João Marreiros

Mr. João Marreiros

Mechanical and Industrial Engineering, NOVA School of Science and Technology (NOVA FCT), Caparica, Portugal
+1
orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 March 2025 in Computers & Industrial Engineering
Verified
Journal Article
Open access
IFInês A. Ferreira
Inês A. Ferreira
PMPaula Miranda
Paula Miranda
João MarreirosJoão Marreiros
João Marreiros
AMAna Mendes
Ana Mendes
Nelson CarriçoNelson Carriço
Nelson Carriço

11 August 2026 in Forecasting
Verified
Journal Article
Open access
PDF file
João MarreirosJoão Marreiros
João Marreiros
Ana J. MendesAna J. Mendes
Ana J. Mendes
MCMARCELA SOUTO CASTRO
MARCELA SOUTO CASTRO
MCMaria da Graça Costa
Maria da Graça Costa
Tiago PinhoTiago Pinho
Tiago Pinho
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.

5 November 2026 in Logistics
Verified
Journal Article
Open access
PDF file
João MarreirosJoão Marreiros
João Marreiros
MCMARCELA SOUTO CASTRO
MARCELA SOUTO CASTRO
Ana J. MendesAna J. Mendes
Ana J. Mendes
Tiago PinhoTiago Pinho
Tiago Pinho
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.