Porous materials are increasingly being used in the design of floating structures in coastal and ocean engineering, but there is a lack of numerical tools that can aid in the design of a movable floating porous structure. To close this gap, the existing volume-averaged numerical model for flow interacting with a fixed porous body was extended to floating scenarios by (1) using the relative velocity in the porous friction force, (2) calculating rigid body motion using volume integral of porous body force, and (3) modifying a dynamic mesh algorithm for a mobile porous body. As a demonstration, the developed model was applied to a porous floating structure consisting of cubically packed uniform spheres. Two sets of model applications were involved. The first set considered three-dimensional flow around a fixed porous block placed beneath the free surface. The measured total force on the block under wave or steady flows was predicted accurately with an error less than 10%. The second set involved a two-dimensional wave interacting with a floating porous block representing a breakwater. For free-floating conditions, the model can accurately predict the dynamic response of the structure, including the time varying movement of its rigid body and the mean drift. For mooring-restrained conditions, the mooring force and wave transmission coefficients were also predicted well with an error less than 20%. The proposed numerical approach can be applied to other floating structures with a rigid volumetric porous body. Future research is also required to study the microscopic pore flows, upon which more detailed parameterization of the porous media can be derived.

Accurate wave forecasting under typhoon conditions is essential for coastal safety in the Pearl River Estuary. This study explores the use of Random Forest (RF) and Long Short-Term Memory (LSTM) models to predict significant wave heights, using SWAN-simulated data from 87 historical typhoon events. Ten representative typhoons were reserved for independent testing. Results show that the LSTM model outperforms RF in 3 h forecasts, achieving a lower mean RMSE and higher R², particularly in capturing wave peaks under highly dynamic conditions. For 6 h forecasts, both models exhibit decreased accuracy, with RF performing slightly better in stable scenarios, while LSTM remains more responsive in complex wave evolution. Generalization tests at three nearby stations demonstrate that both models, especially LSTM, retain strong predictive skill beyond the training location. These findings highlight the potential of combining numerical wave models with machine learning for short-term, data-driven wave forecasting in typhoon-prone and observation-sparse regions. The study also points to future improvements through integration of wind field predictors, model updating strategies, and ensemble meteorological data.

Short-term predictions of regional wind waves are crucial for coastal and ocean engineering. In this study, we introduce a novel Swin-Transformer-based model, named ST-RWP (Swin Transformer for Regional Wave Prediction), designed to leverage the spatiotemporal relationships of wind velocities and significant wave heights. The model considers inductive bias to capture both local and global dependencies via Convolution and Swin Transformer layers, enabling accurate short-term wave field predictions on unseen data. A rolled-out prediction scheme is employed to extend the forecast horizon efficiently. Trained on the reanalysis dataset offered by European Center for Medium-Range Weather Forecasts, ST-RWP demonstrates excellent performance in predicting wave fields with lead times of 6 and 12 h. However, the model's accuracy degrades when the lead time exceeds 24 h, primarily due to the limited spatial information available at boundary nodes and the low autocorrelation value for such large time span. The dataset exhibits strong spatial and temporal correlations, which are key to the model's success. Our findings indicate that ST-RWP offers an efficient tool for real-time wave field nowcasting, representing a significant advancement in the application of Transformer-based deep neural networks to wave prediction.