Predicting Solar Proton Events of Solar Cycles 22-24 using GOES Proton & soft X-Ray flux features

TL;DR

This study uses machine learning models, specifically XGBoost and SVM, on GOES satellite data to predict Solar Proton Events across solar cycles 22-24, highlighting the transferability challenges of models trained on different cycles.

Contribution

It introduces a comprehensive catalog of SPEs and flux data across multiple solar cycles and evaluates the cross-cycle transferability of ML-based SPE prediction models.

Findings

XGBoost outperforms SVM and operational forecasts in accuracy.

Transferability of models trained on one cycle to others is limited.

Long-term data validation is crucial for robust SEP forecasting.

Abstract

Solar Energetic Particle (SEP) events and their major subclass, Solar Proton Events (SPEs), can have unfavorable consequences on numerous aspects of life and technology, making them one of the most harmful effects of solar activity. Garnering knowledge preceding such events by studying operational data flows is essential for their forecasting. Considering only Solar Cycle (SC) 24 in our previous study, Sadykov et al. 2021, we found that it may be sufficient to utilize only proton and soft X-ray (SXR) parameters for SPE forecasts. Here, we report a catalog recording $\geq$ 10 MeV $\geq$ 10 particle flux unit SPEs with their properties, spanning SCs 22-24, using NOAA's Geostationary Operational Environmental Satellite flux data. We report an additional catalog of daily proton and SXR flux statistics for this period, employing it to test the application of machine learning (ML) on the prediction of SPEs using a Support Vector Machine (SVM) and eXtreme Gradient Boosting (XGBoost). We explore the effects of training models with data from one and two SCs, evaluating how transferable a model can be across different time periods. XGBoost proved to be more accurate than SVMs for almost every test considered, while outperforming operational SWPC NOAA predictions and a persistence forecast. Interestingly, training done with SC 24 produces weaker TSS and HSS2, even when paired with SC 22 or SC 23, indicating transferability issues. This work contributes towards validating forecasts using long-spanning data -- an understudied area in SEP research that should be considered to verify the cross-cycle robustness of ML-driven forecasts.