Search for: All records

Abstract The prediction of solar energetic particle (SEP) events garners increasing interest as space missions extend beyond Earth’s protective magnetosphere. These events, which are, in most cases, products of magnetic-reconnection-driven processes during solar flares or fast coronal-mass-ejection-driven shock waves, pose significant radiation hazards to aviation, space-based electronics, and particularly space exploration. In this work, we utilize the recently developed data set that combines the Solar Dynamics Observatory/Space-weather Helioseismic and Magnetic Imager Active Region Patches and the Solar and Heliospheric Observatory/Space-weather Michelson Doppler Imager Active Region Patches. We employ a suite of machine learning strategies, including support vector machines (SVMs) and regression models, to evaluate the predictive potential of this new data product for a forecast of post-solar flare SEP events. Our study indicates that despite the augmented volume of data, the prediction accuracy reaches 0.7 ± 0.1 (experimental setting), which aligns with but does not exceed these published benchmarks. A linear SVM model with training and testing configurations that mimic an operational setting (positive–negative imbalance) reveals a slight increase (+0.04 ± 0.05) in the accuracy of a 14 hr SEP forecast compared to previous studies. This outcome emphasizes the imperative for more sophisticated, physics-informed models to better understand the underlying processes leading to SEP events. 

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, we found that it may be sufficient to only utilize proton and soft X-ray (SXR) parameters for SPE forecasts. Here, we report a catalog recording ≥10 MeV ≥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 oneandtwo SCs, evaluating how transferable a model might be across different time periods. XGBoost proved to be more accurate than SVMs for almost every test considered, while also outperforming operational SWPC NOAA predictions and a persistence forecast. Interestingly, training done with SC 24 produces weaker true skill statistic and Heidke skill scores₂, even when paired with SC 22 or SC 23, indicating transferability issues. This work contributes toward 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. 

Abstract The flux of energetic particles originating from the Sun fluctuates during the solar cycles. It depends on the number and properties of active regions (ARs) present in a single day and associated solar activities, such as solar flares and coronal mass ejections. Observational records of the Space Weather Prediction Center NOAA enable the creation of time-indexed databases containing information about ARs and particle flux enhancements, most widely known as solar energetic particle (SEP) events. In this work, we utilize the data available for solar cycles 21–24 and the initial phase of cycle 25 to perform a statistical analysis of the correlation between SEPs and properties of ARs inferred from the McIntosh and Hale classifications. We find that the complexity of the magnetic field, longitudinal location, area, and penumbra type of the largest sunspot of ARs are most correlated with the production of SEPs. It is found that most SEPs (≈60%, or 108 out of 181 considered events) were generated from an AR classified with the “k” McIntosh subclass as the second component, and these ARs are more likely to produce SEPs if they fall in a Hale class containing aδcomponent. The resulting database containing information about SEP events and ARs is publicly available and can be used for the development of machine learning models to predict the occurrence of SEPs.