Mapping soya bean and corn crops in the State of Paraná, Brazil, using EVI images from the MODIS sensor. Issue 6 (18th March 2016)

• Record Type: Journal Article
• Authors: Grzegozewski, Denise Maria; Johann, Jerry Adriani; Uribe-Opazo, Miguel Angel; Mercante, Erivelto; Coutinho, Alexandre Camargo
• Is Part Of: International journal of remote sensing. Volume 37:Issue 6(2016)
• Page Start: 1257
• Page End: 1275
• Publication Date: 2016-03-18
• Subjects: Annual agriculture -- time series -- vegetation index; Remote sensing -- Periodicals; Télédétection -- Périodiques; 621.3678
• DOI: 10.1080/01431161.2016.1148285
• Languages: English
• ISSNs: 0143-1161

Abstract

ABSTRACT: This study aimed to map, separate, and estimate soya bean and corn crop areas in Paraná State, Brazil, in the harvest years 2012/13 and 2013/14, using the enhanced vegetation index (EVI) images from the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor. Thus, two methodologies were integrated, the first considering heterogeneity on the dates of crop cycles, the scenes required to generate images of minimum and maximum vegetation indexes, creating a colour composite red, green, and blue (RGB), and identifying two cultures simultaneously. In the second methodology, soya bean and corn were identified and mapped using the selection of pure pixels and the supervised classification algorithm Spectral Angle Mapper (SAM). In order to avoid overlapping areas, we multiplied the results from the first and second methodologies to obtain the final separation. The final validation of the mapping was compared to official data, identifying high correlation to crops. Based on Medium-Resolution Linear Imaging Self-Scanner (LISS-III) and Land Remote Sensing Satellite (Landsat-8) images, the similarity of global accuracy (GA) and kappa accuracy indices was determined, being classified as good and excellent, respectively. It showed that the use of the two consortium methodologies for separation and overlap elimination of these crops in the state of Paraná was efficient.