A Machine Learning Model for Lightning-Related Deaths in Brazil

Abstract

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.