An official website of the United States government
Solar flares are characterized by sudden bursts of electromagnetic radiation from the Sun’s surface, and are caused by the changes in magnetic field states in active solar regions. Earth and its surrounding space environment can suffer from various negative impacts caused by solar flares, ranging from electronic communication disruption to radiation exposure-based health risks to astronauts. In this paper, we address the solar flare prediction problem from magnetic field parameter-based multivariate time series (MVTS) data using multiple state-of-the-art machine learning classifiers that include MINImally RandOm Convolutional KErnel Transform (MiniRocket), Support Vector Machine (SVM), Canonical Interval Forest (CIF), Multiple Representations Sequence Learner (Mr-SEQL), and a Long Short-Term Memory (LSTM)-based deep learning model. Our experiment is conducted on the Space Weather Analytics for Solar Flares (SWAN-SF) benchmark data set, which is a partitioned collection of MVTS data of active region magnetic field parameters spanning over nine years of operation of the Solar Dynamics Observatory (SDO). The MVTS instances of the SWAN-SF dataset are labeled by GOES X-ray flux-based flare class labels, and attributed to extreme class imbalance because of the rarity of the major flaring events (e.g., X and M). As a performance validation metric in this class-imbalanced dataset, we used the True Skill Statistic (TSS) score. Finally, we demonstrate the advantages of the MVTS learning algorithm MiniRocket, which outperformed the aforementioned classifiers without the need for essential data preprocessing steps such as normalization, statistical summarization, and class imbalance handling heuristics.
more »
« less
Identifying Flare-indicative Photospheric Magnetic Field Parameters from Multivariate Time-series Data of Solar Active Regions
Abstract Photospheric magnetic field parameters are frequently used to analyze and predict solar events. Observation of these parameters over time, i.e., representing solar events by multivariate time-series (MVTS) data, can determine relationships between magnetic field states in active regions and extreme solar events, e.g., solar flares. We can improve our understanding of these events by selecting the most relevant parameters that give the highest predictive performance. In this study, we propose a two-step incremental feature selection method for MVTS data using a deep-learning model based on long short-term memory (LSTM) networks. First, each MVTS feature (magnetic field parameter) is evaluated individually by a univariate sequence classifier utilizing an LSTM network. Then, the top performing features are combined to produce input for an LSTM-based multivariate sequence classifier. Finally, we tested the discrimination ability of the selected features by training downstream classifiers, e.g., Minimally Random Convolutional Kernel Transform and support vector machine. We performed our experiments using a benchmark data set for flare prediction known as Space Weather Analytics for Solar Flares. We compared our proposed method with three other baseline feature selection methods and demonstrated that our method selects more discriminatory features compared to other methods. Due to the imbalanced nature of the data, primarily caused by the rarity of minority flare classes (e.g., the X and M classes), we used the true skill statistic as the evaluation metric. Finally, we reported the set of photospheric magnetic field parameters that give the highest discrimination performance in predicting flare classes.
more »
« less
- PAR ID:
- 10496084
- Publisher / Repository:
- DOI PREFIX: 10.3847
- Date Published:
- Journal Name:
- The Astrophysical Journal Supplement Series
- Volume:
- 271
- Issue:
- 2
- ISSN:
- 0067-0049
- Format(s):
- Medium: X Size: Article No. 39
- Size(s):
- Article No. 39
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Magnetic reconnection is regarded as the mechanism for the rapid release of magnetic energy stored in active regions during solar flares, and quantitative measurements of the magnetic reconnection rate are essential for understanding solar flares. In the context of the standard two-ribbon flare model, we derive the coronal magnetic reconnection rate of the M6.5 flare on 2015 June 22 in two terms, reconnection flux change rate and reconnection electric field, both of which can be obtained from observations of the flare morphology. Data used include a sequence of chromospheric Hαimages with unprecedented resolution during the flare from the Visual Imaging Spectrometer of the Goode Solar Telescope (GST) at the Big Bear Solar Observatory and a preflare line-of-sight photospheric magnetogram from the GST Near-InfraRed Imaging Spectropolarimeter along with hard X-ray data from the Ramaty High Energy Solar Spectroscopic Imager. The temporal correlation between the magnetic reconnection rate and nonthermal emission is found, and the variation of the reconnection electric field is mainly determined by the ribbon speed, not by the local magnetic field encountered by the ribbon front. Spatially, the hard X-ray source overlaps with the location of the strongest electric field obtained at the same time. The ribbon motion shows abundant fine structures, including a local acceleration at the location of a light bridge with a weaker magnetic field.more » « less
-
Using non-linear force free field (NLFFF) extrapolation, 3D magnetic fields were modeled from the 12-min cadence Solar Dynamics Observatory Helioseismic and Magnetic Imager (HMI) photospheric vector magnetograms, spanning a time period of 1 hour before through 1 hour after the start of 18 X-class and 12 M-class solar flares. Several magnetic field parameters were calculated from the modeled fields directly, as well as from the power spectrum of surface maps generated by summing the fields along the vertical axis, for two different regions: areas with photospheric |Bz|≥ 300 G (active region—AR) and areas above the photosphere with the magnitude of the non-potential field (BNP) greater than three standard deviations above of the AR field and either the unsigned twist number |Tw| ≥ 1 turn or the shear angle Ψ ≥ 80° (non-potential region—NPR). Superposed epoch (SPE) plots of the magnetic field parameters were analyzed to investigate the evolution of the 3D solar field during the solar flare events and discern consistent trends across all solar flare events in the dataset, as well as across subsets of flare events categorized by their magnetic and sunspot classifications. The relationship between different flare properties and the magnetic field parameters was quantitatively described by the Spearman ranking correlation coefficient, rs. The parameters that showed the most consistent and discernable trends among the flare events, particularly for the hour leading up to the eruption, were the total unsigned fluxϕ), free magnetic energy (EFree), total unsigned magnetic twist (τTot), and total unsigned free magnetic twist (ρTot). Strong (|rs| ∈ [0.6, 0.8)) to very strong (|rs| ∈ [0.8, 1.0]) correlations were found between the magnetic field parameters and the following flare properties: peak X-ray flux, duration, rise time, decay time, impulsiveness, and integrated flux; the strongest correlation coefficient calculated for each flare property was 0.62, 0.85, 0.73, 0.82, −0.81, and 0.82, respectively.more » « less
-
Solar flares are significant occurrences in solar physics, impacting space weather and terrestrial technologies. Accurate classification of solar flares is essential for predicting space weather and minimizing potential disruptions to communication, navigation, and power systems. This study addresses the challenge of selecting the most relevant features from multivariate time-series data, specifically focusing on solar flares. We employ methods such as Mutual Information (MI), Minimum Redundancy Maximum Relevance (mRMR), and Euclidean Distance to identify key features for classification. Recognizing the performance variability of different feature selection techniques, we introduce an ensemble approach to compute feature weights. By combining outputs from multiple methods, our ensemble method provides a more comprehensive understanding of the importance of features. Our results show that the ensemble approach significantly improves classification performance, achieving values 0.15 higher in True Skill Statistic (TSS) values compared to individual feature selection methods. Additionally, our method offers valuable insights into the underlying physical processes of solar flares, leading to more effective space weather forecasting and enhanced mitigation strategies for communication, navigation, and power system disruptions.more » « less
-
Context. Machine-learning methods for predicting solar flares typically employ physics-based features that have been carefully cho- sen by experts in order to capture the salient features of the photospheric magnetic fields of the Sun. Aims. Though the sophistication and complexity of these models have grown over time, there has been little evolution in the choice of feature sets, or any systematic study of whether the additional model complexity leads to higher predictive skill. Methods. This study compares the relative prediction performance of four different machine-learning based flare prediction models with increasing degrees of complexity. It evaluates three different feature sets as input to each model: a “traditional” physics-based feature set, a novel “shape-based” feature set derived from topological data analysis (TDA) of the solar magnetic field, and a com- bination of these two sets. A systematic hyperparameter tuning framework is employed in order to assure fair comparisons of the models across different feature sets. Finally, principal component analysis is used to study the effects of dimensionality reduction on these feature sets. Results. It is shown that simpler models with fewer free parameters perform better than the more complicated models on the canonical 24-h flare forecasting problem. In other words, more complex machine-learning architectures do not necessarily guarantee better prediction performance. In addition, it is found that shape-based feature sets contain just as much useful information as physics-based feature sets for the purpose of flare prediction, and that the dimension of these feature sets – particularly the shape-based one – can be greatly reduced without impacting predictive accuracy.more » « less
