Machine learning as a flaring storm warning machine: Was a warning machine for the September 2017 solar flaring storm possible?

Machine learning is nowadays the methodology of choice for flare forecasting and supervised techniques, in both their traditional and deep versions, are becoming the most frequently used ones for prediction in this area of space weather. Yet, machine learning has not been able so far to realize an operating warning system for flaring storms and the scientific literature of the last decade suggests that its performances in the prediction of intense solar flares are not optimal. The main difficulties related to forecasting solar flaring storms are probably two. First, most methods are conceived to provide probabilistic predictions and not to send binary yes/no indications on the consecutive occurrence of flares along an extended time range. Second, flaring storms are typically characterized by the explosion of high energy events, which are seldom recorded in the databases of space missions; as a consequence, supervised methods are trained on very imbalanced historical sets, which makes them particularly ineffective for the forecasting of intense flares. Yet, in this study we show that supervised machine learning could be utilized in a way to send timely warnings about the most violent and most unexpected flaring event of the last decade, and even to predict with some accuracy the energy budget daily released by magnetic reconnection during the whole time course of the storm. Further, we show that the combination of sparsity-enhancing machine learning and feature ranking could allow the identification of the prominent role that energy played as an Active Region property in the forecasting process.

[1]  Haimin Wang,et al.  Active-Region Monitoring and Flare Forecasting – I. Data Processing and First Results , 2002 .

[2]  Rongzhi Li,et al.  Application of support vector machine combined with K-nearest neighbors in solar flare and solar proton events forecasting , 2008 .

[3]  Y. Moon,et al.  Application of the Deep Convolutional Neural Network to the Forecast of Solar Flare Occurrence Using Full-disk Solar Magnetograms , 2018, The Astrophysical Journal.

[4]  D. Jackson,et al.  Flare forecasting at the Met Office Space Weather Operations Centre , 2017, 1703.06754.

[5]  Manolis K. Georgoulis,et al.  Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning , 2018, 1801.05744.

[6]  Amani Al-Ghraibah,et al.  A Study of Feature Selection of Magnetogram Complexity Features in an Imbalanced Solar Flare Prediction Data-Set , 2015, 2015 IEEE International Conference on Data Mining Workshop (ICDMW).

[7]  Jason Weston,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2002, Machine Learning.

[8]  J. T. Hoeksema,et al.  The Helioseismic and Magnetic Imager (HMI) Vector Magnetic Field Pipeline: SHARPs – Space-Weather HMI Active Region Patches , 2014, 1404.1879.

[9]  J. T. Hoeksema,et al.  The Helioseismic and Magnetic Imager (HMI) Investigation for the Solar Dynamics Observatory (SDO) , 2012 .

[10]  D. Shaun Bloomfield,et al.  Flare forecasting using the evolution of McIntosh sunspot classifications , 2018 .

[11]  D. S. Bloomfield,et al.  A COMPARISON OF FLARE FORECASTING METHODS. I. RESULTS FROM THE “ALL-CLEAR” WORKSHOP , 2016, 1608.06319.

[12]  D. S. Bloomfield,et al.  Active Region Photospheric Magnetic Properties Derived from Line-of-Sight and Radial Fields , 2017, 1712.06902.

[13]  Rafal A. Angryk,et al.  Multivariate time series dataset for space weather data analytics , 2020, Scientific Data.

[14]  Rami Qahwaji,et al.  Solar Flare Prediction Using Advanced Feature Extraction, Machine Learning, and Feature Selection , 2011, Solar Physics.

[15]  D. S. Bloomfield,et al.  Solar magnetic feature detection and tracking for space weather monitoring , 2010, 1006.5898.

[16]  Rongzhi Li,et al.  Support Vector Machine combined with K-Nearest Neighbors for Solar Flare Forecasting , 2007 .

[17]  Jinfu Liu,et al.  Deep Learning Based Solar Flare Forecasting Model. I. Results for Line-of-sight Magnetograms , 2018 .

[18]  D. S. Bloomfield,et al.  TOWARD RELIABLE BENCHMARKING OF SOLAR FLARE FORECASTING METHODS , 2012, 1202.5995.

[19]  Michele Piana,et al.  Feature Ranking of Active Region Source Properties in Solar Flare Forecasting and the Uncompromised Stochasticity of Flare Occurrence , 2019, The Astrophysical Journal.

[20]  Chang Liu,et al.  Predicting Solar Flares Using a Long Short-term Memory Network , 2019, The Astrophysical Journal.

[21]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[22]  Huaning Wang,et al.  Solar flare forecasting model supported with artificial neural network techniques , 2008 .

[23]  Monica G. Bobra,et al.  SOLAR FLARE PREDICTION USING SDO/HMI VECTOR MAGNETIC FIELD DATA WITH A MACHINE-LEARNING ALGORITHM , 2014, 1411.1405.

[24]  A. Kosovichev,et al.  Relationships between Characteristics of the Line-of-sight Magnetic Field and Solar Flare Forecasts , 2017, 1704.03423.

[25]  Predicting Solar Flares Using a Novel Deep Convolutional Neural Network , 2020 .

[26]  K. D. Leka,et al.  Evaluating the Performance of Solar Flare Forecasting Methods , 2008 .

[27]  Michele Piana,et al.  A Hybrid Supervised/Unsupervised Machine Learning Approach to Solar Flare Prediction , 2017, ArXiv.

[28]  J. Leake,et al.  Relative magnetic helicity as a diagnostic of solar eruptivity , 2017, 1703.10562.

[29]  M. Zhao,et al.  Conditions for Coronal Observations at the Lijiang Observatory in 2011 , 2017, Solar Physics.

[30]  Rami Qahwaji,et al.  Automated Solar Activity Prediction: A hybrid computer platform using machine learning and solar imaging for automated prediction of solar flares , 2009 .

[31]  Berkay Aydin,et al.  Rare-Event Time Series Prediction: A Case Study of Solar Flare Forecasting , 2019, 2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA).

[32]  Daren Yu,et al.  Short-Term Solar Flare Prediction Using a Sequential Supervised Learning Method , 2009 .