ELIMINATION OF IONOSPHERIC PHASE IN SAR INTERFEROMETRY WITH DEEP CONVOLUTIONAL NEURAL NETWORK

Interferometric Synthetic Aperture Radar (InSAR) technology has been widely used in land surface deformation monitoring due to its advantages including wide coverage, high spatial resolution, all-weather, all-day, and high precision. However, the interferogram will contain residual ionospheric phase in the process of InSAR, which can reduce the accuracy of elevation measurement results and even mask the deformation measurement results, especially at L-band frequencies. In this article, we proposed a standard supervised-trained method, which is based on a deep residual U-shaped network, to eliminate residual ionospheric phase. And the proposed method is evaluated on the computer simulation.