Ports are striving for innovative technological solutions to cope with the ever-increasing growth of transport, while at the same time improving their environmental footprint. An emerging technology that has the potential to substantially increase the efficiency of the multifaceted and interconnected port processes is the digital twin. Although digital twins have been successfully integrated in many industries, there is still a lack of cross-domain understanding of what constitutes a digital twin. Furthermore, the implementation of the digital twin in complex systems such as the port is still in its infancy. This paper attempts to fill this research gap by conducting an extensive cross-domain literature review of what constitutes a digital twin, keeping in mind the extent to which the respective findings can be applied to the port. It turns out that the digital twin of the port is most comparable to complex systems such as smart cities and supply chains, both in terms of its functional relevance as well as in terms of its requirements and characteristics. The conducted literature review, considering the different port processes and port characteristics, results in the identification of three core requirements of a digital port twin, which are described in detail. These include situational awareness, comprehensive data analytics capabilities for intelligent decision making, and the provision of an interface to promote multi-stakeholder governance and collaboration. Finally, specific operational scenarios are proposed on how the ports digital twin can contribute to energy savings by improving the use of port resources, facilities and operations.

Digital twins have gained tremendous momentum since their conceptualization over 20 years ago, as more and more domains discover their value in driving efficiencies and reducing costs, while enabling technologies continue to advance. Originally aimed at product optimization and intelligent manufacturing, the range of applications for digital twins now spans entire complex, often highly interconnected systems such as ports, cities, and supply chains. Despite the increasing demand for sophisticated digital twinning solutions across all domains and scopes, their development is often still constrained by differing definitions, different understandings of their functional scope and design, and a lack of concrete methodology toward implementing a comprehensive digital twinning solution. Although there are already papers that evaluate the capabilities of existing digital twinning solutions on the basis of maturity levels, these usually consider the object to be twinned in isolation and are often domain-specific. With this article we address exactly this gap discussing how interoperability of digital twins can break physical boundaries of an isolated system, enabling system of systems joint optimization. We therefore consider interoperable digital twins to be the most mature twinning platforms, thus, we discuss in detail six digital twin maturity levels, departing from the interrelated contexts of ports, cities, and supply chains. Examples drawn from these domains demonstrate the need for interoperability toward optimizing processes and systems in realistic contexts, rather than in assumed isolation.

Ports are striving to improve operational efficiency in the context of constantly growing volumes of trade. In this context, port terminal storage yard operation is key, since complexity and poor coordination lead to containers stacked without consideration of retrieval schedules, resulting in time- and energy-consuming reshuffling operations. This problem, known as the block relocation (and retrieval) problem (BRP), has recently gained considerable attention. Indeed, there are promising solutions to the BRP. However, the literature views the problem in isolation, optimizing one operational parameter for one of the many port stakeholders. This often leads to efficiency losses since port processes involve different stakeholders and port parts. In this work, we explicitly focus on scheduling trucks for pick-up for hinterland distribution. Appointments are often postponed in order to minimize reshuffling operations, leading to losses for the transport forwarders and decreasing the competitiveness of the port. We discuss the trade-off between minimizing container reshuffling operations while maintaining scheduled time windows for container retrieval. We describe the multi-objective optimization problem as a weighted sum of the two objectives. Given the complexity of the problem, we also present a greedy heuristic. Our results indicate that the number of schedule deviations can be reduced without significantly affecting the number of relocations compared to solutions that consider only the latter. Ideally, a weighting of 0.4 and 0.6 should be applied, reflecting schedule deviations and relocations, respectively, to achieve the highest joint optimization potential. This demonstrates that in complex environments, such as ports, with multiple interacting stakeholders and processes, coordination of solutions yields significant benefits.

Quay cranes (QCs) play a vital role in ship-to-shore operations, enabling the seamless transfer of cargo between sea and land. However, increasing trade volumes require faster and more costeffective container handling, exerting significant pressure on QCs and leading to greater wear on critical components such as wires, hoists, and rope clamps. While operations research has explored maintenance scheduling to improve terminal performance, comparatively little work has examined how machine learning can exploit the growing volume of QC monitoring and operational data to predict breakdowns before they occur. This study contributes to this area by integrating terminal operations data, QC monitoring logs, and meteorological observations into a unified analytical framework. We employ explainable artificial intelligence (XAI), using both global and local SHapley Additive exPlanations (SHAP) to identify the operational and environmental factors most strongly associated with QC failures and to illustrate concrete, instance-level examples of how specific conditions contribute towards breakdowns. In parallel, we develop a robust machine learning pipeline built around nested cross-validation to assess the predictive capability of multiple classifiers for forecasting QC breakdowns. Our XAI analysis reveals that breakdown risk is closely linked to QC working time, the distribution of moves across simultaneously operating QCs, hoist overload and trolley alignment warnings, and adverse weather conditions. Among the evaluated models, LightGBM achieved the highest predictive accuracy, reaching up to 83% in identifying breakdown-prone scenarios. These findings demonstrate the feasibility and value of data-driven predictive maintenance for QCs, providing insights that support safer, more reliable, and more efficient terminal operations.

Efficient port operations depend on the disruption free operation of quay cranes (QCs), which transfer containers between vessels and internal trucks. As global container through put rises, QCs face increased pressure, resulting in accelerated wear and tear. This can lead to QC downtime, which could interrupt the entire chain of port operations. Therefore, timely identification and prediction of critical errors is essential to enable timely maintenance to lower the risk of downtime. This study utilizes two years of QC monitoring data, enriched with weather conditions and terminal operational context, alongside twenty critical error events identified by the terminal operator. The goal is to predict the occurrence and timing of these critical errors through a three-stage machine learning model. The first stage predicts the type of the next critical event based on historical error patterns, warnings, and contextual data. The second stage estimates a time window in which the event will occur. The third stage refines timing predictions when more than one hour remains. The first two stages are formulated as multiclass classification problems, and the third as a regression task. All stages utilize eXtreme Gradient Boosting (XGBoost). SHapley Additive exPlanations (SHAP) are used to identify influential features. Results show that the model predicts the next critical error type with 83% accuracy and its immediacy with 71% accuracy. However, approximating the timing of events anticipated to occur beyond one hour remains challenging. These findings support proactive maintenance planning and operational adjustments, helping port operators mitigate disruptions and enhance QC reliability.

Enhancing fuel efficiency in ferry operations is essential for reducing emissions and advancing maritime sustainability. This study presents a data-driven framework that uses second-level GPS data enriched with operational and environmental variables to identify and explain fuel consumption patterns. Vessel movements are segmented into trip legs and journeys, and operational metrics such as speed, wind exposure, and fuel use are computed. A hybrid machine learning approach combines unsupervised clustering to detect recurring operational patterns with gradient boosting models and explainable methods to quantify feature impacts. The framework achieves strong performance, with a cluster classification accuracy of 94 percent and a coefficient of determination of 0.97 for fuel prediction. Results indicate that operational speed is the dominant driver of fuel consumption, while analysis of captain assignments reveals the influence of human factors. The proposed framework provides actionable insights for speed management and operational optimization, enabling cost-effective emission reductions in ferry services.