18. sep. 2025
New research results from the GASS (Green AI for Sustainable Shipping) and DYNAPORT (Dynamic Navigation and Port Call Optimisation in Real Time) projects demonstrate how cutting-edge digital technology can reduce emissions from shipping while maintaining safe operations.
AI experts in Simula and NAVTOR produced the paper “Deep Learning-Based Vessel Traffic Prediction Using Historical Density and Wave features” earlier this year. It was presented at the International Conference on Agents and Artificial Intelligence 2025. The paper addresses the vessel traffic prediction problem. Dogan Altan, Dusica Marijan, and Tetyana Kholodna propose a vessel traffic prediction method that processes information obtained from different sources indicating historical traffic and wave conditions for vessels.
“Sea traffic is fundamental information that needs to be considered while planning vessel operations to enhance navigational safety and operational efficiency. Therefore, several environmental constraints, such as weather and traffic conditions, must be taken into account to minimise delays caused by vessel traffic and improve safety by decreasing collision risks,” says Dusica Marijan.
Dogan Altan continues, “The proposed method uses a combination of historical traffic density, tailored voyage features, and wave data to forecast vessel traffic along a given trajectory. Unlike traditional models, this approach does not rely on fixed location representations, making it adaptable to any maritime route.
By analysing features such as planned speed and voyage completeness, the model generates insights that help anticipate congestion and optimise navigation,” adds Tetyana Kholodna.
A synergistic vision for the future in reducing emissions
The AI-powered maritime traffic forecasting is a crucial part of the work done in the GASS project. Complementing GASS, the Horizon Europe funded DYNAPORT project tackles another critical aspect of maritime sustainability: real-time coordination between ships and ports.
Promising results
In the paper, Altan, Marijan and Kholodna evaluate the proposed method on real-world historical vessel trajectories and report its performance by providing a comparison with other baselines. The experimental results indicate that our proposed method provides promising results for predicting vessel traffic with a mean squared error of 0.325
The GASS-project is made possible by The Green Platform Initiative (“Grønn Plattform”) funding scheme by Norges forskningsråd, Innovation Norway and Siva SF under the Grant Agreement No. 346603. DYNAPORT is funded by the European Union's Horizon Europe Research and Innovation programme under the Grant Agreement No.101138478.