skip to main content

Title: Predicting Solar Energetic Particles Using SDO/HMI Vector Magnetic Data Products and a Bidirectional LSTM Network
Abstract

Solar energetic particles (SEPs) are an essential source of space radiation, and are hazardous for humans in space, spacecraft, and technology in general. In this paper, we propose a deep-learning method, specifically a bidirectional long short-term memory (biLSTM) network, to predict if an active region (AR) would produce an SEP event given that (i) the AR will produce an M- or X-class flare and a coronal mass ejection (CME) associated with the flare, or (ii) the AR will produce an M- or X-class flare regardless of whether or not the flare is associated with a CME. The data samples used in this study are collected from the Geostationary Operational Environmental Satellite's X-ray flare catalogs provided by the National Centers for Environmental Information. We select M- and X-class flares with identified ARs in the catalogs for the period between 2010 and 2021, and find the associations of flares, CMEs, and SEPs in the Space Weather Database of Notifications, Knowledge, Information during the same period. Each data sample contains physical parameters collected from the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory. Experimental results based on different performance metrics demonstrate that the proposed biLSTM network is better than related more » machine-learning algorithms for the two SEP prediction tasks studied here. We also discuss extensions of our approach for probabilistic forecasting and calibration with empirical evaluation.

« less
Authors:
; ; ; ; ;
Award ID(s):
1927578
Publication Date:
NSF-PAR ID:
10366736
Journal Name:
The Astrophysical Journal Supplement Series
Volume:
260
Issue:
1
Page Range or eLocation-ID:
Article No. 16
ISSN:
0067-0049
Publisher:
DOI PREFIX: 10.3847
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Solar flares, especially the M- and X-class flares, are often associated with coronal mass ejections. They are the most important sources of space weather effects, which can severely impact the near-Earth environment. Thus it is essential to forecast flares (especially the M- and X-class ones) to mitigate their destructive and hazardous consequences. Here, we introduce several statistical and machine-learning approaches to the prediction of an active region’s (AR) flare index (FI) that quantifies the flare productivity of an AR by taking into account the number of different class flares within a certain time interval. Specifically, our sample includes 563 ARs that appeared on the solar disk from 2010 May to 2017 December. The 25 magnetic parameters, provided by the Space-weather HMI Active Region Patches (SHARP) from the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory, characterize coronal magnetic energy stored in ARs by proxy and are used as the predictors. We investigate the relationship between these SHARP parameters and the FI of ARs with a machine-learning algorithm (spline regression) and the resampling method (Synthetic Minority Oversampling Technique for Regression with Gaussian Noise). Based on the established relationship, we are able to predict the value of FIs formore »a given AR within the next 1 day period. Compared with other four popular machine-learning algorithms, our methods improve the accuracy of FI prediction, especially for a large FI. In addition, we sort the importance of SHARP parameters by the Borda count method calculated from the ranks that are rendered by nine different machine-learning methods.

    « less
  2. Abstract Solar flare prediction plays an important role in understanding and forecasting space weather. The main goal of the Helioseismic and Magnetic Imager (HMI), one of the instruments on NASA’s Solar Dynamics Observatory, is to study the origin of solar variability and characterize the Sun’s magnetic activity. HMI provides continuous full-disk observations of the solar vector magnetic field with high cadence data that lead to reliable predictive capability; yet, solar flare prediction effort utilizing these data is still limited. In this paper, we present a machine-learning-as-a-service (MLaaS) framework, called DeepSun, for predicting solar flares on the web based on HMI’s data products. Specifically, we construct training data by utilizing the physical parameters provided by the Space-weather HMI Active Region Patch (SHARP) and categorize solar flares into four classes, namely B, C, M and X, according to the X-ray flare catalogs available at the National Centers for Environmental Information (NCEI). Thus, the solar flare prediction problem at hand is essentially a multi-class (i.e., four-class) classification problem. The DeepSun system employs several machine learning algorithms to tackle this multi-class prediction problem and provides an application programming interface (API) for remote programming users. To our knowledge, DeepSun is the first MLaaS tool capablemore »of predicting solar flares through the internet.« less
  3. Abstract

    Post-flare arcades are well-known components of solar flare evolution, which have been observed for several decades. Coronal rain, cascades of catastrophically cooled plasma, outlines the loops and provides eye-catching evidence of the recent flare. These events are acknowledged to be common, but the scientific literature does not include any statistical overview documenting just how common the phenomenon actually is. This study reviews Solar Dynamics Observatory Atmospheric Imaging Assembly (SDO AIA) observations of 241 flares collected from the Space Weather Prediction Center database between 2011 and 2018. The flares cover the entire strength range of the C, M, and X GOES classes, and are distributed evenly across the SDO-observed majority of Solar Cycle 24. We find that post-flare arcade rain occurs for nearly all X- and most M-class flares, but that it tapers off rapidly within C-class flares. There appears to be a cut-off point around C5, below which the occurrence of post-flare arcade rain drops significantly. There is also a general positive correlation between GOES class and the average duration of post-flare rain events. Post-flare arcade rain events in X- and M-class flares appear to track with the sunspot number, providing a potential new tool for estimating, if notmore »predicting, solar cycle strength. Furthermore, arcades are observed to persist for up to several days after the originating flare, transitioning from hosting post-flare rain to typical quiescent active region condensations. These results open up further avenues for future research, including new methods to estimate energy deposition and to gain greater insight into steady active region heating.

    « less
  4. Abstract

    Flare-associated quasiperiodic pulsations (QPPs) in radio and X-ray wavelengths, particularly those related to nonthermal electrons, contain important information about the energy release and transport processes during flares. However, the paucity of spatially resolved observations of such QPPs with a fast time cadence has been an obstacle for us to further understand their physical nature. Here, we report observations of such a QPP event that occurred during the impulsive phase of a C1.8-class eruptive solar flare using radio imaging spectroscopy data from the Karl G. Jansky Very Large Array (VLA) and complementary X-ray imaging and spectroscopy data. The radio QPPs, observed by the VLA in the 1–2 GHz with a subsecond cadence, are shown as three spatially distinct sources with different physical characteristics. Two radio sources are located near the conjugate footpoints of the erupting magnetic flux rope with opposite senses of polarization. One of the sources displays a QPP behavior with a ∼5 s period. The third radio source, located at the top of the postflare arcade, coincides with the location of an X-ray source and shares a similar period of ∼25–45 s. We show that the two oppositely polarized radio sources are likely due to coherent electron cyclotronmore »maser emission. On the other hand, the looptop QPP source, observed in both radio and X-rays, is consistent with incoherent gyrosynchrotron and bremsstrahlung emission, respectively. We conclude that the concurrent, but spatially distinct QPP sources must involve multiple mechanisms which operate in different magnetic loop systems and at different periods.

    « less
  5. Abstract We present a case study of solar flare forecasting by means of metadata feature time series, by treating it as a prominent class-imbalance and temporally coherent problem. Taking full advantage of pre-flare time series in solar active regions is made possible via the Space Weather Analytics for Solar Flares (SWAN-SF) benchmark data set, a partitioned collection of multivariate time series of active region properties comprising 4075 regions and spanning over 9 yr of the Solar Dynamics Observatory period of operations. We showcase the general concept of temporal coherence triggered by the demand of continuity in time series forecasting and show that lack of proper understanding of this effect may spuriously enhance models’ performance. We further address another well-known challenge in rare-event prediction, namely, the class-imbalance issue. The SWAN-SF is an appropriate data set for this, with a 60:1 imbalance ratio for GOES M- and X-class flares and an 800:1 imbalance ratio for X-class flares against flare-quiet instances. We revisit the main remedies for these challenges and present several experiments to illustrate the exact impact that each of these remedies may have on performance. Moreover, we acknowledge that some basic data manipulation tasks such as data normalization and cross validationmore »may also impact the performance; we discuss these problems as well. In this framework we also review the primary advantages and disadvantages of using true skill statistic and Heidke skill score, two widely used performance verification metrics for the flare-forecasting task. In conclusion, we show and advocate for the benefits of time series versus point-in-time forecasting, provided that the above challenges are measurably and quantitatively addressed.« less