Smart Seaport and Maritime Transport Management

1. Introduction

Smart seaport and maritime transport management constitute a prominent and continually evolving field [1,2], focusing on the application of advanced technological solutions to enhance efficiency, sustainability, and safety within the maritime sector. The integration of smart systems into seaports and maritime transport is transforming traditional practices into intelligent operations that leverage the Internet of Things (IoT), artificial intelligence (AI), big data analytics, operations research, and digitalization systems [3,4,5]. This transformation is crucial for addressing the growing demands of global shipping and supply chain logistics.

The early 2020s have witnessed significant innovations in smart seaport and maritime transport management. For instance, studies by [6,7,8] have explored the applications of IoT and deep learning on vessel monitoring and trajectory prediction, revealing substantial improvements in real-time tracking and management. Similarly, research by [9,10] has re-evaluated maritime logistics through AI-driven optimization models, demonstrating enhanced efficiency in cargo handling and port operations. The implementation of digitalization systems in smart seaport and maritime transport areas, as discussed by [11,12,13], has further streamlined operations, reducing human error and increasing throughput. These advancements illustrate the broad scope and complex challenges inherent in developing smart maritime systems.

Despite these achievements, numerous challenges remain in fully understanding and implementing smart technologies across maritime environments. The diversity of models and conditions under which maritime systems operate means that many aspects are still not completely understood [14,15]. For example, the integration of big data analytics in optimizing cargo logistics requires further exploration [16]. Additionally, the application of data-driven decision support systems in seaport operation and energy management, presents both opportunities and challenges that need to be thoroughly investigated [17,18]. The increasing complexity of cybersecurity threats in smart seaports also demands continuous vigilance and innovation [19].

This Special Issue, titled “Smart Seaport and Maritime Transport Management,” seeks to contribute to the advancement of this evolving field. It aims to provide a comprehensive platform for researchers, academics, and industry professionals to share their original research, case studies, and innovative solutions. The focus will be on addressing the challenges, opportunities, and best practices associated with implementing and operating intelligent systems in seaport and maritime contexts.

2. Published Papers

A comprehensive review by Alamoush and Ölçer (Contribution 1) provides valuable insights into the architecture of autonomous navigation systems of maritime autonomous surface ships, including autonomous navigation architecture, a decision-making and action-taking system, situational awareness and associated technologies, sensor fusion technology, collision avoidance subsystems, motion control and path following, and mooring and unmooring. The results highlight the intricate and interdependent nature of the components that facilitate autonomous navigation. Managers and practitioners can use the findings to better understand and implement these systems.

Li et al. (Contribution 2) present a new deep reinforcement learning model for transportation planning, yard selection optimization, and equipment scheduling in dry bulk cargo terminals. Unlike the existing studies that directly formulate the solution space, the proposed model integrates graph structures for precise yard mapping with mixed-integer programming to enforce operational constraints while maintaining computational efficiency. Furthermore, the proposed model incorporates Dueling Double Deep Q-Network to enhance optimization performance and accelerate the learning process. The experimental results provide valuable insights to the overall management of dry bulk cargo terminals.

Qiu et al. (Contribution 3) provide an improved lightweight ton bag detection algorithm, “You Only Look Once version 8 -Ton Bag” (YOLOv8-TB), to address the problems of inaccurate ton bag identification, large model sizes, and long computation times in traditional freight transportation. The developed algorithm introduces a modified Spatial Pyramid Pooling Fast module with Large Kernel Attention to improve the feature expression performance, and then designs a new convolution block to reduce the spatial and channel redundancy between features in the backbone network while achieving lightweight requirements. The results indicate that the algorithm strengthens small target detection capabilities and improves the accuracy of small target positioning and identification.

Vorkapić et al. (Contribution 4) provides valuable insights to interpretable machine learning for fuel consumption prediction in very large gas carrier (VLGC) ship propulsion. The developed methodology includes comprehensive data exploration, cleaning, and verification, followed by feature selection and training of linear regression and decision tree models. The models underscore not only the interdependencies of variables, but also the importance of feature selection, model complexity, performance, and interpretability in a marine engineering context. This research highlights the need for the interpretability of machine learning models to ensure their reliability and adherence to domain experts and safety standards.

Albo-López et al. (Contribution 5) present an analytical model for the contribution of onshore power supply and batteries in reducing emissions from Ro-Ro ships in ports. The proposed model incorporates three critical factors: engine’s behavior, basic navigation criteria, and different alternatives. Then, the model is integrated with a cost calculation method to select alternatives for Ro-Ro ships, by comparing their costs. The results indicate that incorporating batteries into the ship produces greater savings in annual costs than onshore power supply. The cost savings from onshore power supply depend on the range of prices in each port.

Argyriou and Tsoutsos (Contribution 6) establish a novel operational risk-management method for Internet of Things (IoT) devices in port environments to address operational risks in terms of cybersecurity vulnerabilities and potential disruptions. Their basic idea is to identify the potential security risks (e.g., unauthorized access, cyberattacks, and malware) associated with IoT devices and then explore strategic measures and best practices to mitigate these risks, including risk avoidance, reduction, sharing, and retention strategies. The developed method provides actionable insights and guidelines for port authorities and stakeholders to safeguard their IoT infrastructure and maintain operational stability.

Qiao et al. (Contribution 7) develop a novel ship scheduling and speed optimization method for naval escort operations from maritime security perspectives. The problem is formulated as a mixed-integer programming model that incorporates fleet departure times, fleet grouping, and ship speed across different legs as model decisions, aiming to minimize cargo delay costs and fuel consumption costs simultaneously. To solve the problem efficiently, this research derives the lower bounds of certain parameters within the model based on the problem characteristics, achieving a more compact and efficient model form. The numerical experiments provide robust evidence for the model’s practical applications and demonstrate its potential to maintain economic viability and environmental sustainability.

Xia et al. (Contribution 8) propose a novel dual-component model to analyze the inherent structure and potential vulnerabilities of the container transportation network in the Beibu Gulf Sea areas. The developed model is characterized by a container transportation network constructed with the navigation data, aiming to represent the spatial topology and the functional status of ports. Furthermore, a cascading failure model is integrated, which considers port overload capacity to analyze port failure modes and load redistribution strategies on the cascading failure. This research provides better understanding on the spatial structure and vulnerability of container shipping networks in the Beibu Gulf Sea areas.

Issa-Zadeh et al. (Contribution 9) present a data-driven sensitivity analysis model to explore realistic power-generating options for reducing carbon emissions in the Port of Valencia. This approach comprises varying parameters, coefficients, and external elements in power consumption and deploying renewable energies. Through sensitivity analysis, policymakers and managers discover each scenario’s efficacy and find the best decarbonization strategies. The results demonstrate that gradually replacing traditional fossil fuels for electricity generation with renewables is a reasonable and realistic option for emission reduction.

Chu et al. (Contribution 10) focus on the conflicts associated with automated guided vehicles (AGVs) and unmanned container trucks (UCTs) at automated container terminals. This research examines the interacted relationships between AGVs and UCTs and then develops a synergistic scheduling method to avoid the conflicts. The developed method is characterized by dual optimization models that considers conflict-free paths for both AGVs and UCTs, as well as strategies for conflict resolution. Advanced genetic algorithms are engineered to address the task-dispatching model, and A* search algorithm was adapted to derive conflict-free and conflict resolution paths. The experimental results highlight the superior performance of the developed method to optimize the total operational costs.

Qu et al. (Contribution 11) propose a mechanism to select container handling efficiency for arriving vessels under port congestion. The proposed method takes vessel waiting time as a key modeling consideration, which is predicted and quantified by queueing theory, along with information on vessel schedules, cargo handling volumes, and available port operating time windows. By solving a mixed-integer nonlinear programming model aimed at minimizing the total service costs, the method can design an optimized container ship schedule, including handling efficiency and in-port handling time. The results indicate that the method enables shipping companies to flexibly design liner schedules, balancing the economic costs and service reliability.

Wang and Zou (Contribution 12) propose a berth-tug co-scheduling method to address the dynamic changes in vessel preferences for berth lines caused by the deployment of shore-based power equipment in major ports. The developed method incorporates task sequence and towing scheduling as model decisions, aiming to reduce the economic costs associated with vessel delay and shore power cable connection as well as the environmental costs related to the pollutants from the main engines of tugs and auxiliary engines of container ships. A solution approach that integrates the immune particle swarm optimization algorithm and the commercial solver is designed to solve the problem. The results demonstrate that the collaborative scheduling method exhibits superior performance in reducing the overall costs.

3. Perspectives

The collection of 12 papers in this Special Issue fills many particular gaps in our knowledge of smart seaport and maritime transport management areas, including AI-driven optimization in seaports, operational risk management and cybersecurity, and data-driven analytics for shipping operations. Indeed, one single Special Issue cannot represent the entire research field, but it can try to demonstrate several potential research perspectives that need further exploration. In particular, future research should focus on developing scalable AI-driven optimization models that can be adapted to various port types and cargoes. Moreover, interpretable and trustworthy machine learning models for predictive maintenance, safety management, and emission control should be investigated. The integration of object detection and tracking algorithms with automated handling systems to enable real-time adjustments and optimizations in cargo handling processes should be explored. More sophisticated scheduling models that account for real-time data from IoT sensors and AIS systems should be investigated to enable proactive and responsive decision-making. The integration of cybersecurity measures with automated handling and traffic management should be investigated to ensure holistic protection.

By pursuing these research directions, seaport and maritime industries can continue to advance towards smarter, safer, and more sustainable operations. Continued collaboration between researchers, industry professionals, and policymakers will be essential to overcome challenges and seize opportunities in this evolving field.