The use of artificial neural network segmentation of multivariate time series for the analysis of geomagnetic disturbances

Abstract

This study is devoted to a preliminary analysis of the segmentation of multivariate time series of the parameters of the solar wind, interplanetary magnetic field, and the Dst index using artificial neural networks, for the period from November 1997 to March 2014. It is shown that this technique allows progress in understanding the dynamics of the Earth’s magnetosphere.