Integrating Sentinel-1 SAR and Sentinel-2 optical imagery with a crop structure dynamics model to track crop condition

Sentinel-1 and Sentinel-2 satellites are delivering data at the spatial resolutions geographies needed for operational crop monitoring. Of particular interest, Synthetic Aperture Radar (SAR) in Single Look Complex (SLC) format can be processed to provide polarimetric parameters sensitive development. This study created a based SAR vegetation index canola, calibrated Normalized Difference Vegetation Index (NDVI) (SARcal-NDVI) values calculated from Sentinel-2. A Random Forest Regressor (RFR) modelled SARcal-NDVI, four selected features (degree of linear polarization (DoLP), normalized Shannon entropy (SE), second eigenvalue coherency matrix (l2) ellipticity angle (χ)). The coefficient determination (R2) between NDVI SARcal-NDVI was 0.89. RFR-generated estimates, on SLC generated parameters, were then used with Canopy Structure Dynamics Model (CSDM) Growing Degree Days (GDD) estimate condition canola daily time step. SARcal--NDVI series estimated CSDM model correlated ground measured biomass. During rapid accumulation biomass early mid-season, correlations wet strong (R2 0.88). Correlations still significant albeit weaker during pod development throughout period senescence 0.42). As climate variability drives uncertainty agricultural sector, sensors like Sentinels leveraged track changes acreages productivity. next step this research is extend other economically important crops such as corn, soybeans wheat test ability Sentinel-1-based inform yield estimates.