Prediction of Geomagnetic Variations Using ANN

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 different kinds of NN and different ways of their training, where the inputs and targets are long hourly time series of geomagnetic field values. The found NN was used to predict the values of the hourly mean values of the geomagnetic field components.