Análise da evolução do desmatamento no bioma Cerrado no estado de Minas Gerais utilizando sistemas de detecção e imagens orbitais gratuitas

Abstract

The Cerrado is considered the second largest biome in Brazil, covering an area of more than 200 million hectares in thirteen states of the Federation. This is an area of great importance for the biodiversity of Brazilian fauna and flora. However, the transformation of its vegetation has been accelerated in recent years, mainly due to the need to expand new areas for agricultural production and the formation of pastures. In the specific case of the State of Minas Gerais, the Cerrado Biome occupies more than 54% of the territory and runs through regions of great importance for agricultural productivity. Therefore, this work proposes a qualitative assessment of thematic mapping based on the supervised classification of free orbital images (generated by the Brazilian satellite Amazônia-1), as a viable strategy for understanding the evolution of land use and land cover changes. Deforestation polygon alerts generated by the Real Time Deforestation Detection System of the National Institute for Space Research are also analyzed, as well as the application of machine learning algorithms and techniques (Machine Learning) that can guarantee the availability of this information with greater speed and reliability. The results achieved with the processing of the images demonstrated a great viability for the use of the used methodologies.