Options
Using neural networks to study the geomagnetic field evolution
Issued date
October 2008
Issue/vol(year)
5-6/51 (2008)
Language
English
Pages
755-767
Abstract
study their time evolution in years. In order to find the best NN for the time predictions, we tested many different
kinds of NN and different ways of their training, when the inputs and targets are long annual time series of
synthetic geomagnetic field values. The found NN was used to predict the values of the annual means of the
geomagnetic field components beyond the time registration periods of a Geomagnetic Observatory. In order to
predict a time evolution of the global field over the Earth, we considered annual means of 105 Geomagnetic
Observatories, chosen to have more than 30 years registration (1960.5-2005.5) and to be well distributed over
the Earth. Using the NN technique, we created 137 «virtual geomagnetic observatories» in the places where
real Geomagnetic Observatories are missing. Then, using NN, we predicted the time evolution of the three
components of the global geomagnetic field beyond 2005.5.
kinds of NN and different ways of their training, when the inputs and targets are long annual time series of
synthetic geomagnetic field values. The found NN was used to predict the values of the annual means of the
geomagnetic field components beyond the time registration periods of a Geomagnetic Observatory. In order to
predict a time evolution of the global field over the Earth, we considered annual means of 105 Geomagnetic
Observatories, chosen to have more than 30 years registration (1960.5-2005.5) and to be well distributed over
the Earth. Using the NN technique, we created 137 «virtual geomagnetic observatories» in the places where
real Geomagnetic Observatories are missing. Then, using NN, we predicted the time evolution of the three
components of the global geomagnetic field beyond 2005.5.
References
Agg arwal, K.K., Y. Sing h, P. Chandra and M. Puri
(2005): Bayesian Regularization in a Neural Network
Model, Journal of Computer Sciences, 1 (4), 505-
509.
Demuth, H. and M. Beale (2004): Matlab Neural network
Toolbox User’s Guide, Version 4, The MathWorks inc.,
Natick, MA.
Duka, B. (2005): Modeling the geomagnetic field at different
observatories with nonlinear dynamical system of
equations, in the 10th Scientific Assembly of the International
Association of Geomagnetism and Aeronomy,
(July 18-29, 2005, Toulouse, France).
Frank, R.J., N. Dave and S.P. Hunt (2001): Time Series
Prediction and Neural Networks, Journal of Intelligent
and Robotic Systems, 31(1-3), 91-103.
Hong re, L., P. Sailhac, M. Alexandrescu and J. Dubois
(1999): Nonlinear and multifractal approaches of the geomagnetic
field, Phys. Earth Planet. Inter., 110, 157-190.
Jackson, A., A.R.T. Jonkers and M.R. Walker (2000):
Four centuries of geomagnetic secular variation from
historical records by Phil. Trans. R. Soc. Lond. A, 358,
957-990.
Kugblenu, K., S. Taguchi and T. Okuzawa (1999): Prediction
of the geomagnetic storm associated Dst index
using an artificial neural network algorithm, Earth
Planets Space, 51, 307-313.
(2005): Bayesian Regularization in a Neural Network
Model, Journal of Computer Sciences, 1 (4), 505-
509.
Demuth, H. and M. Beale (2004): Matlab Neural network
Toolbox User’s Guide, Version 4, The MathWorks inc.,
Natick, MA.
Duka, B. (2005): Modeling the geomagnetic field at different
observatories with nonlinear dynamical system of
equations, in the 10th Scientific Assembly of the International
Association of Geomagnetism and Aeronomy,
(July 18-29, 2005, Toulouse, France).
Frank, R.J., N. Dave and S.P. Hunt (2001): Time Series
Prediction and Neural Networks, Journal of Intelligent
and Robotic Systems, 31(1-3), 91-103.
Hong re, L., P. Sailhac, M. Alexandrescu and J. Dubois
(1999): Nonlinear and multifractal approaches of the geomagnetic
field, Phys. Earth Planet. Inter., 110, 157-190.
Jackson, A., A.R.T. Jonkers and M.R. Walker (2000):
Four centuries of geomagnetic secular variation from
historical records by Phil. Trans. R. Soc. Lond. A, 358,
957-990.
Kugblenu, K., S. Taguchi and T. Okuzawa (1999): Prediction
of the geomagnetic storm associated Dst index
using an artificial neural network algorithm, Earth
Planets Space, 51, 307-313.
Type
article
File(s)
Loading...
Name
02 Duka.pdf
Size
2.06 MB
Format
Adobe PDF
Checksum (MD5)
5859f369a1849e29023ffafdce53c0b6