Abstract. Geomagnetic storms and substorms develop under strong control of the solar wind. This is demonstrated by the fact that the geomagnetic activity indices Dst and AE can be predicted from the solar wind alone. A consequence of the strong control by a common source is that substorm and storm indices tend to be highly correlated. However, a part of this correlation is likely to be an effect of internal magnetospheric processes, such as a ring-current modulation of the solar wind-AE relation. The present work extends previous studies of nonlinear AE predictions from the solar wind. It is examined whether the AE predictions are modulated by the Dst index.This is accomplished by comparing neural network predictions from Dst and the solar wind, with predictions from the solar wind alone. Two conclusions are reached: (1) with an optimal set of solar-wind data available, the AE predictions are not markedly improved by the Dst input, but (2) the AE predictions are improved by Dst if less than, or other than, the optimum solar-wind data are available to the net. It appears that the solar wind-AE relation described by an optimized neural net is not significantly modified by the magnetosphere's Dst state. When the solar wind alone is used to predict AE, the correlation between predicted and observed AE is 0.86, while the prediction residual is nearly uncorrelated to Dst. Further, the finding that Dst can partly compensate for missing information on the solar wind, is of potential importance in operational forecasting where gaps in the stream of real time solar-wind data are a common occurrence.Key words. Magnetospheric physics (solar wind · magnetosphere interactions; storms and substorms)
Predicting geomagnetic storms from solar-wind data using time-delay neural networks
