Predicting the geoeffectiveness of CMEs using machine learning

Coronal mass ejections (CMEs) are the most geoeffective space weather phenomena, being associated with large geomagnetic storms, and having the potential to cause disturbances to telecommunications, satellite network disruptions, and power grid damage and failures. Thus, considering these storms' potential effects on human activities, accurate forecasts of the geoeffectiveness of CMEs are paramount. This work focuses on experimenting with different machine-learning methods trained on white-light coronagraph data sets of close-to-Sun CMEs, to estimate whether such a newly erupting ejection has the potential to induce geomagnetic activity. We developed binary classification models using logistic regression, k-nearest neighbors, support vector machines, feed-forward artificial neural networks, and ensemble models. At this time, we limited our forecast to exclusively use solar onset parameters, to ensure extended warning times. We discuss the main challenges of this task, namely, the extreme imbalance between the number of geoeffective and ineffective events in our data set, along with their numerous similarities and the limited number of available variables. We show that even in such conditions adequate hit rates can be achieved with these models.