Modelling and Prediction of Global Magnetic Disturbance in Near-Earth Space: a Case Study for Kp Index using NARX Models

Severe geomagnetic disturbances can be hazardous for mod-ern technological systems. The reliable forecast of parameters related to thestate of the magnetosphere can facilitate the mitigation of adverse effects ofspace weather. This study is devoted to the modeling and forecasting of theevolution of the Kp index related to global geomagnetic disturbances. Through-out this work the Nonlinear AutoRegressive with eXogenous inputs (NARX)methodology is applied. Two approaches are presented: i) a recursive slid-ing window approach, and ii) a direct approach. These two approaches arestudied separately and are then compared to evaluate their performances.It is shown that the direct approach outperforms the recursive approach, butboth tend to produce predictions slightly biased from the true values for lowand high disturbances.