Synergistic Use of Radar Sentinel-1 and Optical Sentinel-2 Imagery for Crop Mapping: A Case Study for Belgium

TLDR

A timely inventory of agricultural areas and crop types is essential for global food security, and satellite remote sensing—especially from the Copernicus Sentinel satellites—provides a reliable, freely available source for identifying crop types. The study aimed to generate a Belgium crop map by combining Sentinel‑1 radar and Sentinel‑2 optical imagery, and to suggest future work on object‑level classification and monitoring. The authors produced incidence‑angle‑normalised Sentinel‑1 backscatter mosaics and cloud‑free NDVI mosaics from Sentinel‑2, then applied a random forest classifier to map eight crop types across Belgium. The random forest achieved 82 % accuracy (kappa 0.77), with radar‑optical combinations outperforming single‑sensor approaches, performance peaking in July, and classification confidence revealing lower reliability at parcel borders.

Abstract

A timely inventory of agricultural areas and crop types is an essential requirement for ensuring global food security and allowing early crop monitoring practices. Satellite remote sensing has proven to be an increasingly more reliable tool to identify crop types. With the Copernicus program and its Sentinel satellites, a growing source of satellite remote sensing data is publicly available at no charge. Here, we used joint Sentinel-1 radar and Sentinel-2 optical imagery to create a crop map for Belgium. To ensure homogenous radar and optical inputs across the country, Sentinel-1 12-day backscatter mosaics were created after incidence angle normalization, and Sentinel-2 normalized difference vegetation index (NDVI) images were smoothed to yield 10-daily cloud-free mosaics. An optimized random forest classifier predicted the eight crop types with a maximum accuracy of 82% and a kappa coefficient of 0.77. We found that a combination of radar and optical imagery always outperformed a classification based on single-sensor inputs, and that classification performance increased throughout the season until July, when differences between crop types were largest. Furthermore, we showed that the concept of classification confidence derived from the random forest classifier provided insight into the reliability of the predicted class for each pixel, clearly showing that parcel borders have a lower classification confidence. We concluded that the synergistic use of radar and optical data for crop classification led to richer information increasing classification accuracies compared to optical-only classification. Further work should focus on object-level classification and crop monitoring to exploit the rich potential of combined radar and optical observations.