Abstract This paper investigates the possibility of predicting the time series of the geomagnetic index Dst. The prediction is based on parameters of the solar wind and interplanetary magnetic field measured at Lagrange point L1 within the Advanced Composition Explorer (ACE) spacecraft experiment using machine learning methods—artificial neural networks: classical perceptrons, recurrent networks of long short-term memory (LSTM), and committees of predictive models. Ultimately, the best results have been obtained using heterogeneous committees based on neural networks of both types.
The Prediction of the Dst-Index Based on Machine Learning Methods
Cosmic Research ; 56 , 6 ; 434-441
2018-11-01
8 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
The Prediction of the Dst-Index Based on Machine Learning Methods
Online Contents | 2018
|Machine Learning Based Prediction of Soil pH
IEEE | 2021
|Severity prediction of motorcycle crashes with machine learning methods
Taylor & Francis Verlag | 2020
|Comparing Machine Learning and Deep Learning Methods for Real-Time Crash Prediction
Transportation Research Record | 2019
|