Journal of Marine Science and Engineering

Accurate short-term container throughput volume (CTV) forecasting is crucial for optimizing yard management and port operational efficiency. However, conventional forecasting frameworks typically assume deterministic vessel-side container volumes, neglecting the lag and uncertainty inherent to Electronic Data Interchange (EDI) pre-allocation data in terminal operations. To address these critical gaps, we develop a short-term forecasting framework structured around fine-grained Route-Terminal combination entities, grounded in the real-world operational requirements of South China Container Terminals (SCCTs) in Shenzhen. To enhance predictive robustness against operational volatility, we propose an improved ensemble methodology “Per-item and Global Greedy Ensemble” strategy, which apply greedy ensemble algorithm in different entities and provides a fallback global ensemble for few-record entities. We conduct a comprehensive evaluation of various models, including statistical and state-space models, gradient boosting models, classic deep learning architectures, and time series language models (TSLMs) across the following dual granularities: micro-level entity scale and macro-level daily business aggregation. Experimental results reveal distinct model advantages based on container types as follows: for continuous laden container flows, the proposed per-item greedy ensemble shows competitive performance at the daily aggregation level, whereas tree-based models perform better for sparse and irregular container flows. Overall, the decomposed entity framework and per-item ensemble strategy provide terminal operators with actionable decision support to improve short-term scheduling flexibility and resource utilization in stochastic port environments.

Wake losses constrain power capture in deep-offshore floating wind farms. Unlike fixed-bottom turbines, yaw control in floating turbines changes both wake propagation and aerodynamic thrust; the resulting platform repositioning further alters wake overlap. To investigate the coupled effects of yaw commands, platform displacement, wake distribution, and power output, this study proposes a repositioning-aware farm-level yaw optimization strategy. A steady-state analytical wake model, aerodynamic thrust calculation, and the quasi-static mooring solver MoorPy are coupled to establish a flow–displacement model, which is validated against OpenFAST simulations. The model is then embedded in a genetic algorithm to identify yaw-angle combinations that maximize farm power. An aligned floating wind farm equipped with NREL-5MW turbines is used to examine the effects of wind conditions, mooring-line length, and layout. The results reveal competing effects of yaw-induced wake deflection and platform repositioning. Under relatively slack mooring conditions, repositioning dominates changes in the farm’s wake distribution. The proposed strategy increases farm power across the tested wind conditions. The maximum gain of 17.25% is achieved at a wind direction of 270° and a mooring-line length factor $\alpha =0.9$ (mooring-line length of 830.47 m), a mooring layout of (60°, 180°, 300°). Directly applying fixed-bottom yaw strategies may yield limited gains or even reduce power.

Abandoned delta lobes worldwide face severe net erosion driven by chronic sediment starvation and intensifying marine hydrodynamic forcing, which poses pervasive threats to nearshore and offshore engineering infrastructure, particularly delta zones with dense subsea energy facilities. This study investigates the multi-scale morphodynamic evolution of the abandoned subaqueous Diaokou Lobe (Yellow River Delta) over a 50-year period (1976–2026), combining multi-source bathymetric mapping, sediment sampling, and year-round hydrodynamic monitoring to assess natural and human-driven geomorphic changes. Four sequential evolutionary stages with falling erosion rates are identified following the 1976 river avulsion: rapid erosion (>0.6 m yr⁻¹, 1976–1986), gradual erosion (0.2–0.3 m yr⁻¹, 1986–1996), erosional adjustment (<0.1 m yr⁻¹, 1996–2016), and dynamic equilibrium (<0.05 m yr⁻¹, 2016–2026). Monsoons trigger annual seabed fluctuations of up to 1 m in shallow zones, while winter cold surge storms dominate short-term erosion and make a disproportionate contribution to annual sediment transport. Natural marine processes are the dominant long-term driver of the morphological evolution, whereas anthropogenic activities—most notably the Chengdao oilfield facilities—create growing localized erosion hotspots and become increasingly important as natural erosion rates decline. The four-stage sequence is proposed as a conceptual framework for the reworking of fine-grained abandoned deltas, providing targeted risk evaluation for the Chengdao offshore oilfield with hundreds of platforms and thousands of kilometers of subsea pipelines, as well as general technical references for erosion control and sustainable coastal management across sediment-starved muddy deltas worldwide.