Geomagnetic Index Kp Forecasting With LSTM

Abstract Through making full use of the solar wind and interplanetary magnetic field data accumulated by ACE satellites we improve the prediction accuracy of the Kp geomagnetic index and accurately predict the occurrence of geomagnetic storms ( Kp ≥ 5). Specially, we use long short‐term memory to train the Kp forecast model described in this study. Based on the large‐scale data, we build the Kp forecasting model with solar wind, interplanetary magnetic field parameters, and the historical Kp value as input. In this study, we first analyze the distribution of Kp and the effect of the data imbalance on the prediction of geomagnetic storms. Second, we analyze the correlation between the different input parameters and Kp . Thus, the input parameters of the model are selected by the results of the correlation. We consider two types of forecasting: one is the overall Kp forecasting and the other is the geomagnetic storm ( Kp ≥ 5) forecasting. Hence, we design an integrated model which is then compared with other models. Some evaluation parameters are introduced: the root‐mean‐square error, the mean‐absolute error, and the correlation coefficient, as well as the measurement of geomagnetic storms ( Kp ≥ 5) F 1. The root‐mean‐square error and mean‐absolute error of our model are 0.4765 and 0.6382, respectively. The experimental results show that the proposed model with long short‐term memory improve the Kp forecasting.