Forecasting geomagnetic activity indices using the Boyle index through artificial neural networks
Reiff, Patricia H.
Doctor of Philosophy
Adverse space weather conditions affect various sectors making both human lives and technologies highly susceptible. This dissertation introduces a new set of algorithms suitable for short term space weather forecasts with an enhanced lead-time and better accuracy in predicting Kp, Dst and the AE index over some leading models. Kp is a 3-hour averaged global geomagnetic activity index good for midlatitude regions. The Dst index, an hourly index calculated using four ground based magnetic field measurements near the equator, measures the energy of the Earth's ring current. The Auroral Electrojet indices or AE indices are hourly indices used to characterize the global geomagnetic activity in the auroral zone. Our algorithms can predict these indices purely from the solar wind data with lead times up to 6 hours. We have trained and tested an ANN (Artificial Neural Network) over a complete solar cycle to serve this purpose. Over the last couple of decades, ANNs have been successful for temporal prediction problems amongst other advanced non-linear techniques. Our ANN-based algorithms receive near-real-time inputs either from ACE (Advanced Composition Explorer), located at L1, and a handful of ground-based magnetometers or only from ACE. The Boyle potential, phi = 10-4 &parl0;vkm/sec&parr0;2+ 11.7BnT sin3 (theta/2) kV, or the Boyle Index (BI) is an empirically-derived formula that approximates the Earth's polar cap potential and is easily derivable in real time using the solar wind data from ACE. The logarithms of both 3-hour and 1-hour averages of the Boyle Index correlate well with the subsequent Kp, Dst and AE: Kp = 8.93 log 10<BI> - 12.55. Dst = 0.355<BI> - 6.48, and AE = 5.87<BI> - 83.46. Inputs to our ANN models have greatly benefitted from the BI and its proven record as a forecasting parameter since its initiation in October, 2003. A preconditioning event tunes the magnetosphere to a specific state before an impending geomagnetic storm. The neural net not only improves the predictions but also helps the prediction by capturing the influence of preconditioning. Two of our models have been running in near-real-time forecast mode already, and the BI and Kp predictions can be obtained from http://space.rice.edu/ISTP/wind.html.