In the global context of population growth and climate change, monitoring crops is necessary to sustain agriculture and conserve natural resources. While many studies have demonstrated the ability of optical and SAR remotely sensed data to estimate crop parameters, these data have not been compared or combined to predict crop phenological stages. Despite the high sensitivity of SAR polarimetric data to crop phenological stages, no study has used high temporal resolution data. The freely available SAR Sentinel-1 (S-1) and optical Sentinel-2 (S-2) time series provide a unique opportunity to monitor crop phenology at a high spatial resolution on a weekly basis. The objective of this study was to evaluate the potential of S-1 data alone, S-2 data alone, and their combined use to predict wheat and rapeseed phenological stages. We first analyzed temporal profiles of spectral bands, vegetation indices and leaf area index (LAI) derived from S-2 data, and backscattering coefficients and polarimetric indicators derived from S-1 data. Then, an incremental procedure was used to estimate the contribution of S-1 and S-2 features to the classification of principal and secondary phenological stages of wheat and rapeseed. Results for both crops showed that the classification obtained with combined S-1 & 2 data (mean kappa = 0.53–0.82 and 0.74–0.92 for wheat and rapeseed, respectively) was more accurate than those obtained with S-2 data alone (mean kappa = 0.54–0.75 and 0.67–0.86 for wheat and rapeseed, respectively) or S-1 data alone (mean kappa = 0.48–0.61 and 0.61–0.64 for wheat and rapeseed, respectively). Combining S-1 & 2 data allowed better identification of the beginning and end of tillering for wheat and the beginning and end of ripening for rapeseed. Among S-2 features, the most important were LAI for wheat and the NDVI for rapeseed. For both crops, the S2REP index was one of the most important vegetation indices, while MCARI was less important. For S-1 features, results hi