RSDD: um Conjunto de Dados para Modelagem de Desmatamentos

• Rosangela Maria Guarienti Ventura UFMT / POLITEC
• Carlo Ralph de Musis UFMT / POLITEC
• Thiago Meirelles Ventura UFMT
• Adriano Marcelo Vilarga Corbelino II UFMT

DOI: https://doi.org/10.5753/wcama.2023.230675

Abstract

It is common to use remote sensing to understand the dynamics of deforestation. However, obtaining and processing these images is not a trivial task, besides to the difficulty of having validated deforestation areas. To solve this problem, this work presents the Remote Sensing Deforestation Dataset (RSDD) containing tabulated data and images of areas affected by deforestation validated by a state agency. RSDD has a size less than 1% related to the original remote sensing images, provides a reduction in efforts in future research and can serve as a common dataset to be used as benchmark for machine learning solutions.

References

Bayma, A. P. and Sano, E. E. (2015). Séries temporais de índices de vegetação (ndvi e evi) do sensor modis para detecção de desmatamentos no bioma cerrado, Boletim de Ciências Geodésicas 21(4): 797–813.

Dias, A., Silva, K. L., Souza, L. G., Perdigão, R. J., Bilio, H., C., O. H. H. and Kummer, O. P. (2018). Análise dos dados de desmatamento do estado de mato grosso: Período 2016/2017, Relatório Técnico 003/2018/CGMA/SRMA/SAGA/SEMA-M, Secretaria de Estado do Meio Ambiente de Mato Grosso (SEMA-MT), Mato Grosso, Brasil.

ESA (2023). Sentinel-2 Mission. Available at https://sentinel.esa.int/web/sentinel/missions/sentinel-2.

Maurano, L., Escada, M. and Renno, C. (2019). Padrões espaciais de desmatamento e a estimativa da exatidão dos mapas do prodes para amazônia legal brasileira, Ciência Florestal 29(4): 1763–1775.

Zhu, Z., Wang, S. and Woodcock, C. E. (2015). Improvement and expansion of the fmask algorithm: cloud, cloud shadow, and snow detection for landsats 4–7, 8, and sentinel 2 images, Remote Sensing of Environment 159: 269–277.