Abstract
A nonlinear autoregressive approach with exogenous input is used as a novel method for statistical forecasting of the disturbance storm time index, a measure of space weather related to the ring current which surrounds the Earth, and fluctuations in disturbance storm time field strength as a result of incoming solar particles. This ring current produces a magnetic field which opposes the planetary geomagnetic field. Given the occurrence of solar activity hours or days before subsequent geomagnetic fluctuations and the potential effects that geomagnetic storms have on terrestrial systems, it would be useful to be able to predict geophysical parameters in advance using both historical disturbance storm time indices and external input of solar winds and the interplanetary magnetic field. By assessing various statistical techniques it is determined that artificial neural networks may be ideal for the prediction of disturbance storm time index values which may in turn be used to forecast geomagnetic storms. Furthermore, it is found that a Bayesian regularization neural network algorithm may be the most accurate model compared to both other forms of artificial neural network used and the linear models employing regression analyses.
Highlights
Many complex system interactions are present throughout the disciplines of geophysics and associated solar dy-How to cite this paper: Caswell, J.M. (2014) A Nonlinear Autoregressive Approach to Statistical Prediction of Disturbance Storm Time Geomagnetic Fluctuations Using Solar Data
The disturbance storm time (DST) index was used as the target variable to be predicted, while a number of solar wind and interplanetary magnetic field (IMF) measures were employed as independent variables (Bx, By, and Bz components of the IMF in nT, solar wind proton density in N·cm−3, solar wind plasma speed in km·s−1, and plasma flow pressure in nPa)
These results suggest that neural network methods produce a greater predictive capacity for both fit and accuracy in the context of DST index and solar winds compared to more traditional regression methods, while the Bayesian regularization (BRANN) algorithm was superior to other variations of Artificial neural networks (ANN) (Figure 13)
Summary
Many complex system interactions are present throughout the disciplines of geophysics and associated solar dy-How to cite this paper: Caswell, J.M. (2014) A Nonlinear Autoregressive Approach to Statistical Prediction of Disturbance Storm Time Geomagnetic Fluctuations Using Solar Data. Each input and hidden neuron consists of statistical weights which are capable of adaptation [2], the exact parameters which are modified by an algorithm over the course of network training procedures These weights essentially form the synaptic connections among neurons which activate during network construction. Because neural networks do not rely on linear correlations for learning, ANNs are capable of nonlinear modelling and may provide a useful alternative approach to a number of both theoretical and real world problems. This includes geo and solar physics [3], medical diagnosis [4], pattern recognition [5], and many other areas. The nonlinear approach used in ANN computations is useful in the context of highly complex or “noisy” datasets
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.
