NOAA-SWPC). The resulting neural network configuration has been designed to accept data from observatories other than e-Callisto, either ground- or spacecraft-based. Typical False Negative and False Positive Scores in single-observatory mode are, respectively, in the 10 – 16% and 6 – 8% ranges, which improve further in cross-match mode. This mode includes new services (, ) allowing the end-user to check at a glance if a solar radio burst has taken place with a high level of confidence.
Funder
Fundación Séneca Junta de Comunidades de Castilla-La Mancha Ministerio de Ciencia e Innovación Comunidad de Madrid Universidad de Alcalá
Publisher
Springer Science and Business Media LLC
Subject
Space and Planetary Science,Astronomy and Astrophysics
Reference23 articles.
1. Afandi, N.Z.M., Sabri, N.H., Umar, R., Monstein, C.: 2020, Burst-finder: burst recognition for E-CALLISTO spectra. Indian J. Phys. 94, 947. DOI. 2. Anguita, D., Ghelardoni, L., Ghio, A., Oneto, L., Ridella, S.: 2012, The ‘K’ in K-fold cross validation. In: 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 441. i6doc.com/en/livre/?GCOI=28001100967420. Accessed on 21 December 2022. 3. Benz, A.O., Monstein, C., Meyer, H., Manoharan, P.K., Ramesh, R., Altyntsev, A., Lara, A., Paez, J., Cho, K.-S.: 2009, A World-Wide Net of Solar Radio Spectrometers: e-CALLISTO. Earth Moon Planets 104, 277. DOI. 4. Chen, Z., Ma, L., Xu, L., Tan, C., Yan, Y.: 2016, Imaging and representation learning of solar radio spectrums for classification. Multimed. Tools Appl. 75, 2859. DOI. 5. Gómez-Herrero, R., Pacheco, D., Kollhoff, A., Espinosa Lara, F., Freiherr von Forstner, J.L., Dresing, N., Lario, D., Balmaceda, L., Krupar, V., Malandraki, O.E., Aran, A., Bučík, R., Klassen, A., Klein, K.-L., Cernuda, I., Eldrum, S., Reid, H., Mitchell, J.G., Mason, G.M., Ho, G.C., Rodríguez-Pacheco, J., Wimmer-Schweingruber, R.F., Heber, B., Berger, L., Allen, R.C., Janitzek, N.P., Laurenza, M., De Marco, R., Wijsen, N., Kartavykh, Y.Y., Dröge, W., Horbury, T.S., Maksimovic, M., Owen, C.J., Vecchio, A., Bonnin, X., Kruparova, O., Pí ša, D., Souček, J., Louarn, P., Fedorov, A., O’Brien, H., Evans, V., Angelini, V., Zucca, P., Prieto, M., Sánchez-Prieto, S., Carrasco, A., Blanco, J.J., Parra, P., Rodríguez-Polo, O., Martín, C., Terasa, J.C., Boden, S., Kulkarni, S.R., Ravanbakhsh, A., Yedla, M., Xu, Z., Andrews, G.B., Schlemm, C.E., Seifert, H., Tyagi, K., Lees, W.J., Hayes, J.: 2021, First near-relativistic solar electron events observed by EPD onboard Solar Orbiter. Astron. Astrophys. 656, L3. DOI. ADS.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|