A Sea Ice Type Recognition Method based on Convolutional Neural Network for GNSS-R Delay Doppler Images

Remote sensing (RS) of sea ice types is of great significance for global climate research. A convolutional neural network (CNN) based sea ice type recognition method for delay Doppler map (DDM) of global navigation satellite system reflection (GNSS-R) is proposed in this paper. In the proposed method, the sea ice type recognition problem is transformed into an image recognition problem by utilizing the difference between the DDM images corresponding to the first-year and multi-year ice, and the CNN model is used to recognize the images. Experimental results show that our proposed CNN based method for identifying sea ice types has excellent performance.