The studies about the Sun rise a strong interest regarding modifications caused by the solar activity on the Earth. For almost a century in literature was discussed the problem of forecasting and analysis of the space weather, which in his definition covers both the near-earth space and the biospheric affection clue to the environmental interaction with the Sun. In particular in the last years increased the attention for magnetospheric response in conjunction with the technological infrastructure and the biosphere itself. This to prevent i.e. spacecraft failures or possible treats to human health. Since the main effect of the activity of the Sun is the solar wind, rises the aim to found a correlation between itself and the localized variations induced on the magnetosphere being the purpose to predict long-term variation of the magnetic field from solar wind time series. As recently proposed for solar wind forecasting, an hybrid approach will be here used than joining the wavelet analysis with the prediction capabilities of recurrent neural networks with an adaptive amplitude activation function algorithm in order to avoid the need to standardize or resealing the input signal and to match the exact range of the activation function.

Exploiting solar wind time series correlation with magnetospheric response by using an hybrid neuro-wavelet approach

NAPOLI, CHRISTIAN;CAPIZZI, GIACOMO
2010-01-01

Abstract

The studies about the Sun rise a strong interest regarding modifications caused by the solar activity on the Earth. For almost a century in literature was discussed the problem of forecasting and analysis of the space weather, which in his definition covers both the near-earth space and the biospheric affection clue to the environmental interaction with the Sun. In particular in the last years increased the attention for magnetospheric response in conjunction with the technological infrastructure and the biosphere itself. This to prevent i.e. spacecraft failures or possible treats to human health. Since the main effect of the activity of the Sun is the solar wind, rises the aim to found a correlation between itself and the localized variations induced on the magnetosphere being the purpose to predict long-term variation of the magnetic field from solar wind time series. As recently proposed for solar wind forecasting, an hybrid approach will be here used than joining the wavelet analysis with the prediction capabilities of recurrent neural networks with an adaptive amplitude activation function algorithm in order to avoid the need to standardize or resealing the input signal and to match the exact range of the activation function.
2010
978-0-52119-741-0
Neural networks; Data analysis; Magnetic fields
File in questo prodotto:
File Dimensione Formato  
S1743921311006806a.pdf

solo gestori archivio

Tipologia: Versione Editoriale (PDF)
Dimensione 158.44 kB
Formato Adobe PDF
158.44 kB 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/20.500.11769/79686
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 33
  • ???jsp.display-item.citation.isi??? 9
social impact