Beach width is an important factor for tourists’ comfort, and the backshore is a swash zone where sediment moves quickly. Artificial sandy beaches focus on beach width stability and evolution. This paper is based on an artificial beach project in Haikou Bay, where, in view of the existing conditions, a new type of beach profile that can protect beach berm and width without being eroded by large wave action. Numerical simulation based on XBeach model were conducted to predict the morphodynamical responses of the beach, including a diagnosis of the erosion spots under storm and normal wave events, respectively. Sediment fluxes along and across the shoreline under varied scenarios, dependent on profile width and backshore slope, were discussed. It was found that normal waves with lower heights and longer periods can induce stronger erosion than storm waves due to the landform of the inner-bay in Haikou Bay. Engineering and biological methods to reduce beach erosion during wave action were discussed. Biological methods such as green-plants-root-system can retain berm surface sediment without allowing it to be transported offshore by wave action. The design concept of this artificial beach project may inspire more beach design and protection projects in coastal zones.

The efficiency of beach recovery during a time of moderate waves following storm waves is closely related to the interaction between dynamics, sediment, and the landform. The existing studies mainly focus on the description of erosion and accretion characteristics, while the response and feedback mechanism of beach berm sediment have not been elucidated. The main controlling factors of recovery efficiency are not clear. In this paper, field observation and the XBeach numerical model are utilized on the sandy beach in Puqian Bay, China, to capture high-frequency cross-shore data during the post-storm recovery period. The variation characteristics and rules of berm elements, including berm ridge height and slope on two sides of the berm ridge, are analyzed. It is observed that the berm constantly changes to adapt to dynamic conditions. Additionally, a correlation between volume change and certain landform parameters is proposed, leading to the identification of a new relationship in wave run-up. The new forum reflects berm influence and considers the berm ridge and berm width.

Sandy beach resilience faces growing threats from extreme events and intensified human activity. Deep Learning (DL) has emerged as a powerful tool in coastal research, offering strengths in spatial feature extraction, nonlinear sequence modeling, acceleration of physical processes, and integration of multi-source data. This review frames resilience in three technical dimensions—resistance, recovery, and adaptation—and examines DL applications across three domains: first, monitoring and forecasting external forcing, including typhoon tracks and storm surge peak values; second, modeling and simulating beach processes, from rapid hydrodynamic forecasting to medium- and long-term shoreline evolution, and high-resolution sediment transport forecasting; and third, management and decision support, where DL methods and multi-scenario generation expand governance options, and interpretable features with uncertainty quantification enhance risk communication and policy adoption. DL complements traditional models by shortening the “observation–model–decision” cycle, expanding scenario analysis, and improving governance transparency. Challenges remain in cross-domain generalization, robustness in extreme scenarios, and data governance. This review confirms DL’s potential as a technology stack for enhancing sandy beach resilience and provides a methodological foundation for future research.

The rapid development of coastal structures on sandy coastlines raises concerns about their impacts on the shoreline’s evolution and the sediment transport dynamics. This study utilized a numerical modeling approach to simulate the multi-year response of Haikou Bay’s coastline to various nearshore structures, including piers and a large artificial island. The LITLINE module of the MIKE21 (v2020) software was employed to analyze the sediment transport patterns across three distinct coastal segments. The simulation results indicated that the sediment transport directions varied significantly: from west to east in the western segment, from east to west in the middle segment, and convergence toward the center in the eastern segment, divided by a construction trestle. The net sediment transport rates were quantified as 2000 m³/year for the western segment, 8000 m³/year for the middle segment, and 13,000 m³/year (west) and 10,000 m³/year (east) for the eastern segment. Due to the conflicting sediment transport directions on each side of the breakwater, noticeable deposition occurred on both sides. The presence of the artificial island created notable deposition in its wave shadow area, while the overall impact on the shoreline changes diminished over time. These findings underscore the significant influence of human activities, particularly coastal structures, on the natural evolution of shorelines.