EVALUATION OF DEFORESTATION IN THE MUNICIPALITY OF BRASIL NOVO IN THE STATE OF PARÁ - BRAZIL, USING MACHINE LEARNING TECHNIQUES

DOI: https://doi.org/10.4215/rm2024.e23029

Abstract

The agricultural frontier of the Brazilian Amazon, is undergoing significant changes in its land cover, primarily driven by the expansion of cattle ranching and cocoa cultivation. Through the analysis of Landsat 8 satellite images and the WorldCover 10m 2020 product, combined with climatic and socioeconomic data, this study investigated land use dynamics between 2015 and 2023, on the municipality of Brasil Novo. The results revealed a substantial reduction in forest cover, with the expansion of pasturelands as the main driver of deforestation. The temporal analysis of the Normalized Difference Vegetation Index (NDVI) indicated interannual variations in vegetation cover, associated with extreme weather events and anthropogenic pressure. Although the municipality still maintains 43.8% of forest cover, with the Arara Indigenous Land being a notable example, the pressure on natural resources demands the implementation of public policies and sustainable management practices to mitigate environmental impacts and ensure the conservation of Amazonian biodiversity.

Keywords: Amazon, NDVI, remote sensing, climate change, livestock, land use.

Author Biographies

Victor Tiago da Silva Catuxo, Federal University of Pará, Belém (PA), Brazil

PhD student in Animal Science. Engineer with experience in the management and implementation of sustainable projects in the Amazon. Extensive experience and knowledge in fishing, aquaculture and forestry resources. Manager of social projects involving traditional, extractive and fishing communities in the Amazon and the Brazilian coastal zone. Currently coordinator of the Sustainable Territory Fomento program developed by the Secretariat for Agricultural and Fisheries Development (SEDAP). Experience in BIM (Building Information Modeling), CAD (Computer Aided Design) and GIS (Geographic Information System) projects. Knowledge of Python and R for Environmental and Social Data Analysis.

Marlene Evangelista Vieira, Amapá State University, Macapá (AP), Brazil

PhD in Plant Production (Soils and Plant Nutrition) from the Darcy Ribeiro State University of Northern Fluminense (2017/2021. She is currently an Assistant Professor I at the State University of Amapá, on the Agricultural Engineering Board, EAG-06 of the course (2024). Researcher/Scholarship holder of the Executive Committee of the Cocoa Crop Plan (2024), in-person tutor - National Rural Learning Service (2022/2024). Agricultural Technician/Agronomist at the State Secretariat for Agricultural Development and Fisheries of Pará. She has experience in the area of ​​Agronomy, working mainly on the following topics: Soil management, Integrated cropping systems, Mineral nutrition of plants, agricultural production, consumption and food security.

Carolina da Silva Gonçalves, Federal Institute of Amapá, Macapá (AP), Brazil

PhD student in Geography at the Federal University of Pará. She worked as a CAPES scholarship holder for the Legal Amazon Program in the Coastal Zone Observatory Project. She holds a degree in Cartographic and Surveying Engineering from the Rural University of the Amazon, and worked as a monitor for Sociology and Rural Extension. She is a member of the GERAM research group - Research Group on Gender Relations and Ruralities in the Amazon; and of the Cabanagem Green Law Academic League at the Center for Traditional Communities and Peoples. She is currently a Substitute Professor at the Federal Rural University of the Amazon and a Councilor for the Regional Council of Engineering and Agronomy. She has experience in Remote Sensing and Geoprocessing.

References

ALI AROOJ, S. et al. Monitoring of Afforestation Activities Using Landsat-8 Temporal Images, Billion Trees Afforestation Project, Pakistan. Nova mehanizacija šumarstva, v. 42, p. 27–40, 20 dez. 2021.
BENZOUGAGH, B. et al. Mapping of land degradation using spectral angle mapper approach (SAM): the case of Inaouene watershed (Northeast Morocco). Modeling Earth Systems and Environment, v. 10, n. 1, p. 221–231, fev. 2024.
BEZERRA, D. et al. Avaliação dos atributos químicos do solo em sistemas agroflorestais e pastagem, no município de Brasil Novo - Pará. Agrarian Academy, v. 5, n. 9, 31 jul. 2018.
CASTELO, T. B.; ADAMI, M.; SANTOS, R. B. N. DOS. Fronteira Agrícola e a política de priorização dos municípios no combate ao desmatamento no estado do Pará, Amazônia. Estudos Sociedade e Agricultura, v. 28, n. 2, p. 434, 1 jun. 2020.
CÔRTES, J. C.; D’ANTONA, Á. DE O.; PERZ, S. Extended families and demographic explanations for land use-cover change in the Brazilian Amazon. Population and Environment, v. 46, n. 1, p. 4, mar. 2024.
FOLHES, R. T.; SERRA, A. B. Os efeitos da concorrência de trajetórias tecnológicas na economia cacaueira paraense sobre as promessas de sustentabilidade do setor: um estudo a partir da transamazônica, Pará, Brasil. v. 1, 2023.
FURUSAWA, T. et al. Time-series analysis of satellite imagery for detecting vegetation cover changes in Indonesia. Scientific Reports, v. 13, n. 1, p. 8437, 25 maio 2023.
GUTIERREZ-CORI, O. et al. On the Hydroclimate-Vegetation Relationship in the Southwestern Amazon During the 2000–2019 Period. Frontiers in Water, v. 3, p. 648499, 24 mar. 2021.
HUNTER, J. D. Matplotlib: A 2D graphics environment. Computing in Science & amp: Engineering, v. 9, p. 90–95, 2007.
JORDAHL, K. GeoPandas: Python tools for geographic data. , 2014. Disponível em:
LIU, B. et al. A Comparison of Six Forest Mapping Products in Southeast Asia, Aided by Field Validation Data. Remote Sensing, v. 15, n. 18, p. 4584, 18 set. 2023.
LUZ, G. G.; GALVINCIO, J. D. Dinâmica do Uso do Solo, Balanço hídrico e NDVI no município de Floresta-Pernambuco, Brasil. Revista Brasileira de Geografia Física, v. 16, n. 5, p. 2898–2909, 30 out. 2023.
MACHADO, N. G. et al. Effects of deforestation on microclimate in a Cerrado-Amazonia Transition area. Ciência Florestal, v. 33, n. 2, p. e70199, 21 jun. 2023.
MCKINNEY, W. Data Structures for Statistical Computing in Python. . Em: PYTHON IN SCIENCE CONFERENCE. Austin, Texas: 2010. Disponível em: . Acesso em: 22 ago. 2024
MENDES, J. S. R. Desígnios da lei de terras: imigração, escravismo e propriedade fundiária no Brasil Império. Caderno CRH, v. 22, n. 55, p. 173–184, jan. 2009.
NASCIMENTO, D. R. D.; ALVES, L. N.; SOUZA, M. L. Implantação de sistemas agroflorestais para a recuperação de áreas de preservação permanente em propriedades familiares rurais da região da Transamazônica, Pará. Agricultura Familiar: Pesquisa, Formação e Desenvolvimento, v. 13, n. 2, p. 103, dez. 2019.
OLUWAJUWON, T. V. et al. Forest Cover Dynamics of a Lowland Rainforest in Southwestern Nigeria Using GIS and Remote Sensing Techniques. Journal of Geographic Information System, v. 13, n. 02, p. 83–97, 2021.
OTHMAN, M. A. et al. Tropical deforestation monitoring using NDVI from MODIS satellite: a case study in Pahang, Malaysia. IOP Conference Series: Earth and Environmental Science, v. 169, p. 012047, 31 jul. 2018.
PEDREGOSA, F. et al. Scikit-learn: Machine Learning in Python. MACHINE LEARNING IN PYTHON, 2011.
PELLENZ, J. DE L. DA V.; ALMEIDA, M. DE; LIRIO, V. S. Eficiência técnica agropecuária e desmatamento: análise espacial para a Amazônia legal brasileira. Estudios económicos, v. 38, n. 77, p. 119–146, 3 maio 2021.
PEREIRA, R. H. M.; GONCALVES, C. N. geobr: Download Official Spatial Data Sets of Brazil. R package version 1.9.0. , 18 abr. 2024. Disponível em:
QIN, Y. et al. Annual maps of forest cover in the Brazilian Amazon from analyses of PALSAR and MODIS images. Earth System Science Data, v. 16, n. 1, p. 321–336, 15 jan. 2024.
ROSÁRIO, R. R. D. et al. Uso e ocupação do solo do município de novo progresso no Estado do Pará-Brasil. Research, Society and Development, v. 10, n. 1, p. e51210112060, 28 jan. 2021.
WASKOM, M. et al. mwaskom/seaborn: v0.8.1 (setembro de 2017) [Internet]. Zenodo, 2017.
WASSER, L. et al. EarthPy: A Python package that makes it easier to explore and plot raster and vector data using open source Python tools. Journal of Open Source Software, v. 4, n. 43, p. 1886, 13 nov. 2019.
WATRIN, O. D. S. et al. Dinâmica do uso e cobertura da terra em Projeto de Desenvolvimento Sustentável na região da rodovia Transamazônica, Pará. Sociedade & Natureza, v. 32, p. 92–107, 17 fev. 2020.
WU, Q. geemap: A Python package for interactive mapping with Google Earth Engine. Journal of Open Source Software, v. 5, n. 51, 15 jun. 2020.
Published
27/10/2024
How to Cite
CATUXO, Victor Tiago da Silva; VIEIRA, Marlene Evangelista; GONÇALVES, Carolina da Silva. EVALUATION OF DEFORESTATION IN THE MUNICIPALITY OF BRASIL NOVO IN THE STATE OF PARÁ - BRAZIL, USING MACHINE LEARNING TECHNIQUES. Mercator, Fortaleza, v. 23, oct. 2024. ISSN 1984-2201. Available at: <http://www.mercator.ufc.br/mercator/article/view/e23029>. Date accessed: 26 jan. 2025. doi: https://doi.org/10.4215/rm2024.e23029.
Citation Formats
Issue
Vol 23 (2024)
Section
ARTICLES

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

  1. Authors retain the copyright and grant MERCATOR the right of first publication, with the work simultaneously licensed under the Creative Commons Attribution License, which allows the sharing of the work with recognition of the authorship of the work and initial publication in this journal.
  2. Authors are authorized to sign additional contracts separately, for non-exclusive distribution of the version of the work published in this journal (e.g., publish in an institutional repository or as a book chapter), with acknowledgment of authorship and initial publication in this journal.
  3. Authors are allowed and encouraged to publish and distribute their work online (e.g., in institutional repositories or on their personal page) at any point before or during the editorial process, as this can generate productive changes as well as increase the impact and citation of the published work (see The Effect of Free Access).
  4. Authors are responsible for the content of the manuscript published in the journal.