Вестник Мининского университета (Sep 2017)
CLASSIFICATION ALGORITHM FOR MHD WAVELET-SKELETON SPECTRAL IMAGES OF GEOEFFECTIVE PLASMA FLOWS IN THE SOLAR WIND
Abstract
The paper presents a new method for the identification of plasma flows in the solar wind by self-learning classification neural network using their spectral features in the range of magnetic hydrodynamics. To do this, the wavelet skeleton spectra of solar wind parameters of the interplanetary magnetic field recorded in Earth orbit by patrol spacecraft was calculated. Algorithm for classification of wavelet skeleton spectral images for plasma flows in the solar wind on the Earth's orbit, based on neural network processing of compressed data on the main magnetic and dynamic parameters of the flow is proposed. The classification by a neural network type Kohonen layer differentiated by frequency ranges is performed. Specifically, the spectral features of solar plasma flows in the form of magnetic clouds (MC), corotating interaction regions (CIR), shock waves (Shocks) and high-speed streams from coronal holes (HSS) analyzed and established.
