OceanTwin AI: A Maritime Intelligence Platform for Smart Ports
DOI:
https://doi.org/10.69968/ijisem.2026v5i4349-354Keywords:
Maritime Intelligence, Smart Ports, Digital Twin, Machine Learning, Predictive Analytics, Telemetry Simulation, Sustainability Analytics, Explainable AI, Decision Support SystemsAbstract
The current maritime operations are being affected more and more by such factors as port congestion, weather disruption, sediments, fuel efficiency, and sustainability guidelines. It has become a problem in current maritime operations to include in their system the technologies of telemetry simulation, machine learning, and predictive analytics because of different modules that the current maritime systems contain. In this paper, we propose OceanTwin AI, the framework of maritime intelligence, which integrates the mentioned technologies in maritime operations through digital twin concept. The architecture of OceanTwin AI framework is 3 tiered where the frontend, API gateway, and machine learning services are implemented in React, Node JS and Python respectively. Our framework includes such functionality as vessel tracking, port congestion, sediment risks, fuel efficiency, sustainability, and alerts. We performed evaluation of our framework using 3 physics inspired synthetic datasets and predictive models including Linear regression, Random forest and XGBoost. Furthermore, we evaluated our framework using 5-fold cross-validation and Scenario based digital twin simulations.
References
[1] A. De Bari et al., “A decoupled layers architecture for seaport digital twins,” IEEE Access, vol. 12, 2024.
[2] J. M. Zeneli and D. Marinova, “Digital twins in port logistics: simu-lation, monitoring and predictive performance,” International Journal of Logistics Research and Applications, 2024.
[3] V. Badea et al., “Artificial intelligence and IoT integration in smart port digital twin frameworks,” IEEE Transactions on Intelligent Transporta-tion Systems, 2025.
[4] International Maritime Organization, “Initial IMO GHG Strategy,” IMO Publications, 2018.
[5] L. Heilig and S. Voß, “A scientific approach to vessel delay prediction,” Computers & Industrial Engineering, vol. 131, pp. 651–666, 2019.
[6] D. Zhang, C. Zhang, and H. Chen, “Research on port congestion and vessel delay prediction,” Journal of Marine Science and Engineering, vol. 9, no. 4, 2021.
[7] OceanTwin AI Project Repository, “Maritime Intelligence Platform Source Code,” unpublished internal documentation, 2026.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Shubhangi Kamble, Sara Ansingkar, Saloni Tiwari, Sairaj Patil, Darshan Shete

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Re-users must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use. This license allows for redistribution, commercial and non-commercial, as long as the original work is properly credited.





