Predicting the Geoeffectiveness of CMEs Using Machine Learning

TL;DR

This paper explores machine learning techniques to predict whether coronal mass ejections (CMEs) will cause geomagnetic storms, using solar data and addressing challenges like data imbalance to improve space weather forecasting.

Contribution

It introduces multiple machine learning models trained on CME data to forecast geoeffectiveness using only solar onset parameters, highlighting their effectiveness despite data challenges.

Findings

Adequate hit rates achieved with ML models

Models handle class imbalance effectively

Forecasts rely solely on solar onset parameters

Abstract

Coronal mass ejections (CMEs) are the most geoeffective space weather phenomena, being associated with large geomagnetic storms, having the potential to cause disturbances to telecommunication, satellite network disruptions, power grid damages 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 datasets 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, as well as 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 dataset, 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.