Spatio-temporal modelling and hierarchical time series forecasting of the Brazilian wildfires

Abstract

Wildfires are among the most common natural disasters in many world regions and actively impact life quality. These events have become frequent due to climate change, other local policies, and human behaviour. In this talk, I consider the historical data with the geographical locations of all the "fire spots" detected by the reference satellites covering the Brazilian territory between January 2011 and December 2022, comprising more than 2.2 million fire spots. First, I will show the results of a spatio-temporal generalized linear model for areal unit data, whose inferences about its parameters are made in a Bayesian approach and use meteorological variables (precipitation, air temperature, humidity, and wind speed) and a human variable (land-use transition and occupation) as covariates. Then, I will present the results for the hierarchical time series forecasting where the six Brazilian biomes and the 5570 municipalities form the hierarchy. (Joint work with Jonatha Pimentel, Rodrigo Bulhões, and Ana Pinheiro)