Rapeseed Fields Mapping Using Sentinel-1 Time Series

Nicolas N. Baghdadi, Saeideh Maleki, Cássio Fraga Dantas, Sami Najem, Hassan Bazzi, Dino Ienco, Mehrez Zribi

Abstract: This paper analyzes the accuracy on the detection of rapeseed fields using Sentinel-1 (S1) time series. Random Forest (RF) and three deep learning (DL) algorithms namely Long Short-Term Memory Fully Convolutional Network (LSTM-FCN), InceptionTime, and Multi-layer Perceptron (MLP) were tested in this study. All four algorithms were used to classify the S1 time series with a large number of ground samples. To test the transferability of classification models, the algorithms were trained on a given year, and then tested on different years. The results demonstrated the high performance of all four algorithms in mapping rapeseed fields when using different years in training and testing phases (F1 between 85.5% and 92.7%, kappa between 0.85 and 0.93).