Sentinel-2 image analysis in mapping forest formations in the municipality of Uberaba-MG

Authors

DOI:

https://doi.org/10.14808/sci.plena.2023.129901

Keywords:

Random Forest, Google Earth Engine, MapBiomas

Abstract

Deforestation of native forests has been the focus of discussions around the world due to the negative impact provided in various sectors, such as agriculture, water supply, climate change, among others. The use of satellite mapping technologies is crucial for monitoring deforestation and its causes, enabling more effective actions in forest protection. The objective of this study was to analyze the use of images from the Sentinel-2 satellite to map forest formations in Uberaba, Minas Gerais. For this, we used the processing of data in the cloud from Google Earth Engine (GEE). Supervised classification of images between 2016 and 2019 was performed using the Random forest algorithm. The results were compared with MapBiomas data, as it is the most consolidated mapping project on a national scale. The results show that the area occupied by forest formations is equivalent, on average, to 12.22% of the total area of the municipality. When comparing the results obtained in the present study with MapBiomas, it is noted that there was similarity between the two mappings in most of the study area Sentinel-2 images were effective in mapping forest formations and data processing in GEE made the process faster.

Author Biographies

Alex Garcez Utsumi, UFTM

He has a degree in Environmental Engineering and a master's degree in Cartographic Sciences
from the São Paulo State University "Júlio de Mesquita Filho", Presidente Prudente campus.
PhD in Agronomy from the Faculty of Agricultural and Veterinary Sciences -UNESP, Jaboticabal.
He is currently an Adjunct Professor at the Federal University of Triângulo Mineiro - UFTM,
linked to the Environmental Engineering department. He has experience in the areas of
Geographic Information Systems, Cartography and Remote Sensing, working mainly in the
diagnosis of river basins through digital image processing.

Nubya Martins de Almeida Oliveira, Universidade Federal do Triângulo Mineiro

Degree in progress in Environmental Engineering. Federal University of Triângulo Mineiro, UFTM, Brazil.

Nadia Guimarães Sousa, Universidade Federal do Triângulo Mineiro

Graduated in Chemical Engineering from the Federal University of Uberlândia (2008).
Master's degree in Chemical Engineering from the Federal University of Uberlândia (2010)
with an emphasis on fault propagation and a PhD in Chemical Engineering from the same
institution (2015) with an emphasis on fault-tolerant control by control allocation. She
has experience in the area of ​​Modeling, Simulation, Optimization and Control of
Chemical Processes. He is currently a professor at the Federal University of Triângulo
Mineiro in the Chemical Engineering course.

Downloads

Published

2024-01-19

How to Cite

Garcez Utsumi, A., Martins de Almeida Oliveira, N., & Guimarães Sousa, N. (2024). Sentinel-2 image analysis in mapping forest formations in the municipality of Uberaba-MG. Scientia Plena, 19(12). https://doi.org/10.14808/sci.plena.2023.129901

Issue

Vol. 19 No. 12 (2023): Dezembro/December 2023

Section

Articles

License

Copyright (c) 2024 Alex Garcez Utsumi, Nubya Martins de Almeida Oliveira, Nadia Guimarães Sousa

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work