Wide-Area Ship Movement Prediction Using Random Forests




Vähämäki,Tanja; Farahnakian, Farshad; Nevalainen, Paavo; Heikkonen, Jukka

Razminia, Abolhassan; Nguyen, Dinh Hoa

International Symposium on Intelligent Technology for Future Transportation

PublisherSpringer Nature Switzerland

2025

Communications in Computer and Information Science

Intelligent Technology for Future Transportation: First International Symposium, ITFT 2024, Helsinki, Finland, October 19–21, 2024, Proceedings

Communications in Computer and Information Science

2378

220

245

978-3-031-84147-7

978-3-031-84148-4

1865-0929

1865-0937

DOIhttps://doi.org/10.1007/978-3-031-84148-4_18(external)

https://doi.org/10.1007/978-3-031-84148-4_18(external)



Maritime situational awareness requires real-time traffic prediction over a large area based on the Automatic Identification System (AIS). The second requirement is allowing input from all the traffic. We propose Random Forests (RF) for ship movement prediction and demonstrate how it can be adapted to varying zone shapes and anomaly detection tasks. We also apply it to the clustering of vessels to regularly and irregularly moving ships. Our research area is the Baltic Sea and the recording period of data is 26 July 2022... 12 August 2022. Results from the class of regularly behaving ships (499 ships out of 634) show 0.2... 2.1 km mean absolute error (MAE) over 15 min... 2 h which reaches the same accuracy as many published cases with more expensive computational models. The prediction for all supported time intervals can be updated every 10 min, which makes the implementation practical for large-scale situational awareness systems.



Last updated on 2025-02-05 at 07:38