MODIS-NDVI-based extraction of planting areas of major crops in China

This paper presents a method for automatically identifying crop planting areas at a large-scale based on time-series of MODIS NDVI Datasets in China Agriculture Remote Sensing Monitoring System(CHARMS). This method was applied to extracting planting areas of major crops in China, including spring wheat, winter wheat, spring maize, summer maize, cotton, soybean and paddy. More than 50 models were built for different crops in different regions, and the field sampling data, high spatial resolution remote sensing images and statistical data were used to assess the accuracy. The total accuracy is more than 80%, which shows that it is feasible to extract planting areas of different crops at a large scale using MODIS data.