Abstract
Considering the three components of the geomagnetic field as stochastic quantities, we used neural networks to 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.
Highlights
Artificial Neural networks (ANN or shortlyNeural Networks (NN)) are sets of connected neuron layers, which contain one or more neurons
The network inputs are the annual time series of the geomagnetic field component values and the targets are the known annual values of the geomagnetic field components that are shifted in some way from the input values
Concluding Remarks Testing a variety of NN offered by the Mat-Lab software package, we identified those NN that give the most accurate and the longest prediction when are applied on the geomagnetic field synthetic data
Summary
NN) are sets of connected neuron layers, which contain one or more neurons. Each neuron represents a known function f which transfers the input quantity p, multiplied by a weight w and added by a bias b, to the output a:. Using the first approach and the input series of 300 years long, we studied the influence of the kind of network on the relative error of the prediction of known values of X, Y, Z compo-. 6a, 6b, 6c) present the predicted values (the red curve) of X, Y, Z components of the geomagnetic field for different years of the horizon (d =15, from 1956 to 1970) in comparison with the known values from the model (black curve). The rms of deviations between predicted values (from 1991.5 to 2005.5) by NN and real values of the NGK Observatory for X, Y, Z components are respectively: 38.56 nT, 17.12 nT and 32.04 nT Comparing these results with those of the table 1 and 2 of the synthetic data (Gufm model), an increase of the prediction error is noticed. The time series of the geomagnetic field at a place S (t) depends on only one parameter
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
