China has the world’s largest area of coastal aquaculture ponds, accounting for 39% of the total coastal aquaculture pond area worldwide. The rapid development of coastal aquaculture can significantly reduce global food shortages and support the development of marine economies on the Chinese mainland. However, coastal aquaculture ponds have been recognized as a beach hazard because they require pipes to be laid on the surface of the beach to discharge wastewater, polluting the beach and artificially dividing it into multiple segments. Based on a well-conceived remote sensing analysis, the erosion of beaches backed by densely distributed coastal aquaculture ponds was determined to be 10 m/y. A high-efficiency shoreline evolution model was verified using a satellite-derived shoreline dataset. For the present case, the Brier Skill Score (BSS) was calculated to be 0.55, indicating a moderate match between the modeled and satellite-derived shoreline datasets. The verified ShorelineS model was then used to predict the future evolution of a shoreline backed by densely distributed coastal aquacultural ponds. The retreat distance of the erosion hotspot was predicted to increase from 150 m in 2025 to 240 m in 2040. It is expected that the beach will lose the entirety of its dry part in the future. Potential strategies for beach protection include reasonable management and the ecological restoration and nourishment of the beach.
Wave breaking is a fundamental process in ocean energy dissipation and plays a crucial role in the exchange between ocean and nearshore sediments. Foam, the primary visible feature of wave breaking areas, serves as a direct indicator of wave breaking processes. Monitoring the distribution of foam via remote sensing can reveal the spatiotemporal patterns of nearshore wave breaking. Existing studies on wave breaking processes primarily focus on individual wave events or short timescales, limiting their effectiveness for nearshore regions where hydrodynamic processes are often represented at tidal cycles. In this study, video imagery from a typical low-tide terrace (LTT) beach was segmented into four categories, including the wave breaking foam, using the DeepLabv3+ architecture, a convolutional neural networks (CNNs)-based model suitable for semantic segmentation in complex visual scenes. After training and testing on a manually labelled dataset, which was divided into training, validation, and testing sets based on different time periods, the overall classification accuracy of the model was 96.4%, with an accuracy of 96.2% for detecting wave breaking foam. Subsequently, a heatmap of the wave breaking foam distribution over a tidal cycle on the LTT beach was generated. During the tidal cycle, the foam distribution density exhibited both alongshore variability, and a pronounced bimodal structure in the cross-shore direction. Analysis of morphodynamical data collected in the field indicated that the bimodal structure is primarily driven by tidal variations. The wave breaking process is a key factor in shaping the profile morphology of LTT beaches. High-frequency video monitoring further showed the wave breaking patterns vary significantly with tidal levels, leading to diverse geomorphological features at various cross-shore locations.