Groundwater overexploitation and loading of buildings have been the main factors triggering land subsidence along the west coast of Bohai Bay, China, since the 2000s. Uneven subsidence has been causing damage to buildings and civil facilities, loss of elevation, increasing the risk of flood and seawater intrusion, and threatening the safety of people’s lives and property. This paper analyzed the spatial and temporal features of land subsidence along the coastal area from 2003 to 2010 and from 2015 to 2020, respectively. The relations between the initiating factors and land subsidence were explored. Then, the simulation model of land subsidence was constructed through a deep learning method. During the process, multiple data were collected, including land satellite (Landsat), environmental satellite advanced synthetic aperture radar (ENVISAT ASAR) and Sentinel-1 images, leveling data, lithological data, and groundwater level data. The area occupied by buildings and vertical displacement were extracted by using supervised classification, small baseline subset (SBAS), and persistent scatterer interferometry (PSI) technologies. The gated recurrent unit (GRU) neural network was adopted to simulate the evolution of land subsidence. Results showed that the maximum annual vertical displacement rate decreased from −94 mm/yr during 2003–2010 to −87 mm/yr during 2015–2020. The correlation efficiency between the groundwater level of the third confined aquifer group and land subsidence was larger than the area occupied by buildings and the compressible layer thickness with subsidence. The constructed GRU neural network model can simulate subsidence from September 2019 to December 2019, with the overall RMSE and MAE being 3.16 mm and 2.19 mm, respectively. This work can facilitate an understanding of the evolution and prevention of land subsidence along the west coast of Bohai Bay, which will provide information for policy decisions and flood-fighting plans of the worldwide coastal cities.

Current research often neglects the spatial and temporal dynamics of relative sea level rise (RSLR) when assessing its impact on compound flood hazards in urban coastal areas. To address this issue, we develop a framework combining statistical and hydrodynamic overland inundation modeling to assess the combined effect of compound flooding and RSLR on urban functional areas in terms of flood hazard and exposure. This framework uses maximum flood depth (MFD), maximum flood area, and maximum flood volume (MFV) as metrics for flood hazard assessment, and absolute flood exposure and relative flood exposure (RFE) metrics for evaluating flood exposure in urban areas. In a case study focused on Haikou, Hainan Province, we analyze data from 66 TC events from 1960 to 2017 to determine the univariate distribution and bivariate dependency structure of storm tides and rainfall using extreme value distributions and copula functions. We then employ an overland inundation model to simulate compound flooding for various bivariate return periods (RPs) under RSLR. Our findings indicate that flood hazards assessed using univariate RPs are more severe than those derived from bivariate RPs, with the univariate MFV being 90.5% higher for the 200-year RP. RSLR significantly amplifies the compound flood effects in major inundation areas, such as Haidian Island and Jiangdong NewArea. Specifically, for the 100-year RP, the MFD in these regions is projected to increase by 1.5 m by 2100 due to RSLR. Additionally, residential land is identified as the most vulnerable to RSLR, with its RFE reaching 19.8% by 2100, which is 6.3% higher compared to scenarios without considering RSLR. These results show the necessity of incorporating RSLR into compound flood hazard assessment to formulate flood mitigation and management measures in coastal cities.