Abstract
Space weather events may cause damage to several types of technologies, including aviation, satellites, oil and gas industries, and electrical systems, leading to economic and commercial losses. Solar flares belong to the most significant events, and refer to sudden radiation releases that can affect the Earth’s atmosphere within a few hours or minutes. Therefore, it is worth designing high-performance systems for forecasting such events. Although in the literature there are many approaches for flare forecasting, there is still a lack of consensus concerning the techniques used for designing these systems. Seeking to establish some standardization while designing flare predictors, in this study we propose a novel methodology for designing such predictors, further validated with extreme gradient boosting tree classifiers and time series. This methodology relies on the following well-defined machine learning based pipeline: (i) univariate feature selection provided with the F-score, (ii) randomized hyperparameters search and optimization, (iii) imbalanced data treatment through cost function analysis of classifiers, (iv) adjustment of cut-off point of classifiers seeking to find the optimal relationship between hit rate and precision, and (v) evaluation under operational settings. To verify our methodology effectiveness, we designed and evaluated three proof-of-concept models for forecasting flares with an X class larger than C up to 72 hours ahead. Compared to baseline models, those models were able to significantly increase their scores of true skill statistics (TSS) under operational forecasting scenarios by 0.37 (predicting flares in the next 24 hours), 0.13 (predicting flares within 24 – 48 hours), and 0.36 (predicting flares within 48 – 72 hours). Besides increasing the TSS, the methodology also led to significant increases in the area under the receiver operating characteristic (ROC) curve, corroborating that we improved the positive and negative recalls of classifiers while decreasing the number of false alarms.
Similar content being viewed by others
Notes
Data prepared in this section are available from DOI.
The source code for automating the methodology commented on this section is available from https://github.com/tiagocinto/guaraci-toolkit.
References
Ahmed, O.W., Qahwaji, R., Colak, T., Higgins, P.A., Gallagher, P.T., Bloomfield, D.S.: 2013, Solar flare prediction using advanced feature extraction, machine learning, and feature selection. Solar Phys.283, 157. DOI.
Al-Ghraibah, A., Boucheron, L.E., McAteer, R.T.J.: 2015, An automated classification approach to ranking photospheric proxies of magnetic energy build-up. Astron. Astrophys.579, A64. DOI.
Anastasiadis, A., Papaioannou, A., Sandberg, I., Georgoulis, M., Tziotziou, K., Kouloumvakos, A., Jiggens, P.: 2017, Predicting flares and solar energetic particle events: the FORSPEF tool. Solar Phys.292, 134. DOI.
Barnes, G., Leka, K.D.: 2008, Evaluating the performance of solar flare forecasting methods. Astrophys. J.688, L107. DOI.
Barnes, G., Leka, K.D., Schrijver, C.J., Colak, T., Qahwaji, R., Ashamari, O.W., Yuan, Y., Zhang, J., McAteer, R.T.J., Bloomfield, D.S., Higgins, P.A., Gallagher, P.T., Falconer, D.A., Georgoulis, M.K., Wheatland, M.S., Balch, C., Dunn, T., Wagner, E.L.: 2016, A comparison of flare forecasting methods. I. Results from the all-clear workshop. Astrophys. J.829, 89. DOI.
Batista, G.E.A.P.A., Prati, R.C., Monard, M.C.: 2004, A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explor.6, 20.
Bergstra, J., Bengio, Y.: 2012, Random search for hyper-parameter optimization. J. Mach. Learn. Res.13, 281. DOI.
Bloomfield, D.S., Higgins, P.A., McAteer, R.T.J., Gallagher, P.T.: 2012, Toward reliable benchmarking of solar flare forecasting methods. Astrophys. J.747, L41. DOI.
Bobra, M.G., Couvidat, S.: 2015, Solar flare prediction using SDO/HMI vector magnetic field data with a machine-learning algorithm. Astrophys. J.798, 135. DOI.
Canfield, R.C.: 2001, Solar active regions. In: Encyclopedia of the History of Astronomy and Astrophysics, Institute of Physics Publishing, Bristol, 1.
Chang, Y.-W., Lin, C.-J.: 2008, Feature ranking using linear SVM. WCCI2008 Workshop on Causality3, 53.
Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: 2002, SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res.16, 321.
Chen, T., Guestrin, C.: 2016, XGBoost: a scalable tree boosting system. In: Proc. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM Press, New York, 785. DOI.
Claesen, M., De Moor, B.: 2015, Hyperparameter search in machine learning. arXiv.
Colak, T., Qahwaji, R.: 2009, Automated solar activity prediction: a hybrid computer platform using machine learning and solar imaging for automated prediction of solar flares. Space Weather7, 1. DOI.
Crown, M.D.: 2012, Validation of the NOAA Space Weather Prediction Center’s solar flare forecasting look-up table and forecaster-issued probabilities. Space Weather10, S06006. DOI.
Devos, A., Verbeeck, C., Robbrecht, E.: 2014, Verification of space weather forecasting at the Regional Warning Center in Belgium. J. Space Weather Space Clim.4, A29. DOI.
Domijan, K., Bloomfield, D.S., Pitié, F.: 2019, Solar flare forecasting from magnetic feature properties generated by the Solar Monitor Active Region Tracker. Solar Phys.294, 6. DOI.
Elkan, C.: 2001, The foundations of cost-sensitive learning. In: Proc. 17th International Joint Conference on Artificial Intelligence, 973.
Eren, S., Kilcik, A., Atay, T., Miteva, R., Yurchyshyn, V., Rozelot, J.P., Ozguc, A.: 2017, Flare-production potential associated with different sunspot groups. Mon. Not. Roy. Astron. Soc.465, 68. DOI.
Falconer, D.A., Moore, R.L., Barghouty, A.F., Khazanov, I.: 2014, MAG4 versus alternative techniques for forecasting active region flare productivity. Space Weather12, 306. DOI.
Guyon, I., Elisseeff, A.: 2003, An introduction to variable and feature selection. J. Mach. Learn. Res.3, 1157.
Hada-Muranushi, Y., Muranushi, T., Asai, A., Okanohara, D., Raymond, R., Watanabe, G., Nemoto, S., Shibata, K.: 2016, A deep-learning approach for operation of an automated realtime flare forecast, arXiv.
Hale, G.E., Ellerman, F., Nicholson, S.B., Joy, A.H.: 1919, The magnetic polarity of sun-spots. Astrophys. J.49, 153.
Han, J., Kamber, M.: 2006, Data Mining: Concepts and Techniques, 2nd edn. Morgan Kaufmann Publishers, San Francisco.
Hastie, T., Tibshirani, R., Friedman, J.: 2009, The Elements of Statistical Learning – Data Mining, Inference, and Prediction, 2nd edn. Springer, New York.
Huang, X., Yu, D., Hu, Q., Wang, H., Cui, Y.: 2010, Short-term solar flare prediction using predictor teams. Solar Phys.263, 175. DOI.
Huang, X., Wang, H., Xu, L., Liu, J., Li, R., Dai, X.: 2018, Deep learning based solar flare forecasting model. I. Results for line-of-sight magnetograms. Astrophys. J.856, 7. DOI.
Jaeggli, S.A., Norton, A.A.: 2016, The magnetic classification of solar active regions 1992 – 2015. Astrophys. J. Lett.820, L11. DOI.
Jolliffe, I.T., Stephenson, D.B.: 2003, Forecast Verification – A Practitioner’s Guide in Atmospheric Science, 1st edn. John Wiley and Sons, Chichester.
Jonas, R., Bobra, M., Shankar, V., Hoeksema, J.T., Recht, B.: 2018, Flare prediction using photospheric and coronal image data. Solar Phys.293, 48. DOI.
Kilcik, A., Yurchyshyn, V., Sahin, S., Sarp, V., Obridko, V., Ozguc, A., Rozelot, J.P.: 2018, The evolution of flaring and non-flaring active regions. Mon. Not. Roy. Astron. Soc.477, 293. DOI.
Leka, K.D., Barnes, G., Wagner, E.: 2018, The NWRA classification infrastructure: description and extension to the Discriminant Analysis Flare Forecasting System (DAFFS). J. Space Weather Space Clim.8, A25. DOI.
Leka, K.D., Park, S.-H., Kusano, K., Andries, J., Barnes, G., Bingham, S., Bloomfield, D.S., McCloskey, A.E., Delouille, V., Falconer, D., Gallagher, P.T., Georgoulis, M.K., Kubo, Y., Lee, K., Lee, S., Lobzin, V., Mun, J., Murray, S.A., Hamad Nageem, T.A.M., Qahwaji, R., Sharpe, M., Steenburgh, R.A., Steward, G., Terkildsen, M.: 2019a, A comparison of flare forecasting methods. II. Benchmarks, metrics, and performance results for operational solar flare forecasting systems. Astrophys. J. Suppl.243, 36. DOI.
Leka, K.D., Park, S.-H., Kusano, K., Andries, J., Barnes, G., Bingham, S., Bloomfield, D.S., McCloskey, A.E., Delouille, V., Falconer, D., Gallagher, P.T., Georgoulis, M.K., Kubo, Y., Lee, K., Lee, S., Lobzin, V., Mun, J., Murray, S.A., Hamad Nageem, T.A.M., Qahwaji, R., Sharpe, M., Steenburgh, R.A., Steward, G., Terkildsen, M.: 2019b, A comparison of flare forecasting methods. III. Systematic behaviors of operational solar flare forecasting systems. Astrophys. J.881, 101. DOI.
McAteer, R.T.J., Gallagher, P.T., Conlon, P.A.: 2010, Turbulence, complexity, and solar flares. Adv. Space Res.45, 1067. DOI.
McCloskey, A.E., Gallagher, P.T., Bloomfield, D.S.: 2016, Flaring rates and the evolution of sunspot group McIntosh classifications. Solar Phys.291, 1711. DOI.
McIntosh, P.S.: 1990, The classification of sunspot groups. Solar Phys.125, 251. DOI.
Messerotti, M., Zuccarello, F., Guglielmino, S.L., Bothmer, V., Lilensten, J., Noci, G., Storini, M., Lundstedt, H.: 2009, Solar weather event modelling and prediction. Space Sci. Rev.147, 121. DOI.
Muranushi, T., Shibayama, T., Muranushi, Y.H., Isobe, H., Nemoto, S., Komazaki, K., Shibata, K.: 2015, UFCORIN: a fully automated predictor of solar flares in GOES X-ray flux. Space Weather13, 778. DOI.
Murray, S.A., Bingham, S., Sharpe, M., Jackson, D.R.: 2017, Flare forecasting at the Met Office Space Weather Operations Centre. Space Weather15, 577. DOI.
National Research Council (NRC): 2009, Severe space weather events – understanding societal and economic impacts. In: Committee on the Societal and Economic Impacts of Severe Space Weather Events: A Workshop, The National Academic Press, Washington, DC, 1.
Nishizuka, N., Sugiura, K., Kubo, Y., Den, M., Watari, S., Ishii, M.: 2017, Solar flare prediction model with three machine-learning algorithms using ultraviolet brightening and vector magnetogram. Astrophys. J.835, 156. DOI.
Nishizuka, N., Sugiura, K., Kubo, Y., Den, M., Ishii, M.: 2018, Deep Flare Net (DeFN) model for solar flare prediction. Astrophys. J.858, 113. DOI.
NOAA/SWPC: 2008, Sunspot Region Summary (SRS). ftp://ftp.swpc.noaa.gov/pub/forecasts/SRS/README.
NOAA/SWPC: 2011, Daily Solar Indices Summaries. ftp://ftp.swpc.noaa.gov/pub/indices/old_indices/README.
Qahwaji, R., Colak, T.: 2007, Automatic short-term solar flare prediction using machine learning and sunspot associations. Solar Phys.241, 195. DOI.
Shin, S., Lee, J.-Y., Moon, Y.-J., Chu, H., Park, J.: 2016, Development of daily maximum flare-flux forecast models for strong solar flares. Solar Phys.291, 897. DOI.
Song, H., Tan, C., Jing, J., Wang, H., Yurchyshyn, V., Abramenko, V.: 2009, Statistical assessment of photospheric magnetic features in imminent solar flare predictions. Solar Phys.254, 101. DOI.
Wilcoxon, F.: 1945, Individual comparisons by ranking methods. Biom. Bull.1, 80.
Witten, I.H., Frank, E., Hall, M.A.: 2011, Data Mining: Practical Machine Learning Tools and Techniques, 3rd edn. Morgan Kaufmann Publishers, Burlington.
Yang, X., Lin, G., Zhang, H., Mao, X.: 2013, Magnetc nonpotentiality in photospheric active regions as a predictor of solar flares. Astrophys. J.774, L27. DOI.
Yu, D., Huang, X., Wang, H., Cui, Y.: 2009, Short-term solar flare prediction using a sequential supervised learning method. Solar Phys.255, 91. DOI.
Zaki, M.J., Junior, W.M.: 2013, Data Mining and Analysis: Fundamental Concepts and Algorithms, Cambridge University Press, New York.
Acknowledgements
This study was partly funded by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES), Brazil – Finance Code 001. Besides, we thank: (i) Federal Institute of Education, Science and Technology of Rio Grande do Sul (IFRS) – Campus Feliz, for the cooperation with this research; (ii) NOAA/SWPC, for the provided data; (iii) Espaço da Escrita, Pró-Reitoria de Pesquisa, UNICAMP, for the language services provided; (iv) the reviewer, for the valuable comments and suggestions; and (v) the AWS Cloud Credits for Research program, for the computational credits provided for this research.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Disclosure of Potential Conflicts of Interest
The authors declare that they have no conflicts of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article belongs to the Topical Collection:
Towards Future Research on Space Weather Drivers
Guest Editors: Hebe Cremades and Teresa Nieves-Chinchilla
Appendix
Appendix
In this article, we use some well-defined scores according to the proposed methodology to design the forecasting models. Here, we present all of them, namely the true skill statistics (TSS) (Jolliffe and Stephenson, 2003), true positive rate (TPR) (Han and Kamber, 2006), true negative rate (TNR) (Han and Kamber, 2006), area under curve (AUC) (Witten, Frank, and Hall, 2011), false positive rate (FPR) (Witten, Frank, and Hall, 2011), positive predictive value (PPV) (Zaki and Junior, 2013), negative predictive value (NPV) (Zaki and Junior, 2013), overall accuracy (ACC) (Han and Kamber, 2006), and false alarm ratio (FAR) (Jolliffe and Stephenson, 2003).
1.1 A.1 TSS
The TSS score ranks a model performance over a scale lying on the interval [\(-1,1\)], according to which results close to −1 mean all incorrect predictions and those close to 1 mean all correct predictions. The TSS was proposed as a quality measure that combines both class-specific hit rates without being affected by imbalanced data scenarios (Bloomfield et al., 2012). In Equation 6 we show how to calculate this score:
where the TPR refers to the true positive rate and the TNR is the true negative rate.
1.2 A.2 TPR
The TPR – also known as the positive recall or probability of detection (POD) – accounts for the number of positive samples correctly predicted (Han and Kamber, 2006). In Equation 7 we show how to calculate the TPR:
where the TP accounts for the true positives (positive samples predicted as positive) and the FN are the false negatives (positive samples predicted as negative) (Han and Kamber, 2006). The TPR lies around the interval [\(0,1\)], in which higher values are better.
1.3 A.3 TNR
The TNR refers to the true negative rate – also known as the negative recall – and accounts for the number of negative samples correctly predicted (Han and Kamber, 2006). Similarly to the TPR, the TNR is scored in the same interval, as we show in Equation 8:
where the TN accounts for the true negatives (negative samples predicted as negative) and the FP are the false positives (negative samples predicted as positive) (Han and Kamber, 2006).
1.4 A.4 AUC
The AUC measures the two-dimensional area underneath the receiver operating characteristic (ROC) curve, which graphically analyzes the TPR score (y-axis) against the false positive rate (FPR) (x-axis) for a set of increasing probability thresholds to make the yes/no decisions, i.e. 0.1, 0.2, 0.3, etc. (see Figure 8). Also known as the probability of a false detection (POFD) or the false alarm rate, the FPR calculates the probability of detecting false alarms among the negative predictions, as we show in Equation 9 (Witten, Frank, and Hall, 2011):
where the FP are the false positives and the TN are the true negatives.
Best classifiers score the AUC next to the graph left-hand corner (\(\mbox{FPR} = 0\) and \(\mbox{TPR} = 1\)). On the other hand, worst classifiers score next to the graph bottom right-hand corner (\(\mbox{FPR} = 1\) and \(\mbox{TPR} = 0\)). The AUC is always positive and ideally should be greater than 0.5.
1.5 A.5 PPV
Also known as the class-specific accuracy score of a classifier, both PPV and NPV account for the classifier precision regarding individual classes. The positive precision measures the fraction of correctly predicted positive samples over all samples marked to be positive, as we show in Equation 10 (Zaki and Junior, 2013):
where the TP are the true positives and the FP are the false positives. The PPV is measured on the scale [\(0,1\)], in which the higher the values, the better the classifier.
1.6 A.6 NPV
The negative precision, in turn, measures the fraction of correctly predicted negative samples over all samples marked to be negative, as we show in Equation 11 (Zaki and Junior, 2013):
where the TN are true negatives and the FN are the false negatives. Similarly to the TPR, the NPV is also measured on the scale [\(0,1\)], where the higher the values, the better the classifier.
1.7 A.7 ACC
The overall accuracy, in turn, is a global score for classifier performance and also lies around the interval [\(0,1\)], in which the higher the score, the better the classifier. Accordingly, the overall accuracy accounts for the weighted mean of the class-specific accuracy scores, as we show in Equation 12 (Han and Kamber, 2006).
where the TP is the number of true positives, TN is the number of true negatives, FN is the number of false negatives, and FP of false positives. It is worth mentioning that the ACC should not be used alone, since it can mask the real hit rates of individual classes in imbalanced data scenarios; however, we keep it in our study for completeness purposes, since most authors use it.
1.8 A.8 FAR
Finally, the false alarm ratio represents the number of times a method forecasts events that are not observed. It is a complementary metric, and thus should be used with the positive recall to allow a better understanding of the observed false alarms. The FAR also lies around the interval [\(0,1\)]; however, the lower the score, the better the classifier. In Equation 13 we show how to calculate the FAR (Jolliffe and Stephenson, 2003):
where the FP is the number of false positives and the TP are the true positives.
Rights and permissions
About this article
Cite this article
Cinto, T., Gradvohl, A.L.S., Coelho, G.P. et al. Solar Flare Forecasting Using Time Series and Extreme Gradient Boosting Ensembles. Sol Phys 295, 93 (2020). https://doi.org/10.1007/s11207-020-01661-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11207-020-01661-9