Improved and Interpretable Solar Flare Predictions With Spatial and Topological Features of the Polarity Inversion Line Masked Magnetograms
dc.contributor.author | Sun, Hu | |
dc.contributor.author | Manchester, Ward | |
dc.contributor.author | Chen, Yang | |
dc.date.accessioned | 2022-01-06T15:52:28Z | |
dc.date.available | 2023-01-06 10:52:26 | en |
dc.date.available | 2022-01-06T15:52:28Z | |
dc.date.issued | 2021-12 | |
dc.identifier.citation | Sun, Hu; Manchester, Ward; Chen, Yang (2021). "Improved and Interpretable Solar Flare Predictions With Spatial and Topological Features of the Polarity Inversion Line Masked Magnetograms." Space Weather 19(12): n/a-n/a. | |
dc.identifier.issn | 1542-7390 | |
dc.identifier.issn | 1542-7390 | |
dc.identifier.uri | https://hdl.handle.net/2027.42/171250 | |
dc.description.abstract | Many current research efforts undertake the solar flare classification task using the Space‐weather HMI Active Region Patch (SHARP) parameters as the predictors. The SHARP parameters are scalar quantities based on spatial average or integration of physical quantities derived from the vector magnetic field, which loses information of the two‐dimensional spatial distribution of the field and related quantities. In this paper, we construct two new sets of spatial features to expand the feature set used for the flare classification task. The first set uses the idea of topological data analysis to summarize the geometric information of the distributions of various SHARP quantities across active regions. The second set utilizes tools coming from spatial statistics to analyze the vertical magnetic field component Br and summarize its spatial variations and clustering patterns. All features are constructed within regions near the polarity inversion lines (PILs) and classification performances using the new features are compared against those using SHARP parameters (also along the PIL). We found that using the new features can improve the skill scores of the flare classification model and new features tend to have higher feature importance, especially the spatial statistics features. This potentially suggests that even using a single magnetic field component, Br, instead of all SHARP parameters, one can still derive strongly predictive features for flare classification.Plain Language SummaryOur research is targeted at improving the accuracy of solar flare classification by training machine learning models with new interpretable features beyond well‐known physics‐based predictors. We count the number of closed loops and calculate multiple summary statistics of the spatial distribution of high‐resolution magnetic field images of solar active regions to boost the classification result of strong and weak flares. Our results reveal that the spatial distribution of local physical quantities derived from the magnetograms, beyond those commonly adopted, aggregated quantities, can be helpful to improve flare predictability.Key PointsWe adopt a polarity inversion line (PIL) detecting algorithm to obtain PIL masks for the Br component and several SHARP parameter mapsWe construct two sets of spatial statistics features and a collection of topological features based on the PIL masksOur newly constructed features, by itself or joint with topological features, can significantly improve flare predictions than using SHARP parameters only | |
dc.publisher | ACM | |
dc.publisher | Wiley Periodicals, Inc. | |
dc.title | Improved and Interpretable Solar Flare Predictions With Spatial and Topological Features of the Polarity Inversion Line Masked Magnetograms | |
dc.type | Article | |
dc.rights.robots | IndexNoFollow | |
dc.subject.hlbsecondlevel | Electrical Engineering | |
dc.subject.hlbtoplevel | Engineering | |
dc.description.peerreviewed | Peer Reviewed | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/171250/1/swe21234.pdf | |
dc.description.bitstreamurl | http://deepblue.lib.umich.edu/bitstream/2027.42/171250/2/swe21234_am.pdf | |
dc.identifier.doi | 10.1029/2021SW002837 | |
dc.identifier.source | Space Weather | |
dc.identifier.citedreference | Nishizuka, N., Sugiura, K., Kubo, Y., Den, M., & Ishii, M. ( 2018 ). Deep flare net (defn) model for solar flare prediction. The Astrophysical Journal, 858 ( 2 ), 113. https://doi.org/10.3847/1538-4357/aab9a7 | |
dc.identifier.citedreference | Munch, E. ( 2017 ). A user’s guide to topological data analysis. Journal of Learning Analytics, 4 ( 2 ), 47 – 61. https://doi.org/10.18608/jla.2017.42.6 | |
dc.identifier.citedreference | Muranushi, Y. H., Muranushi, T., Asai, A., Okanohara, D., Raymond, R., Watanabe, G., et al. ( 2016 ). A deep‐learning approach for operation of an automated realtime flare forecast (CoRR, abs/1606.01587). Retrieved from http://arxiv.org/abs/1606.01587 | |
dc.identifier.citedreference | Nishizuka, N., Kubo, Y., Sugiura, K., Den, M., & Ishii, M. ( 2021 ). Operational solar flare prediction model using deep flare net. Earth, Planets and Space, 73 ( 1 ), 1 – 12. https://doi.org/10.1186/s40623-021-01381-9 | |
dc.identifier.citedreference | Oliver, M. A., & Webster, R. ( 2015 ). Basic steps in geostatistics: The variogram and kriging. Springer. https://link.springer.com/book/10.1007/978-3-319-15865-5 | |
dc.identifier.citedreference | Omre, H. ( 1984 ). The variogram and its estimation. In Geostatistics for natural resources characterization (pp. 107 – 125 ). Springer. https://doi.org/10.1007/978-94-009-3699-7_7 | |
dc.identifier.citedreference | Ripley, B. D. ( 1976 ). The second‐order analysis of stationary point processes. Journal of Applied Probability, 13 ( 2 ), 255 – 266. https://doi.org/10.2307/3212829 | |
dc.identifier.citedreference | Safavian, S. R., & Landgrebe, D. ( 1991 ). A survey of decision tree classifier methodology. IEEE Transactions on Systems, Man, and Cybernetics, 21 ( 3 ), 660 – 674. https://doi.org/10.1109/21.97458 | |
dc.identifier.citedreference | Schrijver, C. J. ( 2007 ). A characteristic magnetic field pattern associated with all major solar flares and its use in flare forecasting. The Astrophysical Journal, 655 ( 2 ), L117 – L120. https://doi.org/10.1086/511857 | |
dc.identifier.citedreference | Schrijver, C. J., De Rosa, M. L., Title, A. M., & Metcalf, T. R. ( 2005 ). The nonpotentiality of active‐region coronae and the dynamics of the photospheric magnetic field. The Astrophysical Journal, 628 ( 1 ), 501 – 513. https://doi.org/10.1086/430733 | |
dc.identifier.citedreference | Stork, D. G., Duda, R. O., Hart, P. E., & Stork, D. ( 2001 ). Pattern classification. A Wiley‐Interscience Publication. https://www.wiley.com/en-us/Pattern+Classification%2C+2nd+Edition-p-9780471056690 | |
dc.identifier.citedreference | Toriumi, S., & Hotta, H. ( 2019 ). Spontaneous generation of δ ‐sunspots in convective magnetohydrodynamic simulation of magnetic flux emergence. The Astrophysical Journal, 886 ( 1 ), L21. https://doi.org/10.3847/2041-8213/ab55e7 | |
dc.identifier.citedreference | Török, T., Leake, J. E., Titov, V. S., Archontis, V., Mikić, Z., Linton, M. G., et al. ( 2014 ). Distribution of electric currents in solar active regions. The Astrophysical Journal, 782 ( 1 ), L10. https://doi.org/10.1088/2041-8205/782/1/l10 | |
dc.identifier.citedreference | Uritsky, V. M., & Davila, J. M. ( 2012 ). Multiscale dynamics of solar magnetic structures. The Astrophysical Journal, 748 ( 1 ), 60. https://doi.org/10.1088/0004-637X/748/1/60 | |
dc.identifier.citedreference | Wang, J., Liu, S., Ao, X., Zhang, Y., Wang, T., & Liu, Y. ( 2019 ). Parameters derived from the SDO/HMI vector magnetic field data: Potential to improve machine‐learning‐based solar flare prediction models. The Astrophysical Journal, 884 ( 2 ), 175. https://doi.org/10.3847/1538-4357/ab441b | |
dc.identifier.citedreference | Wang, J., Zhang, Y., Webber, S. A. H., Liu, S., Meng, X., & Wang, T. ( 2020 ). Solar flare predictive features derived from polarity inversion line masks in active regions using an unsupervised machine learning algorithm. The Astrophysical Journal, 892 ( 2 ), 140. https://doi.org/10.3847/1538-4357/ab7b6c | |
dc.identifier.citedreference | Wang, X., Chen, Y., Toth, G., Manchester, W. B., Gombosi, T. I., Hero, A. O., et al. ( 2020 ). Predicting solar flares with machine learning: Investigating solar cycle dependence. The Astrophysical Journal, 895 ( 1 ), 3. https://doi.org/10.3847/1538-4357/ab89ac | |
dc.identifier.citedreference | Wasserman, L. ( 2018 ). Topological data analysis. Annual Review of Statistics and Its Application, 5, 501 – 532. https://doi.org/10.1146/annurev-statistics-031017-100045 | |
dc.identifier.citedreference | Zomorodian, A. J. (Ed.). ( 2012 ). Advances in Applied and Computational Topology: American Mathematical Society Short Course on Computational Topology, January 4–5, 2011, New Orleans, Louisiana (Vol. 70 ). American Mathematical Society. | |
dc.identifier.citedreference | Archontis, V., & Török, T. ( 2008 ). Eruption of magnetic flux ropes during flux emergence. Astronomy and Astrophysics, 492 ( 2 ), L35 – L38. https://doi.org/10.1051/0004-6361:200811131 | |
dc.identifier.citedreference | Aschwanden, M. J., & Aschwanden, P. D. ( 2008 ). Solar flare geometries. I. The area fractal dimension. The Astrophysical Journal, 674 ( 1 ), 530 – 543. https://doi.org/10.1086/524371 | |
dc.identifier.citedreference | Aschwanden, M. J., Crosby, N. B., Dimitropoulou, M., Georgoulis, M. K., Hergarten, S., McAteer, J., et al. ( 2016 ). 25 years of self‐organized criticality: Solar and astrophysics. Space Science Reviews, 198 ( 1–4 ), 47 – 166. https://doi.org/10.1007/s11214-014-0054-6 | |
dc.identifier.citedreference | Barnes, G., Leka, K. D., Schrijver, C. J., Colak, T., Qahwaji, R., Ashamari, O., et al. ( 2016 ). A comparison of flare forecasting methods. I. Results from the “all‐clear” workshop. The Astrophysical Journal, 829 ( 2 ), 89. https://doi.org/10.3847/0004-637x/829/2/89 | |
dc.identifier.citedreference | Barnes, G., Leka, K. D., Schumer, E., & Della‐Rose, D. ( 2007 ). Probabilistic forecasting of solar flares from vector magnetogram data. Space Weather, 5 ( 9 ). https://doi.org/10.1029/2007sw000317 | |
dc.identifier.citedreference | Bobra, M. G., & Couvidat, S. ( 2015 ). Solar flare prediction using SDO/HMI vector magnetic field data with a machine‐learning algorithm. The Astrophysical Journal, 798 ( 2 ), 135. https://doi.org/10.1088/0004-637x/798/2/135 | |
dc.identifier.citedreference | Bobra, M. G., Sun, X., Hoeksema, J. T., Turmon, M., Liu, Y., Hayashi, K., et al. ( 2014 ). The helioseismic and magnetic imager (HMI) vector magnetic field pipeline: Sharps – Space‐weather HMI active region patches. Solar Physics, 289 ( 9 ), 3549 – 3578. https://doi.org/10.1007/s11207-014-0529-3 | |
dc.identifier.citedreference | Camporeale, E. ( 2019 ). The challenge of machine learning in space weather nowcasting and forecasting. Space Weather, 17, 1166 – 1207. https://doi.org/10.1029/2018sw002061 | |
dc.identifier.citedreference | Chen, T., & Guestrin, C. ( 2016 ). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785 – 794 ). ACM. | |
dc.identifier.citedreference | Chen, Y., Manchester, W. B., Hero, A. O., Toth, G., DuFumier, B., Zhou, T., et al. ( 2019 ). Identifying solar flare precursors using time series of SDO/HMI images and SHARP parameters. Space Weather, 17 ( 10 ), 1404 – 1426. https://doi.org/10.1029/2019sw002214 | |
dc.identifier.citedreference | Cressie, N., & Hawkins, D. M. ( 1980 ). Robust estimation of the variogram: I. Journal of the International Association for Mathematical Geology, 12 ( 2 ), 115 – 125. https://doi.org/10.1007/bf01035243 | |
dc.identifier.citedreference | Deshmukh, V., Berger, T., Meiss, J., & Bradley, E. ( 2021 ). Shape‐based feature engineering for solar flare prediction. arXiv preprint arXiv:2012.14405. https://ojs.aaai.org/index.php/AAAI/article/view/17795 | |
dc.identifier.citedreference | Deshmukh, V., Berger, T. E., Bradley, E., & Meiss, J. D. ( 2020 ). Leveraging the mathematics of shape for solar magnetic eruption prediction. Journal of Space Weather and Space Climate, 10, 13. https://doi.org/10.1051/swsc/2020014 | |
dc.identifier.citedreference | Ester, M., Kriegel, H.‐P., Sander, J., & Xu, X. ( 1996 ). A density‐based algorithm for discovering clusters in large spatial databases with noise. In KDD Proceedings (Vol. 96, pp. 226 – 231 ). https://www.aaai.org/Papers/KDD/1996/KDD96-037.pdf | |
dc.identifier.citedreference | Falconer, D. A. ( 2001 ). A prospective method for predicting coronal mass ejections from vector magnetograms. Journal of Geophysical Research, 106, 25185 – 25190. https://doi.org/10.1029/2000JA004005 | |
dc.identifier.citedreference | Falconer, D. A., Moore, R. L., & Gary, G. A. ( 2002 ). Correlation of the coronal mass ejection productivity of solar active regions with measures of their global nonpotentiality from vector magnetograms: Baseline results. The Astrophysical Journal, 569, 1016 – 1025. https://doi.org/10.1086/339161 | |
dc.identifier.citedreference | Falconer, D. A., Moore, R. L., & Gary, G. A. ( 2003 ). A measure from line‐of‐sight magnetograms for prediction of coronal mass ejections. Journal of Geophysical Research, 108, 1380. https://doi.org/10.1029/2003JA010030 | |
dc.identifier.citedreference | Falconer, D. A., Moore, R. L., & Gary, G. A. ( 2006 ). Magnetic causes of solar coronal mass ejections: Dominance of the free magnetic energy over the magnetic twist alone. The Astrophysical Journal, 644, 1258 – 1272. https://doi.org/10.1086/503699 | |
dc.identifier.citedreference | Fan, Y. ( 2001 ). The emergence of a twisted Ω‐tube into the solar atmosphere. The Astrophysical Journal, 554 ( 1 ), L111 – L114. https://doi.org/10.1086/320935 | |
dc.identifier.citedreference | Fang, F., & Fan, Y. ( 2015 ). δ ‐Sunspot formation in simulation of active‐region‐scale flux emergence. The Astrophysical Journal, 806 ( 1 ), 79. https://doi.org/10.1088/0004-637X/806/1/79 | |
dc.identifier.citedreference | Fang, F., Manchester, W., Abbett, W. P., & van der Holst, B. ( 2010 ). Simulation of flux emergence from the convection zone to the corona. The Astrophysical Journal, 714 ( 2 ), 1649 – 1657. https://doi.org/10.1088/0004-637x/714/2/1649 | |
dc.identifier.citedreference | Florios, K., Kontogiannis, I., Park, S.‐H., Guerra, J. A., Benvenuto, F., Bloomfield, D. S., & Georgoulis, M. K. ( 2018 ). Forecasting solar flares using magnetogram‐based predictors and machine learning. Solar Physics, 293 ( 2 ). https://doi.org/10.1007/s11207-018-1250-4 | |
dc.identifier.citedreference | Friedman, J. H. ( 2002 ). Stochastic gradient boosting. Computational Statistics & Data Analysis, 38 ( 4 ), 367 – 378. https://doi.org/10.1016/s0167-9473(01)00065-2 | |
dc.identifier.citedreference | Gelfand, A. E., Diggle, P., Guttorp, P., & Fuentes, M. ( 2010 ). Handbook of spatial statistics. CRC Press. https://doi.org/10.1201/9781420072884 | |
dc.identifier.citedreference | Ghrist, R. ( 2008 ). Barcodes: The persistent topology of data. Bulletin of the American Mathematical Society, 45 ( 1 ), 61 – 75. https://doi.org/10.1090/s0273-0979-07-01191-3 | |
dc.identifier.citedreference | Hall, P., Müller, H.‐G., & Wang, J.‐L. ( 2006 ). Properties of principal component methods for functional and longitudinal data analysis. The Annals of Statistics, 34 ( 3 ), 1493 – 1517. https://doi.org/10.1214/009053606000000272 | |
dc.identifier.citedreference | Jiao, Z., Sun, H., Wang, X., Manchester, W., Gombosi, T., Hero, A., & Chen, Y. ( 2020 ). Solar flare intensity prediction with machine learning models. Space Weather, 18 ( 7 ), e2020SW002440. https://doi.org/10.1029/2020sw002440 | |
dc.identifier.citedreference | Kaczynski, T., Mischaikow, K. M., & Mrozek, M. ( 2004 ). Computational homology (Vol. 3, No. 7 ). Springer. https://link.springer.com/book/10.1007/b97315 | |
dc.identifier.citedreference | Leka, K. D., & Barnes, G. ( 2003a ). Photospheric magnetic field properties of flaring versus flare‐quiet active regions. I. Data, general approach, and sample results. The Astrophysical Journal, 595 ( 2 ), 1277 – 1295. https://doi.org/10.1086/377511 | |
dc.identifier.citedreference | Leka, K. D., & Barnes, G. ( 2003b ). Photospheric magnetic field properties of flaring versus flare‐quiet active regions. II. Discriminant analysis. The Astrophysical Journal, 595 ( 2 ), 1296 – 1306. https://doi.org/10.1086/377512 | |
dc.identifier.citedreference | Leka, K. D., & Barnes, G. ( 2018 ). Solar flare forecasting: Present methods and challenges. In N. Buzulukova (Ed.), Extreme events in geospace (pp. 65 – 98 ). Elsevier. https://doi.org/10.1016/B978-0-12-812700-1.00003-0 | |
dc.identifier.citedreference | Leka, K. D., Park, S.‐H., Kusano, K., Andries, J., Barnes, G., Bingham, S., et al. ( 2019a ). A comparison of flare forecasting methods. II. Benchmarks, metrics, and performance results for operational solar flare forecasting systems. The Astrophysical Journal Supplement Series, 243 ( 2 ), 36. https://doi.org/10.3847/1538-4365/ab2e12 | |
dc.identifier.citedreference | Leka, K. D., Park, S.‐H., Kusano, K., Andries, J., Barnes, G., Bingham, S., et al. ( 2019b ). A comparison of flare forecasting methods. III. Systematic behaviors of operational solar flare forecasting systems. The Astrophysical Journal, 881 ( 2 ), 101. https://doi.org/10.3847/1538-4357/ab2e11 | |
dc.identifier.citedreference | Linton, M. G., Dahlburg, R. B., Fisher, G. H., & Longcope, D. W. ( 1998 ). Nonlinear evolution of Kink‐unstable magnetic flux tubes and solar δ ‐spot active regions. The Astrophysical Journal, 507 ( 1 ), 404 – 416. https://doi.org/10.1086/306299 | |
dc.identifier.citedreference | Liu, C., Deng, N., Wang, J. T. L., & Wang, H. ( 2017 ). Predicting solar flares using SDO/HMI vector magnetic data products and the random forest algorithm. The Astrophysical Journal, 843 ( 2 ), 104. https://doi.org/10.3847/1538-4357/aa789b | |
dc.identifier.citedreference | Liu, H., Liu, C., Wang, J. T. L., & Wang, H. ( 2019 ). Predicting solar flares using a long short‐term memory network. The Astrophysical Journal, 877 ( 2 ), 121. https://doi.org/10.3847/1538-4357/ab1b3c | |
dc.identifier.citedreference | Manchester, W., IV. ( 2001 ). The role of nonlinear Alfvén waves in shear formation during solar magnetic flux emergence. The Astrophysical Journal, 547 ( 1 ), 503 – 519. https://doi.org/10.1086/318342 | |
dc.identifier.citedreference | Manchester, W., IV. ( 2007 ). Solar atmospheric dynamic coupling due to shear motions driven by the Lorentz force. The Astrophysical Journal, 666 ( 1 ), 532 – 540. https://doi.org/10.1086/520493 | |
dc.identifier.citedreference | Manchester, W., IV., Gombosi, T., DeZeeuw, D., & Fan, Y. ( 2004 ). Eruption of a buoyantly emerging magnetic flux rope. The Astrophysical Journal, 610 ( 1 ), 588 – 596. https://doi.org/10.1086/421516 | |
dc.identifier.citedreference | Maria, C., Boissonnat, J.‐D., Glisse, M., & Yvinec, M. ( 2014 ). The gudhi library: Simplicial complexes and persistent homology. In International Congress on Mathematical Software (pp. 167 – 174 ). https://doi.org/10.1007/978-3-662-44199-2_28 | |
dc.identifier.citedreference | McAteer, R. T. J., Gallagher, P. T., & Ireland, J. ( 2005 ). Statistics of active region complexity: A large‐scale fractal dimension survey. The Astrophysical Journal, 631 ( 1 ), 628 – 635. https://doi.org/10.1086/432412 | |
dc.working.doi | NO | en |
dc.owningcollname | Interdisciplinary and Peer-Reviewed |
Files in this item
Remediation of Harmful Language
The University of Michigan Library aims to describe library materials in a way that respects the people and communities who create, use, and are represented in our collections. Report harmful or offensive language in catalog records, finding aids, or elsewhere in our collections anonymously through our metadata feedback form. More information at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.