Search for: All records

Abstract We present FlareDB, a database that provides comprehensive magnetic field information, ultraviolet/extreme ultraviolet (UV/EUV) emissions, and white light continuum images for solar active regions (ARs) associated with 151 significant flares from May 2010 to May 2025. The data, sourced from the Solar Dynamics Observatory (SDO) via the Joint Science Operations Center (JSOC), were processed with SunPy and stored in standardized JSOC FITS format. FlareDB includes all M5.0 and larger flares within 50° of the solar disk center. Key features include (1) Atmospheric Imaging Assembly (AIA) AR patches in Helioprojective Cartesian(HPC) and Lambert Cylindrical Equal-Area (CEA) projections, aligned with corresponding HMI magnetogram patches; (2) quick-look movies with uniform value ranges that ensure consistent visualization, maintain data uniformity, and enhance readiness for machine learning studies; (3) a supplementary web interface that allows the entire dataset of a flare to be downloaded for large flare analysis. One of FlareDB’s primary objectives is to support scientists in predicting and understanding the onset of solar eruptions, including flares and coronal mass ejections. The data set is machine-learning ready for this purpose. 

Abstract Solar eruptions, including flares and coronal mass ejections (CMEs), have a significant impact on Earth. Some flares are associated with CMEs, and some flares are not. The association between flares and CMEs is not always obvious. In this study, we propose a new deep learning method, specifically a hybrid neural network (HNN) that combines a vision transformer with long short-term memory, to predict associations between flares and CMEs. HNN finds spatio-temporal patterns in the time series of line-of-sight magnetograms of solar active regions collected by the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory and uses the patterns to predict whether a flare projected to occur within the next 24 hr will be eruptive (i.e., CME-associated) or confined (i.e., not CME-associated). Our experimental results demonstrate the good performance of the HNN method. Furthermore, the results show that magnetic flux cancellation in polarity inversion line regions may well play a role in triggering flare-associated CMEs, a finding consistent with the literature. 

Abstract We present a transformer model, named DeepHalo, to predict the occurrence of halo coronal mass ejections (CMEs). Our model takes as input an active region (AR) and a profile, where the profile contains a time series of data samples in the AR that are collected 24 hr before the beginning of a day, and predicts whether the AR would produce a halo CME during that day. Each data sample contains physical parameters, or features, derived from photospheric vector magnetic field data taken by the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory. We survey and match CME events in the Space Weather Database Of Notification, Knowledge, Information and the Large Angle and Spectrometric Coronagraph CME Catalog, and we compile a list of CMEs, including halo CMEs and nonhalo CMEs, associated with ARs in the period between 2010 November and 2023 August. We use the information gathered above to build the labels (positive vs. negative) of the data samples and profiles at hand, where the labels are needed for machine learning. Experimental results show that DeepHalo with a true skill statistic (TSS) score of 0.907 outperforms a closely related long short-term memory network with a TSS score of 0.821. To our knowledge, this is the first time that the transformer model has been used for halo CME prediction. 

Abstract We present a novel deep generative model, named GenMDI, to improve the temporal resolution of line-of-sight (LOS) magnetograms of solar active regions (ARs) collected by the Michelson Doppler Imager (MDI) on board the Solar and Heliospheric Observatory. Unlike previous studies that focus primarily on spatial super-resolution of MDI magnetograms, our approach can perform temporal super-resolution, which generates and inserts synthetic data between observed MDI magnetograms, thus providing finer temporal structure and enhanced details in the LOS data. The GenMDI model employs a conditional diffusion process, which synthesizes images by considering both preceding and subsequent magnetograms, ensuring that the generated images are not only of high quality but also temporally coherent with the surrounding data. Experimental results show that the GenMDI model performs better than the traditional linear interpolation method, especially in ARs with dynamic evolution in magnetic fields. 

Abstract The application of machine learning to the study of coronal mass ejections (CMEs) and their impacts on Earth has seen significant growth recently. Understanding and forecasting CME geoeffectiveness are crucial for protecting infrastructure in space and ensuring the resilience of technological systems on Earth. Here we present GeoCME, a deep-learning framework designed to predict, deterministically or probabilistically, whether a CME event that arrives at Earth will cause a geomagnetic storm. A geomagnetic storm is defined as a disturbance of the Earth’s magnetosphere during which the minimum Dst index value is less than −50 nT. GeoCME is trained on observations from the instruments including LASCO C2, EIT, and MDI on board the Solar and Heliospheric Observatory (SOHO), focusing on a dataset that includes 136 halo/partial halo CMEs in Solar Cycle 23. Using ensemble and transfer learning techniques, GeoCME is capable of extracting features hidden in the SOHO observations and making predictions based on the learned features. Our experimental results demonstrate the good performance of GeoCME, achieving a Matthew’s correlation coefficient of 0.807 and a true skill statistics score of 0.714 when the tool is used as a deterministic prediction model. When the tool is used as a probabilistic forecasting model, it achieves a Brier score of 0.094 and a Brier skill score of 0.493. These results are promising, showing that the proposed GeoCME can help enhance our understanding of CME-triggered solar-terrestrial interactions. 

Abstract Solar flares are explosions on the Sun. They happen when energy stored in magnetic fields around solar active regions (ARs) is suddenly released. Solar flares and accompanied coronal mass ejections are sources of space weather, which negatively affects a variety of technologies at or near Earth, ranging from blocking high-frequency radio waves used for radio communication to degrading power grid operations. Monitoring and providing early and accurate prediction of solar flares is therefore crucial for preparedness and disaster risk management. In this article, we present a transformer-based framework, named SolarFlareNet, for predicting whether an AR would produce a$$\gamma$$ $\gamma$-class flare within the next 24 to 72 h. We consider three$$\gamma$$ $\gamma$classes, namely the$$\ge$$ $\ge$M5.0 class, the$$\ge$$ $\ge$M class and the$$\ge$$ $\ge$C class, and build three transformers separately, each corresponding to a$$\gamma$$ $\gamma$class. Each transformer is used to make predictions of its corresponding$$\gamma$$ $\gamma$-class flares. The crux of our approach is to model data samples in an AR as time series and to use transformers to capture the temporal dynamics of the data samples. Each data sample consists of magnetic parameters taken from Space-weather HMI Active Region Patches (SHARP) and related data products. We survey flare events that occurred from May 2010 to December 2022 using the Geostationary Operational Environmental Satellite X-ray flare catalogs provided by the National Centers for Environmental Information (NCEI), and build a database of flares with identified ARs in the NCEI flare catalogs. This flare database is used to construct labels of the data samples suitable for machine learning. We further extend the deterministic approach to a calibration-based probabilistic forecasting method. The SolarFlareNet system is fully operational and is capable of making near real-time predictions of solar flares on the Web. 

Abstract We propose a novel deep learning framework, named SYMHnet, which employs a graph neural network and a bidirectional long short‐term memory network to cooperatively learn patterns from solar wind and interplanetary magnetic field parameters for short‐term forecasts of the SYM‐H index based on 1‐ and 5‐min resolution data. SYMHnet takes, as input, the time series of the parameters' values provided by NASA's Space Science Data Coordinated Archive and predicts, as output, the SYM‐H index value at time pointt + whours for a given time pointtwherewis 1 or 2. By incorporating Bayesian inference into the learning framework, SYMHnet can quantify both aleatoric (data) uncertainty and epistemic (model) uncertainty when predicting future SYM‐H indices. Experimental results show that SYMHnet works well at quiet time and storm time, for both 1‐ and 5‐min resolution data. The results also show that SYMHnet generally performs better than related machine learning methods. For example, SYMHnet achieves a forecast skill score (FSS) of 0.343 compared to the FSS of 0.074 of a recent gradient boosting machine (GBM) method when predicting SYM‐H indices (1 hr in advance) in a large storm (SYM‐H = −393 nT) using 5‐min resolution data. When predicting the SYM‐H indices (2 hr in advance) in the large storm, SYMHnet achieves an FSS of 0.553 compared to the FSS of 0.087 of the GBM method. In addition, SYMHnet can provide results for both data and model uncertainty quantification, whereas the related methods cannot. 

Abstract Small-scale interplanetary magnetic flux ropes (SMFRs) are similar to ICMEs in magnetic structure, but are smaller and do not exhibit coronal mass ejection plasma signatures. We present a computationally efficient and GPU-powered version of the single-spacecraft automated SMFR detection algorithm based on the Grad–Shafranov (GS) technique. Our algorithm can process higher resolution data, eliminates selection bias caused by a fixed 〈B〉 threshold, has improved detection criteria demonstrated to have better results on an MHD simulation, and recovers full 2.5D cross sections using GS reconstruction. We used it to detect 512,152 SMFRs from 27 yr (1996–2022) of 3 s cadence Wind measurements. Our novel findings are the following: (1) the SMFR filling factor (∼ 35%) is independent of solar activity, distance to the heliospheric current sheet, and solar wind plasma type, although the minority of SMFRs with diameters greater than ∼0.01 au have a strong solar activity dependence; (2) SMFR diameters follow a log-normal distribution that peaks below the resolved range (≳10⁴km), although the filling factor is dominated by SMFRs between 10⁵and 10⁶km; (3) most SMFRs at 1 au have strong field-aligned flows like those from Parker Solar Probe measurements; (4) the radial density (generally ∼1 detected per 10⁶km) and axial magnetic flux density of SMFRs are higher in faster solar wind types, suggesting that they are more compressed. Implications for the origin of SMFRs and switchbacks are briefly discussed. The new algorithm and SMFR dataset are made freely available. 

Abstract The F10.7 and F30 solar indices are the solar radio fluxes measured at wavelengths of 10.7 and 30 cm, respectively, which are key indicators of solar activity. F10.7 is valuable for explaining the impact of solar ultraviolet (UV) radiation on the upper atmosphere of Earth, while F30 is more sensitive and could improve the reaction of thermospheric density to solar stimulation. In this study, we present a new deep learning model, named the Solar Index Network, or SINet for short, to predict daily values of the F10.7 and F30 solar indices. The SINet model is designed to make medium‐term predictions of the index values (1–60 days in advance). The observed data used for SINet training were taken from the National Oceanic and Atmospheric Administration as well as Toyokawa and Nobeyama facilities. Our experimental results show that SINet performs better than five closely related statistical and deep learning methods for the prediction of F10.7. Furthermore, to our knowledge, this is the first time deep learning has been used to predict the F30 solar index.