Forecasting the Geomagnetic Activity of the Dst Index Using Radial Basis Function Networks

The Dst index is a key parameter which characterises the disturbance of the geomagnetic field in magnetic storms. Modelling of the Dst index is thus very important for the analysis of the geomagnetic field. A data-based modelling approach, aimed at obtaining efficient models based on limited inputoutput observational data, provides a powerful tool for analysing and forecasting geomagnetic activities including the prediction of the Dst index. Radial basis function (RBF) networks are an important and popular network model for nonlinear system identification and dynamical modelling. A novel generalised multiscale RBF (MSRBF) network is introduced for Dst index modelling. The proposed MSRBF network can easily be converted into a linear-in-the-parameters form and the training of the linear network model can easily be implemented using an orthogonal least squares (OLS) type algorithm. One advantage of the new MSRBF network, compared with traditional single scale RBF networks, is that the new network is more flexible for describing complex nonlinear dynamical systems.