An Intelligent Learning Reconfiguration Model Based on Optimized Transformer and Multi-Source Features (TMSF) for High-Precision InSAR DEM Void Filling

Synthetic aperture radar (SAR) systems can provide sub-meter terrain mapping and accurate point elevation information quickly and efficiently. InSAR technology has proven to be a powerful method for producing digital elevation models (DEMs). However, DEM generation using InSAR technology is limited by mountain shadow overlap, atmospheric noise, low backscatter coefficient, and spatiotemporal incoherence, leading to the problem of voids. This article proposes an intelligent learning reconfiguration model based on optimized transformer and multi-source features (TMSF). First, the intelligent learning reconfiguration model based on the transformer and convolutional neural network (CNN) was constructed, and the multi-source feature connection module was used for feature supervision and loss function optimization. Then, the relationship of non-void areas between the low-resolution DEM and the high-resolution InSAR DEM was found, and the voids were intelligently filled. The experiments used 19 TerraSAR-X images in San Diego (SD), USA, and 18 PAZ images in Yan’an (YA), China, to generate high-precision InSAR void DEMs and intelligently fill the voids. Compared to traditional interpolation or deep learning models, modeling accuracy improved by 11.31-45.74% and 2.32-8.78% in the SD and YA areas, respectively. Using the photogrammetric DEM to evaluate the accuracy of the filled DEM, the new method showed improvements of 15.64-25.91% and 5.60-28.26% respectively. In addition, 122 ICESat/GLAS points collected in the YA area were further validated, with an improvement of 4.40-22.28%. The generated DEM has considerable advantages for terrain feature preservation and river network extraction, and the new method can provide technical support for DEM void filling.