Deep Neural Networks With Convolutional and LSTM Layers for SYM‐H and ASY‐H Forecasting

Geomagnetic indices quantify the disturbance caused by the solar activity on a planetary scale or in particular regions of the Earth. Among them, the SYM‐H and ASY‐H indices represent the (longitudinally) symmetric and asymmetric geomagnetic disturbance of the horizontal component of the magnetic field at midlatitude with a 1‐min resolution. Their resolution, along with their relation to the solar wind parameters, makes the forecasting of the geomagnetic indices a problem that can be addressed through the use of Deep Learning, particularly using Deep Neural Networks (DNNs). In this work, we present two DNNs developed to forecast respectively the SYM‐H and ASY‐H indices. Both networks have been trained using the Interplanetary Magnetic Field (IMF) and the related index for the solar storms occurred in the last two solar cycles. As a result, the networks are able to accurately forecast the indices 2 h in advance, considering the IMF and indices values for the previous 200 min. The evaluation of both networks reveals a great forecasting precision, including good predictions for large storms that occurred during the solar cycle 23 and comparing with the persistence model for the period 2013–2020. Plain Language Summary Machine Learning applications are conquering new areas taking advantage of the availability of large amounts of data. Considering space probes such as ACE that are providing information about the solar wind at the L1 point for more than 25 years, it is feasible that Machine Learning approaches can be applied to the space weather context. In this work, we present a SYM‐H and ASY‐H indices (that quantify the disturbance of the Earth's magnetosphere) forecasting system for the next 1 and 2 h. To do so, we apply the state of the art in Artificial Neural Networks. The goal of the work is to drive an operational geomagnetic indices forecasting system that can minimize the damages caused by geomagnetic storms, providing an alert ahead enough to take containment measures. Key Points Deep Neural Networks using convolutional and Long Short‐Term Memory layers achieve great accuracy for SYM/ASY‐H indices forecasting up to 2 h The network only uses the magnetic field data measured by ACE and the own index as inputs The ASY‐H index is significantly harder to forecast than the SYM‐H index