A Machine Learning Model for Lightning-Related Deaths in Brazil
Bibliographic Data
| ID | 22332117 |
|---|---|
| Authors | Daniela de Oliveira Maionchi (Universidade Federal de Mato Grosso), Adriano Carvalho Nunes e Araújo (Universidade Federal de Mato Grosso), Walter Aguiar Martins (Universidade Federal de Mato Grosso), Junior Gonçalves da Silva (Universidade Federal de Mato Grosso), Danilo Ferreira De Souza (0000-0002-1155-1778, Universidade Federal de Mato Grosso) |
| Year | 2024 |
| Volume | 16 |
| Issue | 1 |
| Pages | 117-127 |
| Publication date | 2024-01-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Weather, Climate, and Society (JOURNAL) |
| Journal identifiers | ISSN: 1948-8327 • E-ISSN: 1948-8335 |
| Publisher | American Meteorological Society (PUBLISHER • US) |
| DOI | 10.1175/wcas-d-23-0084.1 |
| OpenAlex | W4389992005 |
| Language | EN |
| References cited | 6 |
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
Physics · Computer Science · Fire Detection and Safety Systems
Learning representations by back-propagating errors
Human-started wildfires expand the fire niche across the United States
Greedy function approximation
Random Forests
A Summary of Recent National-Scale Lightning Fatality Studies
Mapping main risk areas of lightning fatalities between 2000 and 2020 over Odisha state (India)
| Highly cited | No |
|---|