Digital Surface Model Super-Resolution by Integrating High-Resolution Remote Sensing Imagery Using Generative Adversarial Networks

Digital surface model (DSM) is the fundamental data in various geoscience applications, such as city 3-D modeling and urban environment analysis. The freely available DSM often suffers from limited spatial resolution. Super-resolution (SR) is a promising technique to increase the spatial resolution of DSM. However, most existing SR models struggle to reconstruct spatial details, such as buildings, valleys, and ridges. This article proposes a novel DSM super-resolution (DSMSR) model that integrates high-resolution remote sensing imagery using generative adversarial networks. The generator in DSMSR contains three modules. The first DSM feature extraction module uses the residual-in-residual dense block to extract features from low-resolution DSM. The second multiscale attention feature extraction module employs the pyramid convolutional residual dense blocks to capture the spatial details of ground objects at multiple scales from remote sensing imagery. The third DSM reconstruction module uses a squeeze-and-excitation block to fuse the extracted features from low-resolution DSM and high-resolution remote sensing imagery for generating SR DSM. The discriminator of DSMSR uses the relativistic average discriminator for adversarial learning. The slope loss is further introduced to ensure the accurate representation of topographic features. We evaluate DSMSR on four different terrain regions in the U.K. to downscale the 30-m AW3D30 DSM to 5-m DSM. The experimental results indicate that DSMSR outperforms the traditional interpolation algorithms and four existing deep-learning-based SR models. The DSMSR restores more spatial detail of topographic features and generates more accurate image quality, elevation, and terrain metrics.