Solar wind prediction using Deep learning

Emanating from the base of the Sun’s corona, the solar wind fills the interplanetary medium with a magnetized stream of charged particles whose interaction with the Earth’s magnetosphere has space weather consequences such as geomagnetic storms. Accurately predicting the solar wind through measurements of the spatio-temporally evolving conditions in the solar atmosphere is important but remains an unsolved problem in heliophysics and space-weather research. In this work, deep learning is used for the prediction of solar-wind speed. Extreme Ultraviolet (EUV) coronal data is used to predict solar wind speed measured at Lagrange point L1. The proposed model obtains a best fit correlation of 0.54 ± 0.04 with the wind speed . Visualization and investigation of activations of the model reveals higher activation at the coronal holes for fast wind prediction, and at the active regions for slow wind prediction, with the higher activation at the coronal holes being 3 to 4 days prior to prediction for the fast wind. These trends bear an uncanny similarity to the influence of regions potentially being the sources of fast and slow wind, as reported in literature. This suggests that the our model was able to learn some of the salient associations between coronal and solar wind structure without built-in physics knowledge. Such an approach may help us discover hitherto unknown relationships in heliophysics data sets.