Detecção em tempo real de desflorestamentos na Amazônia com uso de dados MODIS/TERRA e redes neurais

AUTOR(ES)
DATA DE PUBLICAÇÃO

2007

RESUMO

- This research aims to show a methodology for real-time monitoring of new deforestation caused by clearcutting of forested areas in the Brazilian Amazon. A part of Rondonia State was chosen as the study area in the period of time from May 20 to July 15, 2003, nearly two months, where new deforestations were mapped and analysed. Due to the availability of Terra- MODIS data, with high repetitiveness and moderate spatial resolution, and the possibility to employ Computational Intelligence techniques for land-cover change detection, the methodology proposed here is based on the integration of multitemporal data and an artificial neural net for the real-time monitoring of new deforestations. A Multi-Layer Perceptron with Backpropagation algorithm was employed to evaluate the quality of variable used as indicator for deforestation alarm generation. The main contribution of this research is on the production of mechanisms that may help automate alarm systems, also understand temporal profiles (dynamic) of new deforestations in the region.

ASSUNTO(S)

deforestation neural networks sensor modis/terra modis/terra sensor redes neurais amazon (region) porto velho (city) desmatamento amazônia porto velho

ACESSO AO ARTIGO

Documentos Relacionados