COMBINING TIME SERIES FEATURES AND DATA MINING TO DETECT LAND COVER PATTERNS: A CASE STUDY IN NORTHERN MATO GROSSO STATE, BRAZIL

Conteúdo do artigo principal

Alana Kasahara Neves
Hugo do Nascimento Bendini
Thales Sehn Korting
Leila Maria Garcia Fonseca

Resumo

One product of the MODIS sensor (Moderate Resolution Imaging Spectroradiometer) is the EVI2 (Two Band Enhanced Vegetation Index). It generates images of around 23 observations each year, that combined can be interpreted as time series. This work presents the results of using two types of features obtained from EVI2 time series: basic and polar features. Such features were employed in automatic classiï¬ cation for land cover mapping, and we compared the infl uence of using single pixel versus object-based observations. The features were used to generate classiï¬ cation models using the Random Forest algorithm. Classes of interest included Agricultural Area, Pasture and Forest. Results achieved accuracies up to 91,70% for the northern region of Mato Grosso state, Brazil.

Downloads

Não há dados estatísticos.

Métricas

Carregando Métricas ...

Detalhes do artigo

Como Citar
NEVES, A. K.; BENDINI, H. do N.; KORTING, T. S.; FONSECA, L. M. G. COMBINING TIME SERIES FEATURES AND DATA MINING TO DETECT LAND COVER PATTERNS: A CASE STUDY IN NORTHERN MATO GROSSO STATE, BRAZIL. Revista Brasileira de Cartografia, [S. l.], v. 68, n. 6, 2018. DOI: 10.14393/rbcv68n6-44488. Disponível em: https://seer.ufu.br/index.php/revistabrasileiracartografia/article/view/44488. Acesso em: 20 jul. 2024.
Seção
Artigos

Artigos mais lidos pelo mesmo(s) autor(es)

1 2 > >>