A Deep Learning model to predict geomagnetic storm from solar wind data

Abstract

A deep learning model to predict the geomagnetic storm index (Dst index) 24 hours in advance using solar wind data was proposed. The model employs a two-step prediction process: the preliminary prediction is performed using a Transformer-based model, and the second prediction utilizes multiple models selected according to the preliminary prediction values. The optimal combination of models was explored to minimize RMSE for the contest, resulting in a best RMSE of 28.381 on the test data.