Satellite radar altimetry is an important technology for monitoring water levels, but issues related to waveform contamination restrict its use for rivers, narrow reservoirs, and small lakes. In this study, a novel and improved empirical retracker (ImpMWaPP) is presented that can derive stable inland lake levels from Cryosat-2 synthetic aperture radar interferometer (SARin) waveforms. The retracker can extract a robust reference level for each track to handle multi-peak waveforms. To validate the lake levels derived by ImpMWaPP, the in situ gauge data of seven lakes in the Tibetan Plateau are used. Additionally, five existing retrackers are compared to evaluate the performance of the proposed ImpMWaPP retracker. The results reveal that ImpMWaPP can efficiently process the multi-peak waveforms of the Cryosat-2 SARin mode. The root-mean-squared errors (RMSEs) obtained by ImpMWaPP for Qinghai Lake, Nam Co, Zhari Namco, Ngoring Lake, Longyangxia Reservoir, Bamco, and Dawa Co are 0.085 m, 0.093 m, 0.109 m, 0.159 m, 0.573 m, 0.087 m, and 0.122 m, respectively. ImpMWaPP obtains the lowest mean RMSE (0.175 m) over the seven lakes, indicating that it extracts lake levels well during icing and no-ice periods, and is more suitable for lakes frozen in winter.
Deep learning has recently attracted extensive attention and developed significantly in remote sensing image super-resolution. Although remote sensing images are composed of various scenes, most existing methods consider each part equally. These methods ignore the salient objects (e.g., buildings, airplanes, and vehicles) that have more complex structures and require more attention in recovery processing. This paper proposes a saliency-guided remote sensing image super-resolution (SG-GAN) method to alleviate the above issue while maintaining the merits of GAN-based methods for the generation of perceptual-pleasant details. More specifically, we exploit the salient maps of images to guide the recovery in two aspects: On the one hand, the saliency detection network in SG-GAN learns more high-resolution saliency maps to provide additional structure priors. On the other hand, the well-designed saliency loss imposes a second-order restriction on the super-resolution process, which helps SG-GAN concentrate more on the salient objects of remote sensing images. Experimental results show that SG-GAN achieves competitive PSNR and SSIM compared with the advanced super-resolution methods. Visual results demonstrate our superiority in restoring structures while generating remote sensing super-resolution images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.