Estimating soybean crop areas using spectral-temporal surfaces derived from MODIS images in Mato Grosso, Brazil

Pesquisa Agropecuária Brasileira

Rui Dalla Valle Epiphanio²  Antonio Roberto Formaggio¹  Bernardo Friedrich Theodor Rudorff¹  Eduardo Eiji Maeda¹  Alfredo José Barreto Luiz¹ 

[1] ,Louis Dreyfus Commodities Brasil S.A.São Paulo SP

关键词: Glycine max;    accuracy;    agricultural statistics;    classification;    remote sensing;    thematic map;    Glycine max;    acurácia;    estatísticas agrícolas;    classificação;    sensoriamento remoto;    mapa temático;   

DOI  :  10.1590/S0100-204X2010000100010

来源: SciELO

【 摘 要 】

The objective of this work was to evaluate the application of the spectral-temporal response surface (STRS) classification method on Moderate Resolution Imaging Spectroradiometer (MODIS, 250 m) sensor images in order to estimate soybean areas in Mato Grosso state, Brazil. The classification was carried out using the maximum likelihood algorithm (MLA) adapted to the STRS method. Thirty segments of 30x30 km were chosen along the main agricultural regions of Mato Grosso state, using data from the summer season of 2005/2006 (from October to March), and were mapped based on fieldwork data, TM/Landsat-5 and CCD/CBERS-2 images. Five thematic classes were considered: Soybean, Forest, Cerrado, Pasture and Bare Soil. The classification by the STRS method was done over an area intersected with a subset of 30x30-km segments. In regions with soybean predominance, STRS classification overestimated in 21.31% of the reference values. In regions where soybean fields were less prevalent, the classifier overestimated 132.37% in the acreage of the reference. The overall classification accuracy was 80%. MODIS sensor images and the STRS algorithm showed to be promising for the classification of soybean areas in regions with the predominance of large farms. However, the results for fragmented areas and smaller farms were less efficient, overestimating soybean areas.

【 授权许可】

CC BY   
 All the contents of this journal, except where otherwise noted, is licensed under a Creative Commons Attribution License