Removing InSAR Topography-Dependent Atmospheric Effect Based on Deep Learning

Atmospheric effects are among the primary error sources affecting accuracy of interferometric synthetic aperture radar (InSAR). The topography-dependent atmospheric effect is particularly noteworthy in reservoir areas for landslide monitoring utilizing InSAR, which must be effectively corrected to complete InSAR high-accuracy measurement. This paper proposed a correction method based on Multi-Layer Perceptron (MLP) neural network model combined with topography and spatial data information. We used this approach pairs Sentinel-1 images Baihetan dam. contrasted outcomes those obtained using generic online service (GACOS) traditional linear correction. results indicated that MLP reduced phase standard deviation interferogram by an average 64% nearly eliminated phase-elevation correlation. Both comparisons outperformed GACOS Through two real-world examples, we demonstrated how slopes displacements, were previously obscured significant delay, could successfully clearly identified interferograms following network. atmosphere can better suggested paper. Unlike previous model, adjusted fit each interferogram, regardless much was present. In order improve effectiveness DInSAR time-series solutions, it applied immediately retrieve effective displacement information cannot before