Global sea level rise is a major environmental concern for many countries and cities, particularly for low-lying coastal areas where urban development is threatened by the combined effects of sea level rise and land subsidence. This study employed an improved two-layer network Persistent Scatterers Interferometric Synthetic Aperture Radar (PS-InSAR) technology to obtain high-precision land subsidence in Singapore from 2015 to 2019. Landsat images from 1973 to 2020 were also utilized to extract changes in Singapore’s coastline. Geological, topographical, and global sea level rise data were integrated to investigate the causes and impacts of land subsidence in Singapore. The results indicate that the areas with severe subsidence coincide with land reclamation areas, where subsidence is mainly due to soil consolidation. Based on WorldDEM, land subsidence, and sea level rise data, the maximum inundation depth in Singapore by 2050 is estimated to be 1.24 m, with the Marina Bay area in Singapore’s central business district being the most vulnerable to sea level rise. This study provides data support and a scientific basis for understanding the impact of land subsidence on Singapore’s coastal areas under the influence of multiple factors using advanced InSAR technology.
Clouds in optical remote sensing images are an unavoidable existence that greatly affect the utilization of these images. Therefore, accurate and effective cloud detection is an indispensable step in image preprocessing. To date, most researchers have tried to use deep-learning methods for cloud detection. However, these studies generally use computer vision technology to improve the performances of the models, without considering the unique spectral feature information in remote sensing images. Moreover, due to the complex and changeable shapes of clouds, accurate cloud-edge detection is also a difficult problem. In order to solve these problems, we propose a deep-learning cloud detection network that uses the haze-optimized transformation (HOT) index and the edge feature extraction module for optical remote sensing images (CD_HIEFNet). In our model, the HOT index feature image is used to add the unique spectral feature information from clouds into the network for accurate detection, and the edge feature extraction (EFE) module is employed to refine cloud edges. In addition, we use ConvNeXt as the backbone network, and we improved the decoder to enhance the details of the detection results. We validated CD_HIEFNet using the Landsat-8 (L8) Biome dataset and compared it with the Fmask, FCN8s, U-Net, SegNet, DeepLabv3+ and CloudNet methods. The experimental results showed that our model has excellent performance, even in complex cloud scenarios. Moreover, according to the extended experimental results for the other L8 dataset and the Gaofen-1 data, CD_HIEFNet has strong performance in terms of robustness and generalization, thus helping to provide new ideas for cloud detection-related work.