International Journal of Remote Sensing · 2011 · 258 citations · 47 references
AgricultureCrop SciencesEarth SciencesCrop SensingCropping SystemsRemote SensingCrop ClassificationCropping IntensityCropping PatternsLand Cover ClassificationVegetation IndicesVegetation MonitoringCrop MappingCrop Type Change DetectionEnhanced Vegetation IndexImage Classification For CropsRemote Sensing Crop ClassificationSmoothingSpatial Feature ExtractionTime Series Crop Classification
Agriculture in Brazilian Amazonia is undergoing intensification. The study seeks to map crop types to assess how this intensification is occurring and its impacts. Two successive MODIS‑EVI time‑series classifications were applied—first to delineate agricultural areas and then to identify five crop classes (soybean, maize, cotton) in single or double cropping systems—using a five‑step workflow of time‑series analysis, smoothing, feature selection, classification, and post‑processing. The first classification detected 95 % of agricultural areas (5.6 million ha) with correlation coefficients >0.98 for the three crops, while the second achieved 74 % overall accuracy (kappa 0.675) and showed that 30 % of planted area employed double cropping, especially along BR163 and the Parecis plateau.
Agriculture in Brazilian Amazonia is going through a period of intensification. Crop mapping is important in understanding the way this intensification is occurring and the impact it is having. Two successive classifications based on MODIS (MODerate Resolution Imaging Spectroradiometer)-TERRA/EVI (Enhanced Vegetation Index) time series are applied (1) to map agricultural areas and (2) to identify five crop classes. These classes represent agricultural practices involving three commercial crops (soybean, maize and cotton) planted in single or double cropping systems. Both classifications are based on five steps: (1) analysis of the MODIS/EVI time series, (2) application of a smoothing algorithm, (3) application of a feature selection/extraction process to reduce the data set dimensionality, (4) application of a classifier and (5) application of a post-classification treatment. The first classification detected 95% of the agricultural areas (5 617 250 ha during the 2006–2007 harvest) and correlation coefficients with agricultural statistics exceeded 0.98 for the three crop classes at municipality level. The second classification (overall accuracy = 74% and kappa index = 0.675) allowed us to obtain the spatial variability mapping of agricultural practices in the state of Mato Grosso. A total of 30% of the total planted area was cultivated through double cropping systems, especially along the BR163 highway and in the Parecis plateau region.
47
Overview of the radiometric and biophysical performance of the MODIS vegetation indices
Alfredo Huete, Kamel Didan, Tomoaki Miura et al. · Remote Sensing of Environment · 2002 · 9.6K citations
Agriculture, Ecology, Geography +14
Photogrammetric Engineering and Remote Sensing
John Nicol, B. King · UCL Discovery (University College London) · 2007 · 9.4K citations