This study presents a novel approach to predicting ship speed based on real-time voyage observation data, aiming to enhance maritime safety and operational efficiency. Observational data from a 20,000-ton bulk carrier, including variables such as latitude, longitude, GPS orientation, wind direction, wind speed, and main engine parameters, were collected and preprocessed to mitigate noise and handle missing values. Six machine learning models—the Backpropagation (BP) Neural Network, Support Vector Regression (SVR), Decision Tree (DT), Random Forest (RF), XGBoost, and LightGBM—were employed to develop predictive models. Among these, the LightGBM model demonstrated the highest prediction accuracy, achieving a Root Mean Squared Error (RMSE) of 0.188, Mean Absolute Error (MAE) of 0.149, and a coefficient of determination (R²) of 0.978. The results highlight the potential of the LightGBM model in optimizing ship navigation and improving maritime operational efficiency. These findings offer a reliable foundation for further advancements in predictive maritime technologies and route optimization.

To enhance the passing capacity of the Bailongtan Ship Lock on the Hongshui River, this study focused on the design scheme of its water conveyance system reconstruction and expansion project. A three-dimensional mathematical model meeting the experimental accuracy requirements was established based on the RNG k-ε turbulence model and the Volume of Fluid (VOF) free-surface tracking method. A 1:30 scale ship lock water conveyance system physical model was built and used the independently developed system for hydraulic test monitoring, acquisition, and control. Experimental research on the hydraulic characteristics and shape optimization of the water conveyance system was carried out. The experimental results show that, under the condition of a maximum head difference of 16.0 m between the upstream and downstream of the ship lock, in the design scheme, the flow in the corridor after the filling valve fails to diffuse adequately, forming a high-velocity zone and a significant pressure difference between the inner and outer sides, which poses an operational risk. By optimizing the shape of the corridor after the valve (deepening the bottom end by 2.0 m and adjusting the turning angle from 75° to 70°), the range of the high-velocity zone can be shortened from 3.0 m to 1.5 m. The pressure difference between the inner and outer sides of the corridor at the horizontal turning section is reduced by 19.2% from 5.35 m to 4.32 m of the pressure head at the moment of maximum flow rate, and the velocity in the horizontal section is less than 15 m/s. Physical model tests confirmed these improvements, with mooring forces within safety limits (longitudinal ≤ 32 kN, transverse ≤ 16 kN). The research findings indicate that integrating numerical simulation with physical model testing can effectively mitigate risks in the original design of the ship lock water conveyance system. This approach notably enhances the reliability and safety of the design scheme, as demonstrated by the significant reduction in high-velocity zones and pressure differentials. Moreover, it offers a robust scientific basis and practical technical reference for in-depth hydraulic research and targeted optimization of ship lock water conveyance systems.

Sustainable port development in coastal regions necessitates robust frameworks for quantifying hydrodynamic risks under climate change. To bridge the gap between generic guidelines and site-specific resilience planning, this study proposes and applies a numerical modeling-based risk assessment framework. Within the context of the Port Master Plan, the framework is applied to the critical case of Takoradi Port in West Africa, employing a two-dimensional hydrodynamic model to simulate current fields under three current regimes, “Normal”, “Stronger”, and “Estimated Extreme” scenarios, for the first time. The model quantifies key hydrologic parameters such as current velocity and direction in critical zones (the approach channel, port basin, and berths), providing actionable data for the Port Master Plan. Key new findings include the following: (1) Northeastward surface currents, driven by the southwest monsoon, dominate the study area; breakwater sheltering creates a prominent circulation zone north of the port entrance. (2) Under extreme conditions, the approach channel exhibits amplified currents (0.3–0.7 m/s), while inner port areas maintain stable conditions (<0.1 m/s). (3) A stark spatial differentiation in designed current velocities for 2–100 years return periods, where the 100-year extreme current velocity in the external approach channel (0.87 m/s at P1) exceeds the range in the internal zones (0.01–0.15 m/s) by approximately 5 to 86 times. The study validates the framework’s utility in assessing hydrodynamic risks. By integrating numerical simulation with risk assessment, this work provides a scalable methodological contribution that can be adapted to other port environments, directly supporting the global pursuit of sustainable and resilient ports.