Neural Network Prediction of Daily Relativistic Electrons Fluence in the Outer Radiation Belt of the Earth: Selection of Delay Embedding Method

Abstract

Prediction of the time series of relativistic electrons fluence in the outer radiation belt of the Earth encounters problems caused by complexity and non-linearity of the “solar wind – the Earth’s magnetosphere” system. Artificial neural networks are a biologically inspired architecture that is a suitable tool to solve problems of such type. This study considers the dependence of the quality of prediction on the type and depth of delay embedding of input features.