TY - JOUR
TI - Assessing the Predictability of Solar Energetic Particles with the Use
of Machine Learning Techniques
AU - Lavasa, E.
AU - Giannopoulos, G.
AU - Papaioannou, A.
AU - Anastasiadis, A.
AU - and Daglis, I. A.
AU - Aran, A.
AU - Pacheco, D.
AU - Sanahuja, B.
JO - SOLAR PHYSICS
PY - 2021
VL - 296
TODO - 7
SP - null
PB - Springer-Verlag
SN - 0038-0938
TODO - 10.1007/s11207-021-01837-x
TODO - Solar energetic particles; Nowcasting; Machine learning methods;
Forecasting
TODO - A consistent approach for the inherently imbalanced problem of solar
energetic particle (SEP) events binary prediction is being presented.
This is based on solar flare and coronal mass ejection (CME) data and
combinations of both thereof. We exploit several machine learning (ML)
and conventional statistics techniques to predict SEPs. The methods used
are logistic regression (LR), support vector machines (SVM), neural
networks (NN) in the fully connected multi-layer perceptron (MLP)
implementation, random forests (RF), decision trees (DTs), extremely
randomized trees (XT) and extreme gradient boosting (XGB). We provide an
assessment of the methods employed and conclude that RF could be the
prediction technique of choice for an optimal sample comprised by both
flares and CMEs. The best-performing method gives a Probability of
Detection (POD) of 0.76(+/- 0.06), False Alarm Rate (FAR) of 0.34(+/-
0.10), true skill statistic (TSS) 0.75(+/- 0.05), and Heidke skill score
(HSS) 0.69(+/- 0.04). We further show that the most important features
for the identification of SEPs, in our sample, are the CME speed, width
and flare soft X-ray (SXR) fluence.
ER -