We propose a new method for predicting the solar cycle in terms of the sunspot number (SN) based on multivariate machine learning algorithms, various proxies of solar activity, and the spectral analysis of all considered time series via the fast Fourier transform (through the latter we identify periodicities with which to lag these series and thus generate new attributes –predictors– for incorporation in the prediction model). This combination of three different techniques in a single method is expected to enhance the accuracy and reliability of the solar activity prediction models developed to date. Thus, predictive results for SN are presented for Solar Cycles 25 (the current one) and 26 (using the 13-month smoothed SN, version 2) up until January 2038, yielding maximum values of 134.2 (in June 2024) and 115.4 (in May 2034), respectively, with a root mean squared error (RMSE) of 9.8. These results imply, on the one hand, a maximum of Cycle 25 below the average and, on the other hand, a lower peak than the preceding ones for Cycle 26, suggesting that Solar Cycles 24, 25, and 26 are part of a minimum of the centennial Gleissberg cycle, as occurred with Cycles 12, 13, and 14 in the final years of the 19th century and the early 20th century.
A strong Forbush decrease, i.e., suppression of the flux of galactic cosmic rays recorded on Earth, was observed by the global network of ground-based neutron monitors (NMs) on 24 – 25 March 2024. The decrease was very unusual as characterised by so rapid recovery that a false Ground-level enhancement (GLE) alarm was produced by the corresponding warning systems. Here we present the first comprehensive collection and analysis of the available data for this event. The event was highly anisotropic as exhibited in a 3-h spread of the deep-phase timing for different NMs. The anisotropy was focused nearly at the anti-sunward direction with a narrow cone of 20 – 30. The heliospheric situation leading to this unusual Forbush decrease was quite complex. An analysis of first look records was performed, considering the stations acceptance, taking into account the complex geomagnetic conditions. A leader fraction analysis indicates that the recovery phase of the event was rigidity-independent and had essentially the same spectral shape as the pre-event period. A summary of the solar-terrestrial phenomena is provided to assist in future work on modelling this complex event.
This study aims to improve the understanding of geomagnetic storms by utilizing machine learning models and analyzing several heliophysical variables, such as the interplanetary magnetic field, proton density, solar wind speed, and proton temperature. Rather than relying on traditional correlation-based methods, we employ advanced machine learning techniques to examine the complex relationships between these factors and geomagnetic storms. Our analysis covers a large dataset spanning six solar cycles, including the current 25th cycle, to provide comprehensive insights into the dynamics of these storms.
Our study highlights the significance of the interplanetary magnetic field as a key predictor of geomagnetic storms, challenging previous beliefs that primarily focused on sunspot activity. By using high-resolution data, we uncover new patterns and provide a more detailed analysis of the factors influencing geomagnetic storms. We emphasize the importance of considering a range of heliophysical variables, such as proton temperature and flow pressure, which offer new insights into the complex dynamics driving these storm events.
The application of machine learning models, particularly Random Forest and Gradient Boosting, demonstrated superior predictive accuracy compared to traditional methods. Our results reveal that the Dst-index MIN, scalar B, and alpha/proton ratio are among the most influential factors, accounting for a significant portion of the prediction model’s accuracy. These findings underscore the utility of machine learning in identifying critical drivers of geomagnetic activity and enhancing forecast precision.
Additionally, our research underscores the need for comprehensive models that can accurately predict geomagnetic storms by integrating various data sources. This machine learning approach not only improves predictive accuracy but also enhances our understanding of the underlying mechanisms of space weather. The insights gained from this study have important implications for both scientific research and practical applications, such as improving early warning systems for geomagnetic storms and mitigating their potential impacts on Earth.