ON THE PREDICTION OF SOLAR-ACTIVITY USING DIFFERENT NEURAL-NETWORK MODELS

Authors
FESSANT F BENGIO S COLLOBERT D
Citation
F. Fessant et al., ON THE PREDICTION OF SOLAR-ACTIVITY USING DIFFERENT NEURAL-NETWORK MODELS, Annales geophysicae, 14(1), 1996, pp. 20-26
Citations number
32
Categorie Soggetti
Astronomy & Astrophysics","Geosciences, Interdisciplinary","Metereology & Atmospheric Sciences
Journal title
Annales geophysicae → ACNP
ISSN journal
09927689
Volume
14
Issue
1
Year of publication
1996
Pages
20 - 26
Database
ISI
SICI code
0992-7689(1996)14:1<20:OTPOSU>2.0.ZU;2-G
Abstract
Accurate prediction of ionospheric parameters is crucial for telecommu nication companies. These parameters rely strongly on solar activity. In this paper, we analyze the use of neural networks for sunspot time series prediction. Three types of models are tested and experimental r esults are reported for a particular sunspot time series: the IR5 inde x.