Maritime ETA prediction system uses historical knowledge graph

A new methodology uses Automatic Identification System (AIS) data to construct a historical maritime knowledge graph for predicting vessel estimated-time-of-arrival (ETA). This graph, comprising over 5,000 nodes and 12,000 edges, stores speed distributions stratified by vessel type, time, and direction. The system achieved a median RMSE of 22.75 minutes for segment-level predictions and 30.90 minutes for trajectory-level predictions on a test set, demonstrating its potential for optimizing port operations and reducing emissions through just-in-time arrival planning. AI

IMPACT Enables more accurate global travel-time predictions for maritime logistics and emissions reduction.

RANK_REASON The cluster contains an academic paper detailing a new methodology for maritime ETA prediction. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.CV →

• Automatic Identification System (AIS)
• Neofytos Dimitriou

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →