Prediction of geomagnetic storms from solar wind data using Elman Recurrent Neural Networks

In order to accurately predict geomagnetic storms, we exploit Elman recurrent neural networks to predict the Dst index one hour in advance only from solar wind data. The input parameters are the interplanetary magnetic field z-component Bz (GSM), the solar wind plasma number density n and the solar wind velocity V. The solar wind data and the geomagnetic index Dst are selected from observations during the period 1963 to 1987, covering 8620h and containing 97 storms and 10 quiet periods. These data are grouped into three data sets; a training set 4877h, a validation set 1978h and a test set 1765h. It is found that different strengths of the geomagnetic storms are accurately predicted, and so are all phases of the storms. As an average for the out-of-sample performance, the correlation coefficient between the predicted and the observed Dst is 0.91. The predicted average relative variance is 0.17, i.e. 83 percent of the observed Dst variance is predictable by the solar wind. The predicted root-mean-square error is 16 nT.