Marcela Castro

Background: Digitalisation has increased the volume and strategic importance of data exchanged across heterogeneous organisational and technological environments in maritime-port logistics, yet persistent failures in data governance constrain interoperability, coordination, and effective data use. This study examines which data-governance failures are documented (RQ1), their associated impacts (RQ2), and the governance mechanisms proposed or implemented in response (RQ3). Methods: A systematic review was conducted following the PRISMA 2020 protocol, searching Scopus and Web of Science and combining AI-assisted title/abstract screening with human adjudication and a false-negative recovery audit. Results: A total of 106 studies published between 2017 and 2026 were included. The synthesis identified nine failure categories, dominated by system fragmentation and information silos, present in 82 studies (77.4%), with markedly higher counts than any other category across every impact dimension examined. Established mechanisms such as CISE coexist with uncoordinated, emerging approaches, including blockchain and Data Mesh, revealing that technology is outpacing governance; generic frameworks such as DAMA-DMBOK are only marginally represented, reflecting a literature gap rather than unsuitability. Conclusions: Organisational and cultural barriers emerged as a comparatively underexplored dimension, indicating that effective maritime data governance requires technical interoperability, institutional coordination, and organisational capacity together, rather than technical solutions alone.

Unmanned and autonomous systems are increasingly investigated in maritime-port operations, but evidence remains fragmented across platforms, applications, and maturity levels. This review combined the PRISMA-based screening of Scopus publications (2010–2026), VOSviewer bibliometric mapping, and structured technical coding. Of 1030 records, 86 studies met the eligibility criteria. Sensing, imaging, and perception were the most represented capabilities, followed by autonomy, navigation, and control. The cross-platform synthesis showed complementarity rather than substitution: platform suitability depends on physical access and task requirements, whereas interoperability, communication continuity, and validation maturity are shared constraints across platform families. Validation coding identified 15 conceptual studies, 14 simulations, 29 controlled experiments, 27 field or port validations, and one documented operational deployment. Decision-support coding identified 19 studies with no explicit contribution, 53 providing information or situational awareness, seven supporting vehicle- or mission-level planning and optimisation, and seven providing recommendations, priorities, allocations, or optimised alternatives for operational or managerial decisions; no coded record explicitly reported a measured improvement in decision outcomes. The evidence therefore supports technological feasibility and information provision more strongly than routine operational readiness or demonstrated improvement in managerial decision outcomes. Future research should prioritise repeated multi-port validation, integration with operational information systems, and comparative evaluation of technology-supported decisions.

Big Data platforms are expected to unify data engineering, governance and machine learning in one environment, and the data lakehouse has become the dominant architectural answer. Empirical evaluations on real operational data remain scarce, and those that exist tend to validate a downstream model rather than the architecture itself. This study designs, implements and evaluates a governed data lakehouse following Design Science Research. The artefact organises Apache Spark, Delta Lake, Unity Catalog and MLflow into a medallion architecture, and is exercised on operational data from the Port of Sines: 36,773 reporting events yielding 8148 berth visits by 1923 vessels between October 2020 and September 2024. The architecture is evaluated against explicit criteria rather than by proxy. Ingestion throughput stays between 16.8 and 18.5 thousand records per second as volume quadruples; the curated Gold layer answers analytical queries 100 times faster than recomputation from source and compacts storage 6.6-fold; an explicit quality ledger and a physical-bound quarantine make governance auditable and measurably beneficial downstream, restoring a correlation structure that 55 out-of-bound values had erased; and an incremental refresh path updates the analytical layer in 0.98 ms at the weekly cadence, at a cost that does not grow with accumulated history. A berth-time regression under rolling-origin validation, benchmarked against tuned ensembles, operational heuristics and time-aware sequence models, serves as the analytical probe rather than as the contribution. The study contributes a measured, replicable reference architecture for governed Big Data analytics.

Background: Accurate prediction of vessel time at berth is essential for smart berth planning, yet berth-allocation research typically treats processing time as a given input rather than a learned variable. This study develops a governed data lakehouse blueprint for port operational data and uses berth-time prediction at the Port of Sines, Portugal, to establish what routinely collected administrative records support. Methods: Following a design science research approach, a Bronze–Silver–Gold medallion pipeline was realised twice from one design, on a managed cloud platform and on single-node open-source components, demonstrating portability rather than vendor dependence. Four years of administrative data (October 2020 to September 2024) yielded 8148 berth visits. Results: Under rolling-origin temporal validation across five cut-offs, a Random Forest regressor attained a mean R² of 0.260 and a mean absolute error of 10.1 h, against 13.5 h for the median-stay heuristic, predicting 52.6% of visits within six hours. SHapley Additive exPlanations identified the vessel’s own previous stay, the berth and vessel size as the strongest predictors. Pipeline measurement shows near-linear scaling and a hundredfold query speed-up over raw-source recomputation. Conclusions: Predictive accuracy remains bounded by the absence of exogenous operational variables; the contribution is the governed data foundation that berth planning requires.

Global seaports play a pivotal role in international supply chains; however, prevailing port performance evaluation frameworks remain predominantly intraport-oriented, limiting their capacity to support sustainability transitions and the integration of Environmental, Social, and Governance (ESG) criteria. Although ports are increasingly conceptualised as multiscale systems embedded within maritime and inland networks, existing approaches remain fragmented across intraport, foreland (seaside connectivity) and hinterland dimensions. Using a systematic literature review following PRISMA 2020, combined with bibliometric mapping through VOSviewer and covering 2019–2024, this study adopts a two-stage analytical design. First, a broad corpus of 238 peer-reviewed articles is used to develop a six-category port performance framework. Second, this corpus is refined to 95 articles focused on container ports, examined by integrating six methodological approaches with three spatial scales. This layered design ensures that the broad corpus defines the categories, while the refined corpus supports the multiscale application of the matrix. The findings reveal a persistent dominance of intraport-focused and efficiency-oriented approaches, alongside limited integration across spatial scales. Sustainability and governance perspectives are increasingly present but remain weakly connected to logistics network performance and rarely operationalise ESG criteria. The study develops a Multiscale Diagnostic Matrix that synthesises the literature and diagnoses fragmentation in port performance evaluation.

Accurate Estimated Time of Arrival (ETA) forecasting is essential for improving operational planning and decision-making in modern ports. While machine learning has significantly enhanced ETA prediction using Automatic Identification System data, the impact of data preprocessing on forecasting performance remains underexplored. This study investigates how AIS data preprocessing and machine learning model selection jointly affect ETA forecasting for short-sea shipping, using the Port of Sines as an empirical case study. A reproducible forecasting workflow was developed, integrating dataset construction, voyage selection, feature engineering, predictive modelling and performance evaluation. Three supervised machine learning algorithms, K-Nearest Neighbors, Random Forest Regression, and Multilayer Perceptron, were trained and compared under identical experimental conditions. The results show that forecasting performance depends not only on model selection but also on the quality of the modelling dataset. In particular, Random Forest Regression achieved the strongest and most consistent performance. It was found to be invariant to feature scaling, whereas scaling had a small negative effect on K-Nearest Neighbors and increased training variance for the Multilayer Perceptron. Although all three models achieved accurate ETA predictions, they exhibited different strengths regarding predictive performance, computational efficiency, and operational applicability. The proposed workflow contributes to the development of transparent and reproducible ETA forecasting methodologies and provides practical guidance for implementing AIS-based decision-support systems in short-sea port operations.

Ports are critical nodes in global supply chains and increasingly depend on intelligent, energy-efficient, and autonomous technologies to improve operational performance and sustainability. Within this context, unmanned aerial vehicles (UAVs) are evolving from isolated aerial platforms into network-enabled systems capable of supporting sensing, communication, computation, and decision-support functions. This study examines the evolution of energy-efficient UAV-enabled systems for sustainable port logistics, with particular emphasis on autonomous system architectures, mobile edge computing, artificial intelligence, optimisation, and Internet of Things integration. Following PRISMA 2020 reporting guidelines, a bibliometric and systematic review was conducted based on a curated dataset of 49 peer-reviewed publications indexed in Scopus between 2001 and 2026. The analysis combines performance indicators with science mapping techniques, including bibliographic coupling and keyword co-occurrence, to identify research trends, influential contributions, and thematic structures. The results reveal a transition from fragmented exploratory studies to a rapidly expanding research field shaped by UAV-assisted edge computing, resource allocation, intelligent optimisation, and energy-aware system design. Four main thematic clusters are identified: UAV-assisted mobile edge computing and network optimisation; advanced optimisation and intelligent UAV systems; energy efficiency and resource allocation; and application-oriented developments and hardware innovations. The findings indicate that energy efficiency is the central design principle connecting UAV autonomy, system integration, and sustainability-oriented port logistics.

Ports are increasingly required to respond to environmental regulation, digital transformation, and demands for more sustainable logistics systems. Although research on smart ports, green ports and innovation ecosystems has expanded, less attention has been given to how Open and Sustainable Innovation is enabled, constrained and institutionalised within public port authorities. This study examines this process in the Port of Sines, Portugal’s largest port and a strategic Atlantic logistics hub. A qualitative single-case study was conducted, drawing on institutional documents, nine semi-structured interviews, observational material and MAXQDA-supported qualitative coding. The analysis was structured around four interdependent dimensions: environmental, organisational, cultural and technological. The findings show that Open and Sustainable Innovation is enabled by European sustainability agendas, digitalisation initiatives, the NEXUS Agenda and multi-stakeholder collaboration. However, it remains only partially institutionalised. Organisational fragmentation, limited learning routines, uneven cultural readiness, data-sharing concerns and dependence on externally funded projects constrain long-term innovation capabilities. The study contributes by conceptualising Open and Sustainable Innovation in public port ecosystems as an institutionalisation process rather than as a set of isolated digital, environmental or collaborative initiatives. It offers practical insights for strengthening governance coordination, stakeholder trust, data-sharing arrangements and organisational learning in sustainable port transformation.

Open data platforms (ODPs) are emerging as strategic infrastructures for smart port development within the European Union, yet there is limited research offering integrated approaches to evaluate their performance across technical, operational, and regulatory dimensions. To address this gap, this study develops an analytical framework combining four complementary perspectives: open data platform design, FAIR (Findability, Accessibility, Interoperability, and Reusability) principles, smart port enablement, and EU regulatory alignment. The framework is applied through a qualitative comparative case study of the Ports of Barcelona and Antwerp–Bruges, based exclusively on secondary data sources, including the academic literature, policy documents, and publicly accessible platform data. The analysis is structured around three analytical dimensions—FAIR and interface features and accessibility, smart port enablement, and EU regulatory alignment—applied consistently across both cases. The findings reveal two distinct models: Barcelona adopts an open-by-default approach prioritising accessibility, transparency, and integration with public data ecosystems, while Antwerp–Bruges follows a controlled-access model focused on operational integration, system reliability, and business-to-business data exchange. Both approaches align with EU policy frameworks but involve different trade-offs between openness and operational control. The study contributes a structured, transferable framework for evaluating port ODPs and identifies practices for their design and governance in smart port and maritime logistics contexts.

The transition towards sustainable, resilient and digitally integrated port ecosystems has increased the need for collaborative innovation approaches capable of supporting broader sustainability transitions. In this context, open and sustainable innovation (OSI) offers a strategic mechanism for integrating economic, environmental and social objectives within complex maritime ecosystems. Although previous studies have explored technological innovation and isolated sustainability initiatives in ports, limited empirical attention has been given to how stakeholders perceive OSI and how its implementation is operationalised across a national port system. This study addresses this gap by investigating the central research question: how do key stakeholders perceive and implement OSI practices within the Portuguese port system? Specifically, it analyses organisational culture, governance structures, stakeholder engagement mechanisms, institutional barriers and sustainability-oriented innovation practices. The research adopts a qualitative approach based on ten semi-structured interviews with representatives of five Portuguese port authorities occupying senior management and strategic positions. The findings show that OSI is widely recognised as important for competitiveness, sustainability performance and alignment with transition agendas, but its implementation remains uneven across ports. Organisational resistance, fragmented governance, regulatory complexity and limited monitoring mechanisms constrain the institutionalisation of OSI practices. Nevertheless, collaborative initiatives involving universities, innovation networks, public–private partnerships and digital platforms indicate a gradual shift towards more integrated and participatory governance models. The study concludes that OSI can support sustainability transitions in port ecosystems when enabled by coordinated governance, stakeholder collaboration and organisational capabilities.