Classification of Wheat and Barley Fields Using Sentinel-1 Backscatter

Abstract

The knowledge of the distribution of crop types is of great importance to numerous applications at regional to global scales. Different techniques, including microwave remote sensing methods, have been developed for automatized, accurate crop mapping, however, the discrimination of crops with similar morphology and phenology remains a challenge. In this study, we investigate how to distinguish wheat and barley fields by applying statistical methods and a long-short term memory network to backscatter observed by the C-band SAR instrument onboard the Sentinel-1 satellite.