Space Weather (SW) poses a hazard to modern society. SW phenomena depend on the Sun's magnetic field and understanding and forecasting the solar magnetic field is an important research subject. To achieve this goal, in this paper Global Oscillation Network Group (GONG) solar magnetograms 2006-2019 are investigated with different approaches provided by unsupervised and supervised Computational Intelligence techniques. Such techniques were successful at providing insights into the behavior and evolution of the photospheric magnetic field, revealing patterns of activity and their relation with the different phases of the solar cycle. On the one hand, representative prototypes of synoptic maps were found, capturing the variations in homogeneity, intensity and variability of magnetic activity. On the other hand, Convolutional neural networks combined with transfer learning and dimensionality reduction techniques were helpful in providing classification models which accurately predict classes associated to the main stages of the cycle. Such models provide results in good correspondence with the natural classes found in feature spaces and have classification errors concentrated mostly at transition periods of the solar cycles.

A Computational Intelligence Characterization of Solar Magnetograms

Disabato S.;Roveri M.
2020-01-01

Abstract

Space Weather (SW) poses a hazard to modern society. SW phenomena depend on the Sun's magnetic field and understanding and forecasting the solar magnetic field is an important research subject. To achieve this goal, in this paper Global Oscillation Network Group (GONG) solar magnetograms 2006-2019 are investigated with different approaches provided by unsupervised and supervised Computational Intelligence techniques. Such techniques were successful at providing insights into the behavior and evolution of the photospheric magnetic field, revealing patterns of activity and their relation with the different phases of the solar cycle. On the one hand, representative prototypes of synoptic maps were found, capturing the variations in homogeneity, intensity and variability of magnetic activity. On the other hand, Convolutional neural networks combined with transfer learning and dimensionality reduction techniques were helpful in providing classification models which accurately predict classes associated to the main stages of the cycle. Such models provide results in good correspondence with the natural classes found in feature spaces and have classification errors concentrated mostly at transition periods of the solar cycles.
Proceedings of the International Joint Conference on Neural Networks
978-1-7281-6926-2
clustering (optics, pam, kmeans)
computational intelligence
convolutional neural networks
deep learning
intrinsic dimension
low dimensional mappings
MSSIM image similarity
solar synoptic maps
Space weather
svm
transfer learning
File in questo prodotto:
File Dimensione Formato  
09206596.pdf

Accesso riservato

: Publisher’s version
Dimensione 5.7 MB
Formato Adobe PDF
5.7 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1169405
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact