Metodologia para Avaliação do Impacto de Eventos (Epidemias e Desastres) por Machine Learning : Estudo de caso da Barragem de Fundão

Abstract

This article proposes a new method for assessing the impact of an event, such as epidemics, natural and technological disasters, in a given set of places. The proposed method uses machine learning techniques and statistical tools to investigate effects of the event, in one or more variables, through different angles. Four distinct analyses are performed, three monovariate (descriptive analysis; Resultant Vectors Graph; and statistical comparison through paired t tests) and one multivariate analysis through Fuzzy c-means clustering algorithm. The proposed method is applied in a case study: the Fund˜ao dam failure in Mariana – MG. This event is investigated with respect to “Number of dengue fever cases” and “GDP” variables. This new method managed to identify the impact, or its absence, in the observed counties after the event. The main results indicated that Mariana and Conselheiro Pena suffered an increase in dengue fever cases level in almost all analysis.