Neural network classification of discontinuities in space plasma parameters

The artificial neural network technique is applied to the method for dividing discontinuities in space plasma and magnetic field parameters into classes corresponding to the known types of magnetohydrodynamic discontinuities. Parameter discontinuities recorded by the WIND spacecraft in 1996-1999 are classified by means of the network of the Kohonen layer type. We propose an algorithm for determining the orientation of discontinuity surfaces from one-dimensional observations of solar wind parameter discontinuities on board spacecraft.