A Sparse Convolution Method to Reduce the Atmospheric Phase Screen of SAR Interferometry in the Coastal Region

Effective mitigation of atmospheric phase screen (APS) is crucial for synthetic aperture radar (SAR) interferometry in coastal regions. However, existing methods suffer from various limitations in estimating atmospheric delays, especially turbulent mixing components. As a solution, we propose a sparse convolution-based attention deep residual U-shaped network (sARU-Net), a submanifold sparse convolutional neural network (SSCNN), for adaptive estimation of APS from InSAR coherent pixels. Moreover, we propose a straightforward and effective iterative processing strategy for generating sample datasets for model training. The results obtained from the TerraSAR-X and Sentinel-1 datasets in two coastal regions of China demonstrate a reduction in the standard deviation of the interferograms by 77.7% and 68.3%, respectively, after applying our correction method. Additionally, the InSAR results align more closely with the leveling data. On the same dataset, our method shows superior performance compared to both the generic atmospheric correction online service for InSAR (GACOS) method and the linear model method. When compared to previous convolutional neural network (CNN, i.e., attention-based deep residual U-shaped network, ARU-Net) method, our approach exhibits better accuracy and more detail, and is 21% more computationally efficient for training, while requiring 24% less graphics processing unit (GPU) memory. The effectiveness of the proposed method shows that sparse convolution has great potential in mitigating the effects of APS in InSAR coherent pixels.