To address the issue of low accuracy in ship trajectory prediction in complex navigable waters, this paper proposes a GRU-Attention-BiLSTM model for ship trajectory prediction. In the encoder part, the Gated Recurrent Unit (GRU) is employed to capture temporal features in trajectory sequences. The decoder adopts a Bidirectional Long Short-Term Memory Network (BiLSTM) integrated with an Attention mechanism to adjust the weights of data features. The model input is based on the longitude, latitude, speed and heading of the ship at the historical moment, and the ship density in the water area after median filtering smoothing is introduced as an additional feature. Using Automatic Identification System (AIS) data from the core port area of Ningbo-Zhoushan Port in March 2024, the model was trained and validated. Quantitative and qualitative comparisons with GRU, LSTM, Seq2Seq-LSTM, Attention-BiLSTM, and Transformer models demonstrate that the proposed model achieves superior prediction performance across different prediction durations and navigation scenarios.

To address the safety and economic requirements for ships navigating the complex ice environments of Arctic waters, this paper proposes a multi-objective improved Sparrow Search Algorithm (SSA) to optimize both wind resistance and ice resistance. The Risk Index Outcome (RIO), calculated by the Polar Operational Limit Assessment Risk Indexing System (POLARIS), and the safe water depth threshold are adopted as constraints to ensure navigation safety and mitigate the impact of resistance on navigation efficiency along Arctic routes. First, meteorological and ice data for the Arctic route are processed, and a grid environment map is constructed according to ship type. Second, safe navigable areas are identified, and a multi-objective function model is established. Finally, the improved sparrow search algorithm is applied to optimize the route and is compared with other typical path planning algorithms to verify the effectiveness and feasibility of the proposed method. The results indicate that the optimal path generated by the improved sparrow search algorithm, based on the multi-objective model of wind and ice resistance, can significantly reduce ship resistance during navigation-achieving a reduction of up to 10.9%. Moreover, there is no significant difference in path length or running time compared with other algorithms. This study provides an economical and reliable optimization solution for ship navigation in Arctic routes.

To study the pitching stabilization performance of super-large ships under severe sea conditions, this paper takes the tanker "KVLCC2" as the research object. A weighting matrix is utilized to stabilize its transfer function model in Mathematica, and the stability of the model is verified using the root trajectory shaping method. Subsequently, a simplified first-order closed-loop gain-shaping algorithm is applied to design the robust controller. In addition, a dual nonlinear feedback control algorithm is proposed to be incorporated into the control system to further enhance its pitching stabilization performance. To validate the effectiveness of the dual nonlinear feedback control system for pitching stabilization, wind scale of 7 and 8 wind and wave models along with perturbation links are introduced into the system for simulation experiments. The experimental results demonstrate that even with a time lag constant of 0.15, the dual nonlinear feedback control system effectively improves the ship's pitching stabilization performance under rough sea conditions. The proposed dual nonlinear feedback control system can provide technical support for the smooth and efficient navigation of super-large ships in varying sea conditions.

This study employs the MARIS model and a convective diffusion model to simulate the diffusion of nuclear wastewater released from Japan. Based on the simulation results, it proposes optimized methods for ballast water exchange to prevent the direct discharge of radioactive ballast water into ports, thereby mitigating potential threats to the ecological environment. The research focuses on the Fukushima nuclear incident and the subsequent continuous release of 1.3 million tons of nuclear wastewater into the ocean. Results indicate that radioactive substances are mainly concentrated in the surface layer of the ocean, with detectable enrichment of radioactive elements such as cesium in seawater and aquatic organisms near the Fukushima nuclear power plant. Consequently, ships operating near eastern Japanese ports are taking in ballast water contaminated with radioactive materials, including cesium-134 and cesium-137. Using a convective diffusion module, the study simulates the variation in radioactive substance concentrations during ballast water exchange at different distances, providing theoretical support for optimizing exchange strategies. The findings show that performing a secondary ballast water exchange more than 20 nautical miles from Japan's coast can reduce radioactive substance concentrations in ballast water to one ten-thousandth of the pre-exchange levels. The conclusions of this study can assist maritime regulatory authorities in formulating effective management measures, thereby contributing to the protection of marine ecosystems.

In the context of port shore power deployment, studying the impact of different policies on port and shipping enterprises is crucial for improving shore power utilization and achieving established emission reduction goals. To explore the policy effects on these enterprises, a Stackelberg game model was constructed with the port as the leader and shipping companies as the follower, incorporating innovation subsidies into the framework. This model aims to address innovation challenges in shore power equipment and examines the combined impact of subsidies and carbon trading policies on port and shipping enterprises. The model is solved using backward induction and numerically simulated via Matlab. The results indicate that in the early stages of emission reduction, subsidy policies help enhance innovation levels, while after the maturation of shore power technology, the implementation of dual policies involving both subsidies and carbon trading is more effective in motivating the industry to develop emission reduction technologies. Therefore, it is recommended that the government take measures to expand market scale, strengthen societal low-carbon awareness, and increase innovation subsidies in the early phase to promote shore power utilization. After the technology matures, the subsidy ratio and carbon price can be adjusted to sustain the utilization of shore power.

To accurately predict the fuel consumption of in service ships, analyze the complex and variable influencing factors of fuel consumption, and quantify their respective impacts, this study selects tankers and bulk carriers for operational data collection and preprocessing. A fuel consumption prediction model based on the Extreme Gradient Boosting (XGBoost) algorithm is established, and factor importance is evaluated using the Gain method. The results demonstrate that the proposed model achieves strong computational and predictive performance, with mean absolute percentage errors of 4.88% and 3.92% for the tanker and bulk carrier models, respectively. Among internal factors, ship speed shows the greatest influence, with weights of 0.671 and 0.429 for the two vessel types. Regarding external factors, navigation environment conditions such as wind and waves also exhibit significant impacts.

To effectively identify vessels using fuel with excessive sulfur content, a reverse calculation method for determining fuel sulfur content was developed based on emission and diffusion characteristics. A Gaussian puff compensation model was applied to estimate the emission source strength of vessels from monitored SO₂ concentrations at designated points. In addition, a computational model for vessel fuel consumption was established using key vessel parameters, including the power and fuel consumption rates of main and auxiliary engines. The proposed method demonstrated superior performance compared to the mainstream carbon balance method in detecting vessels with non-compliant sulfur content, achieving detection and false detection rates of 86.60% and 2.06%, respectively. Over a 30-day continuous monitoring period, the fuel sulfur content of 2,743 vessels was successfully determined, representing an effective detection rate of 82.72%. Among these, 131 vessels were identified as potentially exceeding sulfur limits. Subsequent verification confirmed that 111 vessels used non-compliant fuel, resulting in an assessment accuracy of 84.73%. These findings demonstrate the method's capability to enable real-time monitoring of fuel sulfur content without requiring CO₂ concentration data.

To achieve carbon neutrality, governments and enterprises are accelerating the decarbonization process in the shipping industry. This paper focuses on the Low-Carbon Maritime Supply Chain (LMSC), considering both government policies and consumers' green preferences. A two-stage Stackelberg game model between shipping companies and freight forwarders is developed to determine optimal pricing and carbon emission reduction strategies, while examining the impacts of carbon taxes, government subsidies, and consumers' green preferences on decision-making. The analysis yields three main findings: First, cooperation between freight forwarders and shipping companies maximizes overall profits for the LMSC; however, to achieve higher emission reduction levels, both parties should co-lead the supply chain. Second, government subsidies and enhanced low-carbon awareness produce dual effects: while they help reduce emissions and increase corporate profits, they may also raise TEU market prices for consumers under certain conditions. Third, although carbon taxes significantly improve the low-carbon performance of the LMSC, they reduce profits for all participants and increase TEU market prices.

In the global energy transportation landscape, maritime transport accounts for over 70% of crude oil shipments, making the reliability of its channels paramount to national energy security. Escalating geopolitical tensions have significantly elevated the risk of disruption to critical maritime channels, posing severe challenges to the stability of energy supply chains. To accurately assess this risk, this study employs complex network theory and integrates Automatic Identification System (AIS) trajectory data with vessel capacity weights to construct a global directed weighted network for crude oil maritime transportation, in which critical channels are abstracted as network nodes. Based on this framework, three progressive attack simulation strategies are designed-single channel disruption, compound scenario failure, and optimal disruption sequence-to systematically investigate the multidimensional vulnerability of the network to channel blockages. The findings indicate: 1) Functional differentiation. critical channels exhibit significant functional differentiation. Some are vital for global efficiency; for instance, removing the Strait of Malacca reduces network efficiency by 1.99%. Conversely, others demonstrate structural suboptimality, as exemplified by the removal of the Panama Canal, which paradoxically increases topological efficiency by 2.57%, revealing quantifiable suboptimal paths within the network. 2) Asynchronous vulnerability. The network exhibits asynchronous responses across performance dimensions. While macro-connectivity remains highly robust against single-point or regional failures, the core structure is highly fragile. For example, the network's K-Core value plummets after attacks targeting only four optimal nodes. 3) Non-linear degradation. Under optimal sequence attacks, global network efficiency follows a "U-shaped" trajectory-initially declining before rebounding beyond its original value due to topological reconfiguration. Notably, the collapse of the core structure occurs significantly earlier than the deterioration of overall transmission functionality, with the latter even showing a paradoxical recovery in the later stages of the attack. This study elucidates the underlying failure mechanisms of the global crude oil maritime transportation network under channel blockages, offering a new analytical paradigm and decision-making basis for ensuring national energy transportation security and enhancing the resilience of global supply chains.

In response to the global sulfur cap regulations established by the IMO MARPOL Convention and the management requirements of China's ship emission control areas, it is imperative to improve the efficiency and accuracy of maritime ship emission monitoring. This study proposes a three-dimensional "Terrestrial-Maritime-Aerial" monitoring technology for ship exhaust emissions, which integrates shore stations, bridges, ships, and mobile platforms into a unified network to address the practical monitoring demands of diverse and complex navigation environments. Additionally, an automatic peak signal recognition algorithm has been developed to enable intelligent remote monitoring of ship exhaust emissions and facilitate precise source tracing. Finally, an integrated intelligent control system was constructed, incorporating intelligent remote monitoring, precise source tracing, and enforcement verification, thereby promoting seamless information flow across multiple aspects of maritime supervision.