Prior Flaring as a Complement to Free Magnetic Energy for Forecasting Solar Eruptions

Falconer, D. A.; Moore, Ronald L.; Barghouty, A. F.; Khazanov, Igor

doi:10.1088/0004-637x/757/1/32

Cited by 39 publications

(40 citation statements)

References 19 publications

(30 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We find that prior flaring activity has significant predictive capacity in and of itself, a result corroborated by many others (e.g. Falconer et al 2012). In all cases, we find that values of the decay parameter τ equal to 12 and 24 hours perform the best.…”

Section: Physical Featuressupporting

confidence: 89%

“…Since these features have wildly differing dynamic ranges and are rejected for some time periods, we perform median imputation on all missing data before normalizing each feature to a zero-mean unit variance. Knowledge of whether an active region flared in its past can greatly improve the ability to forecast its future (Falconer et al 2012, Wheatland 2004. As such, we derived a number of features that capture the flaring history of an active region.…”

Section: Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Flare Prediction Using Photospheric and Coronal Image Data

et al. 2018

View full text Add to dashboard Cite

The precise physical process that triggers solar flares is not currently understood. Here we attempt to capture the signature of this mechanism in solar image data of various wavelengths and use these signatures to predict flaring activity. We do this by developing an algorithm that [1] automatically generates features in 5.5 TB of image data taken by the Solar Dynamics Observatory of the solar photosphere, chromosphere, transition region, and corona during the time period between May 2010 and May 2014, [2] combines these features with other features based on flaring history and a physical understanding of putative flaring processes, and [3] classifies these features to predict whether a solar active region will flare within a time period of T hours, where T = 2 and 24. This type of machinelearning algorithm is conceptually similar to a single-layer Convolutional Neural Network (CNN) with pre-specified filters that is trained using a linear classifier. Such an approach may be useful since, at the present time, there are no physical models of flares available for real-time prediction. We find that when optimizing for the True Skill Score (TSS), photospheric vector magnetic field data combined with flaring history yields the best performance, and when optimizing for the area under the precision-recall curve, all the data are helpful. Our model performance yields a TSS of 0.84 ± 0.03 and 0.81 ± 0.03 in the T = 2 and 24 hour cases, respectively, and a value of 0.13 ± 0.07 and 0.43 ± 0.08 for the area under the precision-recall curve in the T = 2 and 24 hour cases, respectively. These relatively high scores are similar to, but not greater than, other attempts to predict solar flares. Given the similar values of algorithm performance across various types of models reported in the literature, we conclude that we can expect a certain baseline predictive capacity using these data. This is the first attempt to predict solar flares using photospheric vector magnetic field data as well as multiple wavelengths of image data from the chromosphere, transition region, and corona.

show abstract

Section: Physical Featuressupporting

confidence: 89%

Section: Algorithmmentioning

confidence: 99%

Flare Prediction Using Photospheric and Coronal Image Data

et al. 2018

View full text Add to dashboard Cite

show abstract

“…A magnetic polarity inversion line (MPIL) in the photosphere of an AR separates distinct patches of positive-and negative-polarity magnetic flux. Several studies have been carried out to investigate the relationship between flare occurrence and MPIL characteristics (Schrijver, 2007;Falconer et al, 2012). We determine a specific subset of a MPIL, that has been also identified as MPIL*, with i) a strong gradient in the vertical component of the field across the MPIL and ii) a strong horizontal component of the field around the MPIL.…”

Section: Magnetic Polarity Inversion Line (Tlmpil)mentioning

confidence: 99%

Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning

et al. 2018

View full text Add to dashboard Cite

We propose a forecasting approach for solar flares based on data from Solar Cycle 24, taken by the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory (SDO) mission. In particular, we use the Spaceweather HMI Active Region Patches (SHARP) product that facilitates cut-out magnetograms of solar active regions (AR) in the Sun in near-realtime (NRT), K. Florios cflorios@aueb.gr I. Kontogiannis K. Florios et al.taken over a five-year interval (2012 -2016). Our approach utilizes a set of thirteen predictors, which are not included in the SHARP metadata, extracted from line-of-sight and vector photospheric magnetograms. We exploit several Machine Learning (ML) and Conventional Statistics techniques to predict flares of peak magnitude >M1 and >C1, within a 24 h forecast window. The ML methods used are multi-layer perceptrons (MLP), support vector machines (SVM) and random forests (RF). We conclude that random forests could be the prediction technique of choice for our sample, with the second best method being multi-layer perceptrons, subject to an entropy objective function. A Monte Carlo simulation showed that the best performing method gives accuracy ACC=0.93(0.00), true skill statistic TSS=0.74(0.02) and Heidke skill score HSS=0.49(0.01) for >M1 flare prediction with probability threshold 15% and ACC=0.84(0.00), TSS=0.60(0.01) and HSS=0.59(0.01) for >C1 flare prediction with probability threshold 35%.

show abstract

“…A novel technique offering a 24 h warning of large flares and SEPs based on solar magnetic field measurements was described by Falconer et al . [, ]. It is based on vector magnetograph measurements of active regions, so it is most reliable when they are within 30° of the Sun's central meridian [ Falconer et al ., ].…”

Section: Existing Sep Forecasting Techniquesmentioning

confidence: 99%

Solar energetic particle warnings from a coronagraph

Cyr

Posner²,

Burkepile³

2017

Space Weather

View full text Add to dashboard Cite

We report here the concept of using near‐real time observations from a coronagraph to provide early warning of a fast coronal mass ejection (CME) and the possible onset of a solar energetic particle (SEP) event. The 1 January 2016, fast CME, and its associated SEP event are cited as an example. The CME was detected by the ground‐based K‐Cor coronagraph at Mauna Loa Solar Observatory and by the SOHO Large Angle and Spectrometric Coronagraph. The near‐real‐time availability of the high‐cadence K‐Cor observations in the low corona leads to an obvious question: “Why has no one attempted to use a coronagraph as an early warning device for SEP events?” The answer is that the low image cadence and the long latency of existing spaceborne coronagraphs make them valid for archival studies but typically unsuitable for near‐real‐time forecasting. The January 2016 event provided favorable CME viewing geometry and demonstrated that the primary component of a prototype ground‐based system for SEP warnings is available several hours on most days. We discuss how a conceptual CME‐based warning system relates to other techniques, including an estimate of the relative SEP warning times, and how such a system might be realized.

show abstract

Prior Flaring as a Complement to Free Magnetic Energy for Forecasting Solar Eruptions

Cited by 39 publications

References 19 publications

Flare Prediction Using Photospheric and Coronal Image Data

Flare Prediction Using Photospheric and Coronal Image Data

Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning

Solar energetic particle warnings from a coronagraph

Contact Info

Product

Resources

About