Synergy of Sentinel-1 and Sentinel-2 Imagery for Early Seasonal Agricultural Crop Mapping

The exploitation of the unprecedented capacity Sentinel-1 (S1) and Sentinel-2 (S2) data offers new opportunities for crop mapping. In framework SenSAgri project, this work studies synergy very high-resolution Sentinel time series to produce accurate early seasonal binary cropland mask type map products. A classification processing chain is proposed address following: (1) high dimensionality challenges arising from explosive growth in available satellite observations (2) scarcity training data. two-fold methodology based on an S1-S2 system combining so-called soft output predictions two individually trained classifiers. performances were assessed over three European test sites characterized by different agricultural systems. large number highly diverse independent sets used validation experiments. agreement between algorithms was confirmed through presented results assess interest decision-level fusion strategies, such as product experts. Accurate products obtained countries season with limited highlight benefit mapping detecting areas before identification types.