Impact of Categorical and Spatial Scale on Supervised Crop Classification using Remote Sensing

High temporal revisit frequency over vast geographic areas is necessary to properly use satellite earth observation for monitoring agricultural production. However, this often limits the spatial resolution that can be used. The challenge of discriminating pixels that correspond to a particular crop type, a prerequisite for crop specific monitoring remains daunting when the signal encoded in pixels stems from several land uses (mixed pixels). Naturally, the concept of spatial scale arises but the issue of selecting a proper class legend (the categorical scale) should not be neglected. A framework is presented that addresses these issues and that can be used to quantitatively define pixel size requirements for crop identification and to assess the effect of categorical scale. The framework was applied over two agricultural landscapes. It was demonstrated that there was no unique spatial resolution that provided the best classification result for all classes at once at a given categorical scale. The suitability of pixel populations characterized by pixel size and purity differed for identifying specific crops within tested landscapes, and for one crop there were large differences among the landscapes. In the context of agricultural crop growth monitoring the framework described above can be used to draw guidelines for selecting appropriate imagery, e.g. suitable pixel sizes, and for selecting class legends suitable for accurate crop classification when the interest is only on pixels covering arable land as a prerequisite for crop specific monitoring. The framework could be used to plot the suitability (or accuracy) of pixels as a function of their purity to provide a spatial assessment of classification performance