Abstract
This paper describes a neural network-based model developed to predict geomagnetic storms time K index as measured at a magnetic observatory located in Hermanus (34°25 S; 19°13 E), South Africa. The parameters used as inputs to the neural network were the solar wind particle density N, the solar wind velocity V, the interplanetary magnetic field (IMF) total average field B t as well as the IMF B z component. Averaged hourly OMNI-2 data comprising storm periods extracted from solar cycle 23 (SC23) were used to train the neural network. The prediction performance of this model was tested on some moderate to severe storms (with K≥5) that were not included in the training data set and the results are compared to the prediction of the global geomagnetic Kp index. The model results show a good predictability of the Hermanus storm time K index with a correlation coefficient of 0.8.
Highlights
Geomagnetic storms are the common features of space weather causing a threat to ground- and space-based technology systems
Most of the intense geomagnetic storms are generally caused by fast coronal mass ejections (CMEs) which induce disturbances in the solar wind (SW)
The study described in this paper explored the application of Elman neural network (NN) techniques for predicting the locally measured geomagnetic K index at the Hermanus Magnetic Observatory
Summary
Geomagnetic storms are the common features of space weather causing a threat to ground- and space-based technology systems. Most of the intense geomagnetic storms are generally caused by fast coronal mass ejections (CMEs) which induce disturbances in the solar wind (SW). Geomagnetic storms occur as a result of the energy transfer from the SW to the Earth’s magnetosphere via magnetic reconnection. Changes in the SW plasma and the interplanetary magnetic field (IMF) are important factors to consider when developing magnetic storm forecast models. The physics of the magnetosphere and the interplanetary medium is not completely understood and there is still no comprehensive model of the solar-terrestrial environment. There have been various functional relationships proposed for magnetic storm prediction such models to predict the disturbance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
