Accurate crop type information is of paramount importance for decision makers. This paper focuses on refining rapeseed field detection. This goal is achieved by creating high accuracy rapeseed maps using Sentinel-1 (S1) time series and secondly, by developing different solutions for mapping the rapeseed fields when there are constraints in ground samples collection. Proposed solutions include transferring a model developed over one year to other years with no retraining , and developing models with limited training samples. The research evaluates the performance of Random Forest (RF) and three deep learning (DL) algorithms: Long Short-Term Memory Fully Convolutional Network (LSTM-FCN), InceptionTime, and Multilayer Perceptron (MLP). All four algorithms were used to classify the S1 time series with a large number of ground samples from the same years for training and testing. Smaller sample sizes were then tested for the training phase (100, 300, 500 and 1000 samples in a study site of 800 km2). Model transferability is tested across years. The impact of S1 image count on transfer accuracy is examined. Additionally, the effect of the phenological shift in the rapeseed growth cycle of 15 and 30 days between the training and test years was also investigated. The findings demonstrate strong model performance when training and testing occur in the same year (F1score up to 95%). Within sample sizes of 300 to 1000, RF and InceptionTime stand out with high accuracy (F1-score>90%). When employing different years for training and testing with ample sample sizes, all four algorithms correctly classified rapeseed (F1-score between 85.5% and 92.7%). In cases of a reduced number of images, the performance of InceptionTime and LSTM-FCN decreased (16% decrease in the F1-score), while RF and MLP maintain their performance. Notably, RF outperforms DL algorithms with an F1 score of 89.1%. In the context of a phenological shift, only InceptionTime and LSTM-FCN demonstrated strong performance (F1-score between 87.7% and 92.6%).