A Hybrid Supervised/Unsupervised Machine Learning Approach to Solar Flare Prediction

Benvenuto, Federico; Piana, Michele; Campi, Cristina; Massone, Anna Maria

doi:10.3847/1538-4357/aaa23c

Cited by 70 publications

(61 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning is a subfield of artificial intelligence, which grants computers abilities to learn from the past data and make predictions on unseen future data (Alpaydin 2009). Commonly used machine learning methods for flare prediction include decision trees (Yu et al 2009(Yu et al , 2010, random forests (Barnes et al 2016;Liu et al 2017;Florios et al 2018;Breiman 2001), k-nearest neighbors Huang et al 2013;Winter & Balasubramaniam 2015;Nishizuka et al 2017), support vector machines (Qahwaji & Colak 2007;Yuan et al 2010;Bobra & Couvidat 2015;Boucheron et al 2015;Muranushi et al 2015;Florios et al 2018), ordinal logistic regression (Song et al 2009), the least absolute shrinkage and selection operator (LASSO) (Benvenuto et al 2018;Jonas et al 2018), extremely randomized trees (Nishizuka et al 2017), and neural networks (Qahwaji & Colak 2007;Wang et al 2008;Colak & Qahwaji 2009;Higgins et al 2011;Ahmed et al 2013). Recently, Nishizuka et al (2018) adopted a deep neural network, named Deep Flare Net, for flare prediction.…”

Section: Introductionmentioning

confidence: 99%

Predicting Solar Flares Using a Long Short-term Memory Network

Líu

Liu

Wang

et al. 2019

ApJ

126

View full text Add to dashboard Cite

We present a long short-term memory (LSTM) network for predicting whether an active region (AR) would produce a Υ-class flare within the next 24 hours. We consider three Υ classes, namely ≥M5.0 class, ≥M class, and ≥C class, and build three LSTM models separately, each corresponding to a Υ class. Each LSTM model is used to make predictions of its corresponding Υ-class flares. The essence of our approach is to model data samples in an AR as time series and use LSTMs to capture temporal information of the data samples. Each data sample has 40 features including 25 magnetic parameters obtained from the Space-weather HMI Active Region Patches (SHARP) and related data products as well as 15 flare history parameters. We survey the flare events that occurred from 2010 May to 2018 May, using the GOES X-ray flare catalogs provided by the National Centers for Environmental Information (NCEI), and select flares with identified ARs in the NCEI flare catalogs. These flare events are used to build the labels (positive vs. negative) of the data samples. Experimental results show that (i) using only 14-22 most important features including both flare history and magnetic parameters can achieve better performance than using all the 40 features together; (ii) our LSTM network outperforms related machine learning methods in predicting the labels of the data samples. To our knowledge, this is the first time that LSTMs have been used for solar flare prediction.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting Solar Flares Using a Long Short-term Memory Network

Líu

Liu

Wang

et al. 2019

ApJ

126

View full text Add to dashboard Cite

show abstract

“…Nishizuka et al (2017) and Jonas et al (2018) include Solar Dynamics Observatory (SDO) Atmospheric Imaging Assembly and EUV image characteristics in addition to magnetogram data in a fully connected neural network architecture. Benvenuto et al (2018) use Fuzzy C-Means-an unsupervised machine learning method-in combination with some of the mentioned supervised methods for solar flare prediction. Approaches such as Guerra et al (2018) and Kontogiannis et al (2018), while not machine-learning approaches themselves, provide statistical tools for evaluating the engineered features in terms of their potential advantage in machine learning models.…”

Section: Introductionmentioning

confidence: 99%

Leveraging the mathematics of shape for solar magnetic eruption prediction

Deshmukh

Berger²,

Bradley

et al. 2020

J. Space Weather Space Clim.

View full text Add to dashboard Cite

Current operational forecasts of solar eruptions are made by human experts using a combination of qualitative shape-based classification systems and historical data about flaring frequencies. In the past decade, there has been a great deal of interest in crafting machine-learning (ML) flareprediction methods to extract underlying patterns from a training set-e.g., a set of solar magnetogram images, each characterized by features derived from the magnetic field and labeled as to whether it was an eruption precursor. These patterns, captured by various methods (neural nets, support vector machines, etc.), can then be used to classify new images. A major challenge with any ML method is the featurization of the data: pre-processing the raw images to extract higherlevel properties, such as characteristics of the magnetic field, that can streamline the training and use of these methods. It is key to choose features that are informative, from the standpoint of the task at hand. To date, the majority of ML-based solar eruption methods have used physics-based magnetic and electric field features such as the total unsigned magnetic flux, the gradients of the fields, the vertical current density, etc. In this paper, we extend the relevant feature set to include characteristics of the magnetic field that are based purely on the geometry and topology of 2D magnetogram images and show that this improves the prediction accuracy of a neural-net based flare-prediction method.

show abstract

“…With quickly increasing interest in and success of pilot studies in the solar-physics community, machinelearning technology has opened a new window into the space weather forecast. Various models have been investigated and developed (e.g., Ahmed et al 2013;Bobra & Couvidat 2015;Liu et al 2017aLiu et al , 2019Nishizuka et al 2017Nishizuka et al , 2018Benvenuto et al 2018;Florios et al 2018;Huang et al 2018;Jonas et al 2018).…”

Section: Introductionmentioning

confidence: 99%

Parameters Derived from the SDO/HMI Vector Magnetic Field Data: Potential to Improve Machine-learning-based Solar Flare Prediction Models

Wang

Liu

et al. 2019

ApJ

View full text Add to dashboard Cite

Citation: J Wang et al. "Parameters derived from the SDO/HMI vector magnetic field data: potential to improve machine-learning-based solar flare prediction models. AbstractIt is well established that solar flares and coronal mass ejections (CMEs) are powered by the free magnetic energy stored in volumetric electric currents in the corona, predominantly in active regions (ARs). Much effort has been made to search for eruption-related signatures from magnetic field observed mostly in the photosphere; and the signatures are further employed for predicting flares and CMEs. The parameters in the Space-weather HMI Active Region Patches (SHARP) data from the Solar Dynamics Observatory/HMI observation of vector magnetic field are designed and generated for this purpose. In this paper, we report research done on modification of these SHARP parameters with an attempt to improve flare prediction. The newly modified parameters are weighed heavily by magnetic polarity inversion lines (PIL) with high magnetic gradient, as suggested by Schrijver, by multiplying the parameters with a PIL mask. We demonstrate that the number of the parameters that can well discriminate erupted and nonerupted ARs increases significantly by a factor of two, in comparison with the original parameters. This improvement suggests that the high-gradient PILs are tightly related with solar eruption that agrees with previous studies. This also provides new data that possess potential to improve the machine-learningbased solar flare prediction models.

show abstract

A Hybrid Supervised/Unsupervised Machine Learning Approach to Solar Flare Prediction

Abstract: We introduce a hybrid approach to solar flare prediction, whereby a supervised regularization method is used to realize feature importance and an unsupervised clustering method is used to realize the binary flare/no-flare decision. The approach is validated against NOAA SWPC data.

Cited by 70 publications

References 27 publications

Predicting Solar Flares Using a Long Short-term Memory Network

Predicting Solar Flares Using a Long Short-term Memory Network

Leveraging the mathematics of shape for solar magnetic eruption prediction

Parameters Derived from the SDO/HMI Vector Magnetic Field Data: Potential to Improve Machine-learning-based Solar Flare Prediction Models

Contact Info

Product

Resources

About