Crop Mapping Using Sentinel Full-Year Dual-Polarized SAR Data and a CPU-Optimized Convolutional Neural Network With Two Sampling Strategies

Although optical remote sensing can capture the Earth's environment with visible and infrared sensors, it is limited by weather conditions. Often, only a few sets of cloud-free optical imagery are available in cloudy regions, where many agricultural towns are located. On the other hand, radar remote sensing can capture imagery under cloudy conditions. In this study, we examined the capability of Sentinel-1 multitemporal dual-polarized synthetic aperture radar (SAR) imagery in a whole year from Google Earth Engine in crop mapping in two study sites in Chongqing, China, and Landivisiau, France. Results show that it is possible to produce better crop classification maps using multitemporal SAR imagery, but the performance is limited by local terrain. Flat agricultural regions, such as Western Europe, are expected to benefit from the multitemporal SAR information. Mountain agricultural regions, such as Southwestern China, will encounter difficulties due to the undulate terrain. We also tested two sampling strategies, i.e., random sampling and regional sampling, and observed high variation in overall accuracy: the former led to a higher accuracy. The gap is caused by the diversity of training sets examined using tSNE visualization. The importance of SAR channels in each month are correlated with their entropy. Data from the growing season are important in distinguishing crop types. The 3-D convolutional neural network (CNN) achieved similar results under a huge computation cost compared with 2-D CNNs. Based on the experiments, we recommend to use a lightweight 2-D CNN that can run on the CPU for real-world crop mapping with SAR data.