A neural network model relating ΔH at a single station to Dst Original Research Article

The operational goal of real-time estimation of the Dst index from single-station ΔH requires a good understanding of how ΔH depends on local time, storm conditions, and season of year. In this investigation artificial neural networks are trained on several years of data for the San Juan magnetometer. One neural network produces ΔH given Dst, local time, day of year; the other additionally requires Solar Wind dynamic pressure and interplanetary electric field. The neural networks illustrate the local time, seasonal, and storm modulation of the nearly linear relationship between Dst and ΔH. We present evidence that a seasonal offset may be present in the Dst index. We also demonstrate that the partial ring current, as measured by the asymmetry index, persists, after the interplanetary electric field has vanished, for larger values of Dst during northern winter, and that this asymmetry is linearly proportional to Dst.