The 80th session of the IMO Maritime Environment Protection Committee (MEPC 80) adopted the 2023 IMO Strategy on the Reduction of GHG Emissions from Ships (2023 IMO GHG Strategy), with enhanced targets to tackle harmful emissions. This study strives to provide an exact interpretation of the target of the 2023 IMO GHG Strategy and reveal the technical requirements therein. Decarbonization targets were expressed in IMO GHG emission scenarios for specifications. Model calculations and parameterizations were in line with IMO GHG reduction principles and decarbonizing practices in the shipping sector to avoid the prejudicial tendency of alternative fuels and the overestimated integral efficiency of short-term measures in existing predictions. IMO DCS data were used for the first time to gain reliable practical efficiencies of newly adopted regulations and further reduce the model uncertainty. The results demonstrated that the decarbonization goals for emission intensity were actually 51.5–62.5% in the IMO GHG reduction scenarios, which was much higher than the IMO recommended value of 40% as the target. Combined with the continuous applications of short-term measures, onshore power and regulations were required to contribute their maximum potential no later than the year 2030. Even so, considerable penetration (15.0–26.0%) of alternative fuels will be required by 2030 to achieve the decarbonization goals in the 90% and 130% scenarios, respectively, both far beyond the expected value in the 2023 IMO GHG Strategy (i.e., 5–10%). Until 2050, decarbonization from alternative fuels is required to achieve ~95%. Sustainable biodiesel and LNG are the necessary choices in all time periods, while the roles of e-methanol and e-ammonia deserve to be considered in the long term. Our findings highlight the intense technical requirements behind the 2023 IMO GHG Strategy and provide a pathway option for a fair and impartial transition to zero GHG emissions in the shipping sector, which might be meaningful to policymakers.

The lithium battery energy storage system (LBESS) has been rapidly developed and applied in engineering in recent years. Maritime transportation has the advantages of large volume, low cost, and less energy consumption, which is the main transportation mode for importing and exporting LBESS; nevertheless, a fire accident is the leading accident type in the transportation process of LBESS. This paper applied fault tree analysis and Bayesian network methods to evaluate the fire accident risk of LBESS in the process of maritime transportation. The Bayesian network was constructed via GeNIe 2.3 software, and the probability of LBESS fire accidents during maritime transportation was calculated based on the probability of basic events occurring. The results showed that an unsuitable firefighting system for putting out lithium battery fires, high humidity, and monitoring equipment without a real-time alarm function have the most significant influence on the occurrence of LBESS fire accidents during maritime transportation. The research work of this paper provides a theoretical basis for the risk assessment of LBESS during maritime transportation.

The prediction of fuel consumption and Carbon Intensity Index (CII) of ships is crucial for optimizing decarbonization strategies in the maritime industry. This study proposes a ship fuel consumption prediction model based on the Long Short-Term Memory with Self-Attention Mechanism (SA-LSTM). The model is applied to a container ship of 2400 TEU to predict its hourly fuel consumption, hourly CII, and annual CII rating. Four different feature sets are selected from these data sources and are used as inputs for SA-LSTM and another ten models. The results demonstrate that the SA-LSTM model outperforms the other models in prediction accuracy. Specifically, the Mean Absolute Percentage Error (MAPE) for fuel consumption predictions using the SA-LSTM model is reduced by up to 20% compared to the XGBoost and by up to 12% compared to the LSTM model. Additionally, the SA-LSTM model achieves the highest accuracy in annual CII predictions.

The Carbon Intensity Index (CII) exerts a substantial impact on the operations and valuation of international shipping vessels. Accurately predicting the CII of ships could help ship operators dynamically evaluate the possible CII grate of a ship at the end of the year and choose appropriate methods to improve its CII grade to meet the IMO requirement with minimum cost. This study developed and compared five CII predicting models with multiple data sources. It integrates diverse data sources, including Automatic Identification System (AIS) data, sensor data, meteorological data, and sea state data from 2022, and extracts 21 relevant features for the vessel CII prediction. Five machine learning methods, including Artificial Neural Network (ANN), Support Vector Regression (SVR), Least Absolute Shrinkage and Selection Operator (LASSO), Extreme Gradient Boosting (XGBoost), and Random Forest (RF), are employed to construct the CII prediction model, which is then applied to a 2400 TEU container ship. Features such as the mean period of total swell, mean period of wind waves, and seawater temperature were considered for inclusion as inputs in the model. The results reveal significant correlations between cumulative carbon emissions intensity and features like cumulative distance, seawater temperature, wave period, and swell period. Among these, the strongest correlations are observed with cumulative distance and seawater temperature, having correlation coefficients of 0.45 and 0.34, respectively. Notably, the ANN model demonstrates the highest accuracy in CII prediction, with an average absolute error of 0.0336, whereas the LASSO model exhibits the highest error of 0.2817. Similarly, the ANN model provides more accurate annual CII ratings for the vessel. Consequently, the ANN model proves to be the most suitable choice for cumulative CII prediction.

To mitigate the risk of hydrogen leakage in ship fuel systems powered by internal combustion engines, a Bayesian network model was developed to evaluate the risk of hydrogen fuel leakage. In conjunction with the Bow-tie model, fuzzy set theory, and the Noisy-OR Gate model, an in-depth analysis was also conducted to examine both the causal factors and potential consequences of such incidents. The Bayesian network model estimates the likelihood of hydrogen leakage at approximately 4.73 × 10⁻⁴ and identifies key risk factors contributing to such events, including improper maintenance procedures, inadequate operational protocols, and insufficient operator training. The Bow-tie model is employed to visualize the causal relationships between risk factors and their potential consequences, providing a clear structure for understanding the events leading to hydrogen leakage. Fuzzy set theory is used to address the uncertainties in expert judgments regarding system parameters, enhancing the robustness of the risk analysis. To mitigate the subjectivity inherent in root node probabilities and conditional probability tables, the Noisy-OR Gate model is introduced, simplifying the determination of conditional probabilities and improving the accuracy of the evaluation. The probabilities of flash or pool fires, jet fires, and vapor cloud explosions following a leakage are calculated as 4.84 × 10⁻⁵, 5.15 × 10⁻⁵, and 4.89 × 10⁻⁷, respectively. These findings highlight the importance of strengthening operator training and enforcing stringent maintenance protocols to mitigate the risks of hydrogen leakage. The model provides a valuable framework for safety evaluation and leakage risk management in hydrogen-powered ship fuel systems.