Title :
Crop classification in the U.S. Corn Belt using MODIS imagery
Author :
Doraiswamy, Paul C. ; Stern, Alan J. ; Akhmedov, Bakhyt
Author_Institution :
ARS-Hydrology & Remote Sensing Lab, Beltsville
Abstract :
Landcover classification is essential in studies of landcover change, climate, hydrology, carbon sequestration, and yield prediction. The potential for using NASA´s MODIS sensor at 250-meter resolution was investigated for USDA´s operational programs. This research was conducted over Iowa and Illinois to classify corn and soybean crops. Multitemporal 8-day composite 250-meter-resolution surface reflectance product time series were used to generate the NDVI data, which were used to differential between corn and soybean crops in the U.S. Corn Belt. The results of the MODIS-based classification were compared with the Landsat-based classification for the 2-year period. The overall classification accuracy for Iowa was 82%, and for Illinois 75%. In conclusion, this method has been used successively during the 2002-2006 years to develop crop classifications and products for crop conditions and potential yield maps for Iowa and Illinois.
Keywords :
crops; image classification; vegetation mapping; AD 2002 to 2006; Illinois; Iowa; Landsat-based classification; MODIS sensor; Moderate Resolution Imaging Spectrometer; NASA sensor; US Corn Belt; USDA operational programs; carbon sequestration; climate; corn crop; crop classification; hydrology; landcover change; landcover classification; normalized difference vegetation index; soybean crop; time series; yield prediction; Belts; Classification tree analysis; Crops; Decision trees; Error correction; Filtering; MODIS; Reflectivity; Remote sensing; Vegetation mapping; Crop Classification; Data filtering; MODIS Classification;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2007. IGARSS 2007. IEEE International
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-1211-2
Electronic_ISBN :
978-1-4244-1212-9
DOI :
10.1109/IGARSS.2007.4422920
