Predictive Analysis of Fire Occurrences and Air Quality in the State of São Paulo: A Machine Learning-Driven Approach

• Grant number: 25/02582-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2025
• End date: April 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Wallace Correa de Oliveira Casaca
• Grantee: Guilherme Henrique Guimarães da Silva
• Host Institution: Instituto de Biociências, Letras e Ciências Exatas (IBILCE). Universidade Estadual Paulista (UNESP). Campus de São José do Rio Preto. São José do Rio Preto , SP, Brazil

Abstract

This scientific initiation project aims to investigate the relationship between wildfires and air quality in the state of São Paulo, by using Exploratory Data Analysis and Machine Learning techniques. The main goal is to identify the variables that most impact the variation in the Air Quality Index (IQAr), as well as to perform predictive analysis of pollutant levels and meteorological variables on the IQAr. This research will seek to build predictive models based on historical wildfire data, meteorological variables, and environmental conditions. Our analysis will focus on understanding how factors such as the number of fire hotspots, drought intensity, and meteorological conditions affect air quality in different regions of the São Paulo state, as well as exploring predictive techniques that can anticipate critical events. It is expected that the outcomes of this study contribute to reducing the impact on air quality, with a direct reflection on public health, especially in regions vulnerable to wildfires.