%0 Conference Proceedings
%4 sid.inpe.br/marte2/2017/10.27.15.35
%2 sid.inpe.br/marte2/2017/10.27.15.35.03
%@isbn 978-85-17-00088-1
%F 59339
%T Avaliação do mapeamento das lavouras de soja em Mato Grosso na safra 2010/2011 realizado pelo projeto Soja Sat
%D 2017
%A Chaves, Michel Eustáquio Dantas,
%A Alves, Marcelo de Carvalho,
%@electronicmailaddress medchaves@posgrad.ufla.br
%E Gherardi, Douglas Francisco Marcolino,
%E Aragão, Luiz Eduardo Oliveira e Cruz de,
%B Simpósio Brasileiro de Sensoriamento Remoto, 18 (SBSR)
%C Santos
%8 28-31 maio 2017
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 5872-5879
%S Anais
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%X The State of Mato Grosso is characterized by soybean cultivation in summer seasons. As the agricultural sector has an important participation in economy, the implementation of monitoring and systematic mapping tools is important for the strategic planning. Facing this demand, the connection of field data, orbital data and geostatistical techniques appears as a tool in the attempt to ensure accuracy of the generated information. This paper presents and evaluates the Soja Sat initiative, which aimed to map the areas cultivated with soybeans in Mato Grosso between the 2000/2001 and 2010/2011 harvests. A combination of field data, which was obtained in partnership with Bom Futuro SA Group, daily vegetation data, which was derived from the Enhanced Vegetation Index (EVI) derived from the Moderate Resolution Imaging Spectroradiometer (MODIS), that is sensitive to biomass variations during the phenological cycle and geostatistical techniques were used. The period of analysis for validation involved the 2010/2011 harvest due to the relevance in the production and the availability of geographical delimitation. Aiming at validating and demonstrating the accuracy of the mapping, 5 agglomerates of farms were chosen for reference. Subsequently, from a point analysis of the soybean plots and a reference map that is derived from the TerraClass project, reliability indexes were generated through a confusion matrix. The results obtained presented high agreement with the field data. The Global Accuracy (0.92) and the Kappa Index (0.84) indicated that the proposed method was efficient for the mapping soybean crops in the 2010/2011 harvest in Mato Grosso.
%9 Geoprocessamento e aplicações
%@language pt
%3 59339.pdf