Editorial Type:
Article
Article Type:
Research Article

A Machine Learning Model for Lightning-Related Deaths in Brazil

Daniela de Oliveira Maionchi aGraduate Program in Environmental Physics, Federal University of Mato Grosso (UFMT), Cuiabá, Mato Grosso, Brazil

Search for other papers by Daniela de Oliveira Maionchi in
Current site
Google Scholar
PubMed Close
,
Adriano Carvalho Nunes e Araújo aGraduate Program in Environmental Physics, Federal University of Mato Grosso (UFMT), Cuiabá, Mato Grosso, Brazil

Search for other papers by Adriano Carvalho Nunes e Araújo in
Current site
Google Scholar
PubMed Close
,
Walter Aguiar Martins Jr. aGraduate Program in Environmental Physics, Federal University of Mato Grosso (UFMT), Cuiabá, Mato Grosso, Brazil

Search for other papers by Walter Aguiar Martins Jr. in
Current site
Google Scholar
PubMed Close
,
Junior Gonçalves da Silva aGraduate Program in Environmental Physics, Federal University of Mato Grosso (UFMT), Cuiabá, Mato Grosso, Brazil
bGraduate Program in Physics, Institute of Physics, Federal University of Mato Grosso (UFMT), Cuiabá, Mato Grosso, Brazil

Search for other papers by Junior Gonçalves da Silva in
Current site
Google Scholar
PubMed Close
, and
Danilo Ferreira de Souza cInterdisciplinary Center for Energy Planning Studies (NIEPE), Federal University of Mato Grosso (UFMT), Cuiabá, Mato Grosso, Brazil

Search for other papers by Danilo Ferreira de Souza in
Current site
Google Scholar
PubMed Close
Online Publication:
17 Jan 2024
Print Publication:
01 Jan 2024
DOI:
https://doi.org/10.1175/WCAS-D-23-0084.1
Page(s):
117–127
Restricted access

Abstract

Brazil presents the highest number of lightning-related deaths in the world. This study aimed to identify the key victims’ characteristics associated with such fatalities in Brazil and to develop a model that predicts the number of deaths as function of the victims’ data. The dataset provided by the Department of Informatics of the Unified Health System in Brazil (DATASUS) was analyzed and machine learning regression techniques were applied. The gradien-boosting regressor (GBR) model was found to be the most effective, achieving a prediction accuracy of 97%. Through the analysis of 34 initial variables, 10 variables were identified as having the greatest influence on the model’s outcomes. These variables included race, gender, age group, occupational accidents, education, and location of death. Understanding these characteristics is crucial for implementing targeted prevention and safety strategies in various regions, helping to mitigate the risk of lightning-related deaths worldwide. Additionally, the methodology used in this study can serve as a framework for similar research in different locations, allowing for the identification of important factors specific to each region. By adapting the machine learning regression techniques and incorporating local datasets, researchers can gain valuable insights into the determinants of lightning-related fatalities, enabling the development of effective prevention and safety measures tailored to specific geographical areas.

Significance Statement

This study presents a machine learning approach using the gradient-boosting regressor (GBR) method to estimate the weekly number of lightning-related deaths with an impressive 97% prediction accuracy. The research includes a comprehensive analysis of various factors, such as race, gender, age group, occupational accidents, education, and location of death, providing valuable insights for targeted preventive strategies and safety measures. The findings significantly contribute to understanding lightning-related fatalities in Brazil. The proposed machine learning model demonstrates a robust and accurate fit to the data, allowing for a comprehensive understanding of patterns and underlying trends in lightning fatalities.

De Souzas’s current affiliation: Institute of Energy and Environment, University of São Paulo, São Paulo, São Paulo, Brazil.

© 2024 American Meteorological Society. This published article is licensed under the terms of the default AMS reuse license. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Daniela de Oliveira Maionchi, dmaionchi@fisica.ufmt.br

Abstract

Brazil presents the highest number of lightning-related deaths in the world. This study aimed to identify the key victims’ characteristics associated with such fatalities in Brazil and to develop a model that predicts the number of deaths as function of the victims’ data. The dataset provided by the Department of Informatics of the Unified Health System in Brazil (DATASUS) was analyzed and machine learning regression techniques were applied. The gradien-boosting regressor (GBR) model was found to be the most effective, achieving a prediction accuracy of 97%. Through the analysis of 34 initial variables, 10 variables were identified as having the greatest influence on the model’s outcomes. These variables included race, gender, age group, occupational accidents, education, and location of death. Understanding these characteristics is crucial for implementing targeted prevention and safety strategies in various regions, helping to mitigate the risk of lightning-related deaths worldwide. Additionally, the methodology used in this study can serve as a framework for similar research in different locations, allowing for the identification of important factors specific to each region. By adapting the machine learning regression techniques and incorporating local datasets, researchers can gain valuable insights into the determinants of lightning-related fatalities, enabling the development of effective prevention and safety measures tailored to specific geographical areas.

Significance Statement

This study presents a machine learning approach using the gradient-boosting regressor (GBR) method to estimate the weekly number of lightning-related deaths with an impressive 97% prediction accuracy. The research includes a comprehensive analysis of various factors, such as race, gender, age group, occupational accidents, education, and location of death, providing valuable insights for targeted preventive strategies and safety measures. The findings significantly contribute to understanding lightning-related fatalities in Brazil. The proposed machine learning model demonstrates a robust and accurate fit to the data, allowing for a comprehensive understanding of patterns and underlying trends in lightning fatalities.

De Souzas’s current affiliation: Institute of Energy and Environment, University of São Paulo, São Paulo, São Paulo, Brazil.

© 2024 American Meteorological Society. This published article is licensed under the terms of the default AMS reuse license. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).

Corresponding author: Daniela de Oliveira Maionchi, dmaionchi@fisica.ufmt.br
Save
Cover Weather, Climate, and Society
Weather, Climate, and Society

  • Anderson, R. B., 2001: Does a fifth mechanism exist to explain lightning injuries? IEEE Eng. Med. Biol. Mag., 20, 105–113, https://doi.org/10.1109/MEMB.2001.897833.

    • Search Google Scholar
    • Export Citation

  • Andrews, C. J., 1992: Telephone-related lightning injury. Med. J. Aust., 157, 823–826, https://doi.org/10.5694/j.1326-5377.1992.tb141300.x.

    • Search Google Scholar
    • Export Citation

  • Badoux, A., N. Andres, F. Techel, and C. Hegg, 2016: Natural hazard fatalities in Switzerland from 1946 to 2015. Nat. Hazards Earth Syst. Sci., 16, 2747–2768, https://doi.org/10.5194/nhess-16-2747-2016.

    • Search Google Scholar
    • Export Citation

  • Balch, J. K., B. A. Bradley, J. T. Abatzoglou, R. C. Nagy, E. J. Fusco, and A. L. Mahood, 2017: Human-started wildfires expand the fire niche across the United States. Proc. Natl. Acad. Sci. USA, 114, 2946–2951, https://doi.org/10.1073/pnas.1617394114.

    • Search Google Scholar
    • Export Citation

  • Bier, M., W. Chen, E. Bodnar, and R. C. Lee, 2005: Biophysical injury mechanisms associated with lightning injury. NeuroRehabilitation, 20, 53–62.

    • Search Google Scholar
    • Export Citation

  • Boser, B. E., I. M. Guyon, and V. N. Vapnik, 1992: A training algorithm for optimal margin classifier. Proc. Fifth Annual ACM Workshop on Computational Learning Theory, Pittsburgh, PA, Association for Computing Machinery, 144–152, https://doi.org/10.1145/130385.130401.

  • Breiman, L., 2001: Random forests. Mach. Learn., 45, 5–32, https://doi.org/10.1023/A:1010933404324.

  • Cardoso, I., O. Pinto Jr., I. R. C. A. Pinto, and R. Holle, 2014: Lightning casualty demographics in Brazil and their implications for safety rules. Atmos. Res., 135–136, 374–379, https://doi.org/10.1016/j.atmosres.2012.12.006.

    • Search Google Scholar
    • Export Citation

  • Cooper, M. A., 2012: Whether the medical aspects of lightning injury are different in developing countries. 2012 Int. Conf. on Lightning Protection (ICLP), Vienna, Austria, Institute of Electrical and Electronics Engineers, 1–6, https://doi.org/10.1109/ICLP.2012.6344288.

  • Cooper, M. A., and R. L. Holle, 2019: Reducing Lightning Injuries Worldwide. Springer, 233 pp., https://doi.org/10.1007/978-3-319-77563-0.

  • de Azevedo Couto, G., A. Sanchez, R. C. dos Santos Alvalá, and C. A. Nobre, 2023: Natural hazards fatalities in Brazil, 1979–2019. Nat. Hazards, 118, 1487–1514, https://doi.org/10.1007/s11069-023-06059-x.

    • Search Google Scholar
    • Export Citation

  • de Oliveira Maionchi, D., L. Ainstein, F. P. dos Santos, and M. B. de Souza Jr., 2022: Computational fluid dynamics and machine learning as tools for optimization of micromixers geometry. Int. J. Heat Mass Transfer, 194, 123110, https://doi.org/10.1016/j.ijheatmasstransfer.2022.123110.

    • Search Google Scholar
    • Export Citation

  • de Souza, D. F., H. E. Sueta, H. Tatizawa, W. A. Martins Jr., and E. Martinho, 2022: An analysis of lightning deaths in Brazil 2010–2020. 2022 36th Int. Conf. on Lightning Protection (ICLP), Cape Town, South Africa, Institute of Electrical and Electronics Engineers, 643–647, https://doi.org/10.1109/ICLP56858.2022.9942657.

  • Friedman, J., 2000: Greedy function approximation: A gradient boosting machine. Ann. Stat., 29, 1189–1232, https://doi.org/10.1214/aos/1013203451.

    • Search Google Scholar
    • Export Citation

  • Füllekrug, M., 2021: Global lightning quanta. J. Geophys. Res. Atmos., 126, e2020JD033201, https://doi.org/10.1029/2020JD033201.

  • Gatewood, M. O., and R. D. Zane, 2004: Lightning injuries. Emerg. Med. Clin. North Amer., 22, 369–403, https://doi.org/10.1016/j.emc.2004.02.002.

    • Search Google Scholar
    • Export Citation

  • Holle, R. L., 2016: A summary of recent national-scale lightning fatality studies. Wea. Climate Soc., 8, 35–42, https://doi.org/10.1175/WCAS-D-15-0032.1.

    • Search Google Scholar
    • Export Citation

  • Jitsuiki, K., K.-i. Muramatsu, S.-i. Shoda, and Y. Yanagawa, 2020: Lightning injury caused by a side flash. Amer. J. Med. Case Rep., 8, 538–540, https://doi.org/10.12691/ajmcr-8-12-29.

    • Search Google Scholar
    • Export Citation

  • Mishra, M., T. Acharyya, C. A. G. Santos, R. M. da Silva, P. Chand, D. Bhattacharyya, S. Srivastava, and O. Singh, 2022: Mapping main risk areas of lightning fatalities between 2000 and 2020 over Odisha state (India): A diagnostic approach to reduce lightning fatalities using statistical and spatiotemporal analyses. Int. J. Disaster Risk Reduct., 79, 103145, https://doi.org/10.1016/j.ijdrr.2022.103145.

    • Search Google Scholar
    • Export Citation

  • Nwokolo, S. C., N. Proutsos, E. L. Meyer, and C. C. Ahia, 2023: Machine learning and physics-based hybridization models for evaluation of the effects of climate change and urban expansion on photosynthetically active radiation. Atmosphere, 14, 687, https://doi.org/10.3390/atmos14040687.

    • Search Google Scholar
    • Export Citation

  • Qiu, W., H. Chen, A. B. Dincer, S. Lundberg, M. Kaeberlein, and S.-I. Lee, 2022: Interpretable machine learning prediction of all-cause mortality. Commun. Med., 2, 125, https://doi.org/10.1038/s43856-022-00180-x.

    • Search Google Scholar
    • Export Citation

  • Queiroz, L. H., F. P. Santos, J. P. Oliveira, and M. B. Souza Jr., 2021: Physics-informed deep learning to predict flow fields in cyclone separators. Digital Chem. Eng., 1, 100002, https://doi.org/10.1016/j.dche.2021.100002.

    • Search Google Scholar
    • Export Citation

  • Ritenour, A. E., M. J. Morton, J. G. McManus, D. J. Barillo, and L. C. Cancio, 2008: Lightning injury: A review. Burns, 34, 585–594, https://doi.org/10.1016/j.burns.2007.11.006.

    • Search Google Scholar
    • Export Citation

  • Roman-Pognuz, E., and Coauthors, 2022: Neuronal desertification after a direct lightning strike: A case report. J. Med. Case Rep., 16, 391, https://doi.org/10.1186/s13256-022-03500-w.

    • Search Google Scholar
    • Export Citation

  • Rumelhart, D. E., G. E. Hinton, and R. J. Williams, 1986: Learning representations by back propagating errors. Nature, 323, 533–536, https://doi.org/10.1038/323533a0.

    • Search Google Scholar
    • Export Citation
All Time Past Year Past 30 Days
Abstract Views 583 583 28
Full Text Views 169 169 0
PDF Downloads 178 178 0