Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables

This study aims to improve the understanding of geomagnetic storms by utilizing machine learning models and analyzing several heliophysical variables, such as the interplanetary magnetic field, proton density, solar wind speed, and proton temperature. Rather than relying on traditional correlation-b...

Full description

Autores:: Sierra Porta, David
Petro Ramos, Jesús
Ruiz Morales, David
Herrera Acevedo, Daniel
García Teheran, Andrés
Tarazona Alvarado, José

Tipo de recurso:

Fecha de publicación:: 2024

Institución:: Universidad Tecnológica de Bolívar

Repositorio:: Repositorio Institucional UTB

Idioma:: eng

id	UTB2_89426f23e3d8a2fb520860b4722cb9f1
oai_identifier_str	oai:repositorio.utb.edu.co:20.500.12585/12719
network_acronym_str	UTB2
network_name_str	Repositorio Institucional UTB
repository_id_str
dc.title.spa.fl_str_mv	Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables
title	Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables
spellingShingle	Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables Space weather Machine learning Statistical modeling Geomagnetic storms Data science LEMB
title_short	Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables
title_full	Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables
title_fullStr	Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables
title_full_unstemmed	Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables
title_sort	Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables
dc.creator.fl_str_mv	Sierra Porta, David Petro Ramos, Jesús Ruiz Morales, David Herrera Acevedo, Daniel García Teheran, Andrés Tarazona Alvarado, José
dc.contributor.author.none.fl_str_mv	Sierra Porta, David Petro Ramos, Jesús Ruiz Morales, David Herrera Acevedo, Daniel García Teheran, Andrés Tarazona Alvarado, José
dc.subject.keywords.spa.fl_str_mv	Space weather Machine learning Statistical modeling Geomagnetic storms Data science
topic	Space weather Machine learning Statistical modeling Geomagnetic storms Data science LEMB
dc.subject.armarc.none.fl_str_mv	LEMB
description	This study aims to improve the understanding of geomagnetic storms by utilizing machine learning models and analyzing several heliophysical variables, such as the interplanetary magnetic field, proton density, solar wind speed, and proton temperature. Rather than relying on traditional correlation-based methods, we employ advanced machine learning techniques to examine the complex relationships between these factors and geomagnetic storms. Our analysis covers a large dataset spanning six solar cycles, including the current 25th cycle, to provide comprehensive insights into the dynamics of these storms. Our study highlights the significance of the interplanetary magnetic field as a key predictor of geomagnetic storms, challenging previous beliefs that primarily focused on sunspot activity. By using high-resolution data, we uncover new patterns and provide a more detailed analysis of the factors influencing geomagnetic storms. We emphasize the importance of considering a range of heliophysical variables, such as proton temperature and flow pressure, which offer new insights into the complex dynamics driving these storm events. The application of machine learning models, particularly Random Forest and Gradient Boosting, demonstrated superior predictive accuracy compared to traditional methods. Our results reveal that the Dst-index MIN, scalar B, and alpha/proton ratio are among the most influential factors, accounting for a significant portion of the prediction model’s accuracy. These findings underscore the utility of machine learning in identifying critical drivers of geomagnetic activity and enhancing forecast precision. Additionally, our research underscores the need for comprehensive models that can accurately predict geomagnetic storms by integrating various data sources. This machine learning approach not only improves predictive accuracy but also enhances our understanding of the underlying mechanisms of space weather. The insights gained from this study have important implications for both scientific research and practical applications, such as improving early warning systems for geomagnetic storms and mitigating their potential impacts on Earth.
publishDate	2024
dc.date.accessioned.none.fl_str_mv	2024-09-06T14:43:25Z
dc.date.available.none.fl_str_mv	2024-09-06T14:43:25Z
dc.date.issued.none.fl_str_mv	2024-08-14
dc.date.submitted.none.fl_str_mv	2024-09-05
dc.type.coarversion.fl_str_mv	http://purl.org/coar/version/c_b1a7d7d4d402bcce
dc.type.coar.fl_str_mv	http://purl.org/coar/resource_type/c_2df8fbb1
dc.type.driver.spa.fl_str_mv	info:eu-repo/semantics/article
dc.type.hasversion.spa.fl_str_mv	info:eu-repo/semantics/draft
dc.type.spa.spa.fl_str_mv	http://purl.org/coar/resource_type/c_6501
status_str	draft
dc.identifier.citation.spa.fl_str_mv	D. Sierra-Porta, J.D. Petro-Ramos, D.J. Ruiz-Morales, D.D. Herrera-Acevedo, A.F. García-Teheran, M. Tarazona Alvarado, Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables, Advances in Space Research, Volume 74, Issue 8, 2024, Pages 3483-3495, ISSN 0273-1177, https://doi.org/10.1016/j.asr.2024.08.031. (https://www.sciencedirect.com/science/article/pii/S0273117724008500)
dc.identifier.uri.none.fl_str_mv	https://hdl.handle.net/20.500.12585/12719
dc.identifier.doi.none.fl_str_mv	10.1016/j.asr.2024.08.031
dc.identifier.instname.spa.fl_str_mv	Universidad Tecnológica de Bolívar
dc.identifier.reponame.spa.fl_str_mv	Repositorio Universidad Tecnológica de Bolívar
identifier_str_mv	D. Sierra-Porta, J.D. Petro-Ramos, D.J. Ruiz-Morales, D.D. Herrera-Acevedo, A.F. García-Teheran, M. Tarazona Alvarado, Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables, Advances in Space Research, Volume 74, Issue 8, 2024, Pages 3483-3495, ISSN 0273-1177, https://doi.org/10.1016/j.asr.2024.08.031. (https://www.sciencedirect.com/science/article/pii/S0273117724008500) 10.1016/j.asr.2024.08.031 Universidad Tecnológica de Bolívar Repositorio Universidad Tecnológica de Bolívar
url	https://hdl.handle.net/20.500.12585/12719
dc.language.iso.spa.fl_str_mv	eng
language	eng
dc.rights.coar.fl_str_mv	http://purl.org/coar/access_right/c_abf2
dc.rights.uri.*.fl_str_mv	http://creativecommons.org/publicdomain/zero/1.0/
dc.rights.accessrights.spa.fl_str_mv	info:eu-repo/semantics/openAccess
dc.rights.cc.*.fl_str_mv	CC0 1.0 Universal
rights_invalid_str_mv	http://creativecommons.org/publicdomain/zero/1.0/ CC0 1.0 Universal http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv	openAccess
dc.format.extent.none.fl_str_mv	13 páginas
dc.format.mimetype.spa.fl_str_mv	application/pdf
dc.coverage.spatial.none.fl_str_mv	Colombia
dc.publisher.place.spa.fl_str_mv	Cartagena de Indias
dc.publisher.faculty.spa.fl_str_mv	Ciencias Básicas
dc.publisher.sede.spa.fl_str_mv	Campus Tecnológico
dc.source.spa.fl_str_mv	Sciencedirect - Advances in Space Research, Vol. 74 N° 8 (2024)
institution	Universidad Tecnológica de Bolívar
bitstream.url.fl_str_mv	https://repositorio.utb.edu.co/bitstream/20.500.12585/12719/1/GeomagneticStorms_regression_models%20%282%29.pdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12719/2/license_rdf https://repositorio.utb.edu.co/bitstream/20.500.12585/12719/3/license.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12719/5/GeomagneticStorms_regression_models%20%282%29.pdf.txt https://repositorio.utb.edu.co/bitstream/20.500.12585/12719/4/GeomagneticStorms_regression_models%20%282%29.pdf.jpg
bitstream.checksum.fl_str_mv	7e5140280f8dcc571e6b92895eab4f83 42fd4ad1e89814f5e4a476b409eb708c e20ad307a1c5f3f25af9304a7a7c86b6 9df784e3137f8a0388cd10412606e651 3c4c0ab7d1ebef5c4ff33334e769fc01
bitstream.checksumAlgorithm.fl_str_mv	MD5 MD5 MD5 MD5 MD5
repository.name.fl_str_mv	Repositorio Institucional UTB
repository.mail.fl_str_mv	repositorioutb@utb.edu.co
_version_	1812096426355720192
spelling	Sierra Porta, David88a81b30-0b54-4821-b432-affefb13412bPetro Ramos, Jesús9a59ebc0-1d57-44bf-a8d1-788e56d4e5f8Ruiz Morales, David93b5bbdf-c523-481c-9f0d-3faf576e3ed5Herrera Acevedo, Daniel2f2e14ba-6e9b-4697-a7f7-312414a61c76García Teheran, Andrésc19a6ba8-23b1-46c1-85bc-db57a69d9671Tarazona Alvarado, José688d5c9f-75fa-4d17-b67d-859b66ac4628Colombia2024-09-06T14:43:25Z2024-09-06T14:43:25Z2024-08-142024-09-05D. Sierra-Porta, J.D. Petro-Ramos, D.J. Ruiz-Morales, D.D. Herrera-Acevedo, A.F. García-Teheran, M. Tarazona Alvarado, Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables, Advances in Space Research, Volume 74, Issue 8, 2024, Pages 3483-3495, ISSN 0273-1177, https://doi.org/10.1016/j.asr.2024.08.031. (https://www.sciencedirect.com/science/article/pii/S0273117724008500)https://hdl.handle.net/20.500.12585/1271910.1016/j.asr.2024.08.031Universidad Tecnológica de BolívarRepositorio Universidad Tecnológica de BolívarThis study aims to improve the understanding of geomagnetic storms by utilizing machine learning models and analyzing several heliophysical variables, such as the interplanetary magnetic field, proton density, solar wind speed, and proton temperature. Rather than relying on traditional correlation-based methods, we employ advanced machine learning techniques to examine the complex relationships between these factors and geomagnetic storms. Our analysis covers a large dataset spanning six solar cycles, including the current 25th cycle, to provide comprehensive insights into the dynamics of these storms. Our study highlights the significance of the interplanetary magnetic field as a key predictor of geomagnetic storms, challenging previous beliefs that primarily focused on sunspot activity. By using high-resolution data, we uncover new patterns and provide a more detailed analysis of the factors influencing geomagnetic storms. We emphasize the importance of considering a range of heliophysical variables, such as proton temperature and flow pressure, which offer new insights into the complex dynamics driving these storm events. The application of machine learning models, particularly Random Forest and Gradient Boosting, demonstrated superior predictive accuracy compared to traditional methods. Our results reveal that the Dst-index MIN, scalar B, and alpha/proton ratio are among the most influential factors, accounting for a significant portion of the prediction model’s accuracy. These findings underscore the utility of machine learning in identifying critical drivers of geomagnetic activity and enhancing forecast precision. Additionally, our research underscores the need for comprehensive models that can accurately predict geomagnetic storms by integrating various data sources. This machine learning approach not only improves predictive accuracy but also enhances our understanding of the underlying mechanisms of space weather. The insights gained from this study have important implications for both scientific research and practical applications, such as improving early warning systems for geomagnetic storms and mitigating their potential impacts on Earth.13 páginasapplication/pdfenghttp://creativecommons.org/publicdomain/zero/1.0/info:eu-repo/semantics/openAccessCC0 1.0 Universalhttp://purl.org/coar/access_right/c_abf2Sciencedirect - Advances in Space Research, Vol. 74 N° 8 (2024)Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variablesinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/drafthttp://purl.org/coar/resource_type/c_6501http://purl.org/coar/version/c_b1a7d7d4d402bccehttp://purl.org/coar/resource_type/c_2df8fbb1Space weatherMachine learningStatistical modelingGeomagnetic stormsData scienceLEMBCartagena de IndiasCiencias BásicasCampus TecnológicoPúblico generalAbe, O., Fakomiti, M., Igboama, W. et al. (2023). Statistical analysis of the 793 occurrence rate of geomagnetic storms during solar cycles 20–24. Advances 794 in Space Research, 71(5), 2240–2251. doi:https://doi.org/10.1016/ 795 j.asr.2022.10.033.Abraha, G., Yemane, T., & Kassa, T. (2020). Geomagnetic storms and their 797 impacts on ethiopian power grid. Advances in Astronomy and Space Physics, 798 10, 55–64.Adnan, M., Alarood, A. A. S., Uddin, M. I. et al. (2022). Utilizing grid 800 search cross-validation with adaptive boosting for augmenting performance 801 of machine learning models. PeerJ Computer Science, 8, e803. doi:https: 802 //doi.org/10.7717/peerj-cs.803.Alibrahim, H., & Ludwig, S. A. (2021). Hyperparameter optimization: Com- 804 paring genetic algorithm against grid search and bayesian optimization. In 805 2021 IEEE Congress on Evolutionary Computation (CEC) (pp. 1551–1559). 806 IEEE. doi:https://doi.org/10.1109/CEC45853.2021.9504761.Bentéjac, C., Csörgo, A., & Martínez-Muñoz, G. (2021). A comparative analy- ˝ 808 sis of gradient boosting algorithms. Artificial Intelligence Review, 54, 1937– 809 1967. doi:https://doi.org/10.1007/s10462-020-09896-5Biau, G., & Scornet, E. (2016). A random forest guided tour. Test, 25, 197–227. 811 doi:https://doi.org/10.1007/s11749-016-0481-7Borovsky, J. E., & Shprits, Y. Y. (2017). Is the dst index sufficient to define 813 all geospace storms? Journal of Geophysical Research: Space Physics, 814 122(11), 11–543. doi:https://doi.org/10.1002/2017JA024679Boroyev, R. N., Vasiliev, M. S., & Baishev, D. G. (2020). The relation- 816 ship between geomagnetic indices and the interplanetary medium param- 817 eters in magnetic storm main phases during cir and icme events. Jour- 818 nal of Atmospheric and Solar-Terrestrial Physics, 204, 105290. doi:https: 819 //doi.org/10.1016/j.jastp.2020.105290.Breiman, L. (2001). Random forests. Machine learning, 45, 5–32. doi:https: 821 //doi.org/10.1023/A:1010933404324Chiu, M., Von-Mehlem, U., Willey, C. et al. (1998). Ace spacecraft. 823 Space science reviews, 86, 257–284. doi:https://doi.org/10.1023/A: 824 1005002013459.Cliver, E. W., Boriakoff, V., & Bounar, K. H. (1996). The 22-year cy- 826 cle of geomagnetic and solar wind activity. Journal of Geophysical Re- 827 search: Space Physics, 101(A12), 27091–27109. doi:https://doi.org/ 828 10.1029/96JA02037Drucker, H. (1997). Improving regressors using boosting tech- 830 niques. In Icml (pp. 107–115). Citeseer volume 97. URL: 831 https://citeseerx.ist.psu.edu/document?repid=rep1&type= 832 pdf&doi=6d8226a52ebc70c8d97ccae10a74e1b0a3908ec1Echer, E., Gonzalez, W. D., Tsurutani, B. T. et al. (2008). Interplanetary condi- 834 tions causing intense geomagnetic storms (dst≤- 100 nt) during solar cy- 835 cle 23 (1996–2006). Journal of Geophysical Research: Space Physics, 836 113(A5). doi:https://doi.org/10.1029/2007JA012744.Echer, E., Tsurutani, B., & Gonzalez, W. (2013). Interplanetary origins of 838 moderate (- 100 nt< dst≤- 50 nt) geomagnetic storms during solar cycle 23 839 (1996–2008). Journal of Geophysical Research: Space Physics, 118(1), 840 385–392. doi:https://doi.org/10.1029/2012JA018086Eid, A., Nawawy, M., & Robaa, S. (2022). Geomagnetic storm impacts on com843 munication, navigation, surveillance, and air traffic management (cns/atm). 844 Current Science International, 11(3), 282–290.Fairfield, D., Lepping, R., Hones Jr, E. et al. (1981). Simultaneous measure846 ments of magnetotail dynamics by imp spacecraft. Journal of Geophysi847 cal Research: Space Physics, 86(A3), 1396–1414. doi:https://doi.org/ 848 10.1029/JA086iA03p01396.Frank, L. A. (1994). Comprehensive Plasma Instrumentation (CPU) for the 850 Geotail spacecraft. Technical Report. URL: https://ntrs.nasa.gov/ 851 api/citations/19960041496/downloads/19960041496.pdf.Friedman, J. H. (2002). Stochastic gradient boosting. Computational statis853 tics & data analysis, 38(4), 367–378. doi:https://doi.org/10.1016/ 854 S0167-9473(01)00065-2Garrard, T., Davis, A., Hammond, J. et al. (1998). The ace science center. 856 The Advanced Composition Explorer Mission, (pp. 649–663). doi:https: 857 //doi.org/10.1007/978-94-011-4762-0_23.Geurts, P., Ernst, D., & Wehenkel, L. (2006). Extremely randomized 859 trees. Machine learning, 63, 3–42. doi:https://doi.org/10.1007/ 860 s10994-006-6226-1.Gonzalez, W., Joselyn, J.-A., Kamide, Y. et al. (1994). What is a geomagnetic 862 storm? Journal of Geophysical Research: Space Physics, 99(A4), 5771– 863 5792. doi:https://doi.org/10.1029/93JA02867.Gonzalez, W. D., Echer, E., Tsurutani, B. T. et al. (2011). Interplan865 etary origin of intense, superintense and extreme geomagnetic storms. 866 Space science reviews, 158, 69–89. doi:https://doi.org/10.1007/ 867 s11214-010-9715-2Gonzalez, W. D., Tsurutani, B. T., & Clúa de Gonzalez, A. L. (1999). Inter869 planetary origin of geomagnetic storms. Space Science Reviews, 88(3-4), 870 529–562. doi:https://doi.org/10.1023/A:1005160129098Hady, A. (2009). Descriptive study of solar activity sudden increase 872 and halloween storms of 2003. Journal of atmospheric and solar873 terrestrial physics, 71(17-18), 1711–1716. doi:https://doi.org/10. 874 1016/j.jastp.2008.11.019.Hajra, R., Marques de Souza Franco, A., Echer, E. et al. (2021). Long876 term variations of the geomagnetic activity: A comparison between the 877 strong and weak solar activity cycles and implications for the space climate. 878 Journal of Geophysical Research: Space Physics, 126(4), e2020JA028695. 879 doi:https://doi.org/10.1029/2020JA0286950 Hall, C. M., & Johnsen, M. G. (2020). Possible influence of variations in the 881 geomagnetic field on migration paths of snow buntings. International Jour882 nal of Astrobiology, 19(2), 195–201. doi:https://doi.org/10.1017/ 883 S1473550419000193.Hastie, T., Tibshirani, R., Friedman, J. et al. (2009). Random forests. The 885 elements of statistical learning: Data mining, inference, and prediction, (pp. 886 587–604). doi:https://doi.org/10.1007/978-0-387-84858-7_15.Inyurt, S. (2020). Modeling and comparison of two geomagnetic storms. Ad888 vances in Space Research, 65(3), 966–977. doi:https://doi.org/10. 889 1016/j.asr.2019.11.004Ji, E.-Y., Moon, Y.-J., Gopalswamy, N. et al. (2012). Comparison of dst 891 forecast models for intense geomagnetic storms. Journal of Geophysi892 cal Research: Space Physics, 117(A3). doi:https://doi.org/10.1029/ 893 2011JA0168724 Kane, R. P. (2005). How good is the relationship of solar and interplane895 tary plasma parameters with geomagnetic storms? Journal of Geophysi896 cal Research: Space Physics, 110(A2). doi:https://doi.org/10.1029/ 897 2004JA010799.Kiznys, D., Vencloviene, J., & Milvidaite, I. (2020). The associations of ge- ˙ 899 omagnetic storms, fast solar wind, and stream interaction regions with car900 diovascular characteristic in patients with acute coronary syndrome. Life 901 Sciences in Space Research, 25, 1–8. doi:https://doi.org/10.1016/j. 902 lssr.2020.01.002Lakhina, G. S., & Tsurutani, B. T. (2016). Geomagnetic storms: historical 904 perspective to modern view. Geoscience Letters, 3, 1–11. doi:https:// 905 doi.org/10.1186/s40562-016-0037-4Le, G.-M., Cai, Z.-Y., Wang, H.-N. et al. (2013). Solar cycle distribution of 907 major geomagnetic storms. Research in Astronomy and Astrophysics, 13(6), 908 739. doi:https://doi.org/10.1088/1674-4527/13/6/013.Loewe, C., & Prölss, G. (1997). Classification and mean behavior of magnetic 910 storms. Journal of Geophysical Research: Space Physics, 102(A7), 14209– 911 14213. doi:https://doi.org/10.1029/96JA04020Lopez, R. E., Baker, D. N., & Allen, J. (2004). Sun unleashes halloween storm. Eos, Transactions American Geophysical Union, 85(11), 105–108. 913 doi:https://doi.org/10.1029/2004EO110002.Love, J. J., Rigler, E. J., Hartinger, M. D. et al. (2023). The march 1940 915 superstorm: Geoelectromagnetic hazards and impacts on american com- 916 munication and power systems. Space Weather, 21(6), e2022SW003379. 917 doi:https://doi.org/10.1029/2022SW003379Mandea, M., & Chambodut, A. (2020). Geomagnetic field processes and their 919 implications for space weather. Surveys in Geophysics, 41, 1611–1627. 920 doi:https://doi.org/10.1007/s10712-020-09598-1Miteva, R., Nedal, M., Samwel, S. W. et al. (2023). Parameter study of 922 geomagnetic storms and associated phenomena: Cme speed de-projection 923 vs. in situ data. Universe, 9(4), 179. doi:https://doi.org/10.3390/ 924 universe9040179Moore, J. H., Ribeiro, P. H., Matsumoto, N. et al. (2023). Genetic pro- 926 gramming as an innovation engine for automated machine learning: The 927 tree-based pipeline optimization tool (tpot). In Handbook of Evolutionary 928 Machine Learning (pp. 439–455). Springer. doi:https://doi.org/10. 929 1007/978-981-99-3814-8_14Natekin, A., & Knoll, A. (2013). Gradient boosting machines, a tutorial. Fron- 931 tiers in neurorobotics, 7, 21. doi:https://doi.org/10.3389/fnbot. 932 2013.00021.Nitta, N. V., Mulligan, T., Kilpua, E. K. et al. (2021). Understanding the ori- 934 gins of problem geomagnetic storms associated with “stealth” coronal mass 935 ejections. Space Science Reviews, 217(8), 82. doi:https://doi.org/10. 936 1007/s11214-021-00857-0Nti, I. K., Nyarko-Boateng, O., Aning, J. et al. (2021). Performance of machine 938 learning algorithms with different k values in k-fold cross-validation. Inter- 939 national Journal of Information Technology and Computer Science, 13(6), 940 61–71. doi:https://doi.org/10.5815/ijitcs.2021.06.05Ogilvie, K., & Desch, M. (1997). The wind spacecraft and its early scientific 942 results. Advances in Space Research, 20(4-5), 559–568. doi:https://doi. 943 org/10.1016/S0273-1177(97)00439-0Olson, R. S., & Moore, J. H. (2016). Tpot: A tree-based pipeline optimiza- 945 tion tool for automating machine learning. In Workshop on automatic ma- 946 chine learning (pp. 66–74). PMLR. doi:https://doi.org/10.1007/ 947 978-3-030-05318-5_8.Paularena, K., & King, J. (1999). Nasa’s imp 8 spacecraft. Interball in the ISTP 949 Program: Studies of the solar wind-magnetosphere-ionosphere interaction, 950 (pp. 145–154). doi:https://doi.org/10.1007/978-94-011-4487-2_ 951 11.Pedregosa, F., Varoquaux, G., Gramfort, A. et al. (2011). Scikit- 953 learn: Machine learning in python. the Journal of machine Learn- 954 ing research, 12, 2825–2830. URL: https://www.jmlr.org/papers/ 955 volume12/pedregosa11a/pedregosa11a.pdf?ref=https:/.Rathore, B., Kaushik, S., Bhadoria, R. et al. (2012). Sunspots and geomag- 957 netic storms during solar cycle-23. Indian Journal of Physics, 86, 563–567. 958 doi:https://doi.org/10.1007/s12648-012-0106-2.Reyes, P. I., Pinto, V. A., & Moya, P. S. (2021). Geomagnetic storm occur- 960 rence and their relation with solar cycle phases. Space Weather, 19(9), 961 e2021SW002766. doi:https://doi.org/10.1029/2021SW002766Richardson, I., Cliver, E., & Cane, H. (2001). Sources of geomagnetic storms 963 for solar minimum and maximum conditions during 1972–2000. Geo- 964 physical Research Letters, 28(13), 2569–2572. doi:https://doi.org/ 965 10.1029/2001GL013052.Samwel, S., & Miteva, R. (2023). Correlations between space weather pa- 967 rameters during intense geomagnetic storms: Analytical study. Advances in 968 Space Research, 72(8), 3440–3453. doi:https://doi.org/10.1016/j. 969 asr.2023.07.053Sarimov, R. M., Serov, D. A., & Gudkov, S. V. (2023). Biological effects of 971 magnetic storms and elf magnetic fields. Biology, 12(12), 1506. doi:https: 972 //doi.org/10.3390/biology12121506Schaffer, C. (1993). Selecting a classification method by cross- 974 validation. Machine learning, 13, 135–143. doi:https://doi.org/10. 975 1007/BF00993106Schapire, R. E. (2003). The boosting approach to machine learning: 977 An overview. Nonlinear estimation and classification, (pp. 149–171). 978 doi:https://doi.org/10.1007/978-0-387-21579-2_9Schmidt, R., Arends, H., Pedersen, A. et al. (1995). Results from active 980 spacecraft potential control on the geotail spacecraft. Journal of Geo- 981 physical Research: Space Physics, 100(A9), 17253–17259. doi:https: 982 //doi.org/10.1029/95JA01552.Singh Chauhan, D., Tiwari, D., Tripathi, A. et al. (2010). Association of large 985 geomagnetic storms with halo cmes and cirs observed during 1997–2007. 986 Indian Journal of Physics , 84, 881–886. doi:https://doi.org/10.1007/ 987 s12648-010-0052-9 .Siscoe, G., Crooker, N., & Clauer, C. (2006). Dst of the carrington storm of 989 1859. Advances in Space Research , 38(2), 173–179. doi:https://doi. 990 org/10.1016/j.asr.2005.02.102Srivastava, N., & Venkatakrishnan, P. (2002). Relationship between cme speed 992 and geomagnetic storm intensity. Geophysical research letters , 29(9), 1–1. 993 doi:https://doi.org/10.1029/2001GL013597Sugiura, M. (1960). The average morphology of geomagnetic stroms with sud995 den commencements. Abh. Akad. Wiss. Gottingen, Math.-phys., 53Taran, S., Alipour, N., Rokni, K. et al. (2023). E ffect of geomagnetic storms 997 on a power network at mid latitudes. Advances in Space Research , 71(12), 998 5453–5465. doi:https://doi.org/10.1016/j.asr.2023.02.027Tsurutani, B. T., Gonzalez, W. D., Gonzalez, A. L. et al. (1995). Interplane1000 tary origin of geomagnetic activity in the declining phase of the solar cycle. 1001 Journal of Geophysical Research: Space Physics , 100(A11), 21717–21733. 1002 doi:https://doi.org/10.1029/95JA01476Tsurutani, B. T., Gonzalez, W. D., Lakhina, G. et al. (2003). The extreme mag1004 netic storm of 1–2 september 1859. Journal of Geophysical Research: Space 1005 Physics , 108(A7). doi:https://doi.org/10.1029/2002JA009504Tsurutani, B. T., Gonzalez, W. D., Tang, F. et al. (1992). Great magnetic storms. 1007 Geophysical Research Letters , 19(1), 73–76. doi:https://doi.org/10. 1008 1029/91GL02783 .Verbanac, G., Vršnak, B., Veronig, A. et al. (2011). Equatorial coronal 1010 holes, solar wind high-speed streams, and their geoe ffectiveness. Astronomy 1011 & astrophysics , 526, A20. doi:https://doi.org/10.1051/0004-6361/ 1012 201014617 .Wilson III, L. B., Brosius, A. L., Gopalswamy, N. et al. (2021). A quar1014 ter century of wind spacecraft discoveries. Reviews of Geophysics, 59(2). 1015 doi:https://doi.org/10.1029/2020RG000714 .6 Yacouba, S., Somaïla, K., & Louis, Z. J. (2022). Factors of geomagnetic 1017 storms during the solar cycles 23 and 24: A comparative statistical study. 1018 Scientific Research and Essays , 17(3), 46–56. doi:https://doi.org/10. 1019 5897/SRE2022.6751Ying, C., Qi-Guang, M., Jia-Chen, L. et al. (2013). Advance and prospects of 1021 adaboost algorithm. Acta Automatica Sinica , 39(6), 745–758. doi:https: 1022 //doi.org/10.1016/S1874-1029(13)60052-X .Zhang, S., He, L., & Wu, L. (2020). Statistical study of loss of gps sig1024 nals caused by severe and great geomagnetic storms. Journal of Geo1025 physical Research: Space Physics, 125(9), e2019JA027749. doi:https: 1026 //doi.org/10.1029/2019JA027749 .http://purl.org/coar/resource_type/c_2df8fbb1ORIGINALGeomagneticStorms_regression_models (2).pdfGeomagneticStorms_regression_models (2).pdfapplication/pdf539206https://repositorio.utb.edu.co/bitstream/20.500.12585/12719/1/GeomagneticStorms_regression_models%20%282%29.pdf7e5140280f8dcc571e6b92895eab4f83MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8701https://repositorio.utb.edu.co/bitstream/20.500.12585/12719/2/license_rdf42fd4ad1e89814f5e4a476b409eb708cMD52LICENSElicense.txtlicense.txttext/plain; charset=utf-83182https://repositorio.utb.edu.co/bitstream/20.500.12585/12719/3/license.txte20ad307a1c5f3f25af9304a7a7c86b6MD53TEXTGeomagneticStorms_regression_models (2).pdf.txtGeomagneticStorms_regression_models (2).pdf.txtExtracted texttext/plain78294https://repositorio.utb.edu.co/bitstream/20.500.12585/12719/5/GeomagneticStorms_regression_models%20%282%29.pdf.txt9df784e3137f8a0388cd10412606e651MD55THUMBNAILGeomagneticStorms_regression_models (2).pdf.jpgGeomagneticStorms_regression_models (2).pdf.jpgGenerated Thumbnailimage/jpeg7955https://repositorio.utb.edu.co/bitstream/20.500.12585/12719/4/GeomagneticStorms_regression_models%20%282%29.pdf.jpg3c4c0ab7d1ebef5c4ff33334e769fc01MD5420.500.12585/12719oai:repositorio.utb.edu.co:20.500.12585/127192024-09-24 14:16:09.846Repositorio Institucional UTBrepositorioutb@utb.edu.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

Machine learning models for predicting geomagnetic storms across five solar cycles using Dst index and heliospheric variables

Publicaciones similares