The Use of Coupling Functions in the Forecasting of the Dst-Index Amplitude with Adaptive MethodsстатьяИсследовательская статья
Информация о цитировании статьи получена из
Web of Science,
Scopus
Статья опубликована в журнале из списка Web of Science и/или Scopus
Дата последнего поиска статьи во внешних источниках: 28 июля 2021 г.
Аннотация:The possible use of artificial neural networks—classical multilayer perceptrons—with coupling functions to forecast time series of the Dst geomagnetic index is studied. The basic forecast is based on parameters of the solar wind and interplanetary magnetic field measured at the libration point L1 in an experiment on the ACE spacecraft. It is shown that the largest contribution to the improvement in forecast quality is made by the Bs and vBs functions, as well as the use of several coupling functions simultaneously.