In recent years, investments in the shipping industry have continued to grow to improve maritime transport systems. A vital part of these systems is the accurate Vessel Traffic Flow Forecasting (VTFF). In the literature, the most promising methods used in predicting vessel traffic flow, mostly employ grid-based representation analysis, approaching the VTFF problem from two different perspectives: a) directly - by predicting the future traffic based on sequence analysis of historical traffic flow, and b) indirectly - by estimating the future traffic based on future vessel locations produced by vessel route forecasting algorithms. We investigated the VTFF problem from both perspectives by employing machine learning methods and conducting an experimental comparative study.

------------------------------------------------------

Corresponding Papers:
- Mandalis P., Chondrodima E., Kontoulis  Y., Pelekis N., Theodoridis Y., “Machine Learning Models for Vessel Traffic Flow Forecasting: An Experimental Comparison”, 23rd IEEE International Conference on Mobile Data Management (MDM), 2022, Paphos, Cyprus.
- Mandalis P., Chondrodima E., Kontoulis Y., Pelekis N., Theodoridis Y., “Towards a Unified Vessel Traffic Flow Forecasting Framework”, International Workshop on Big Mobility Data Analytics of the EDBT/ICDT 2023 Joint Conference, 2023, Ioannina, Greece.

------------------------------------------------------

Implementation:

The indirect VTFF strategy can alternatively be implemented using the VRF method and the H3 grid.