Constructing Trajectory and Predicting Estimated Time of Arrival for Long Distance Travelling Vessels: A Probability Density-based Scanning Approach

TL;DR

This paper introduces a probability density-based method for constructing vessel trajectories and predicting their estimated time of arrival, achieving high accuracy and low error in long-distance maritime navigation.

Contribution

The study presents a novel probability density-based approach for trajectory construction and ETA prediction, validated with real-world maritime data.

Findings

Average ETA prediction error of 2.544 hours

Prediction accuracy of 92.08%

R-Squared value of 0.959 for trajectory predictions

Abstract

In this study, a probability density-based approach for constructing trajectories is proposed and validated through an typical use-case application: Estimated Time of Arrival (ETA) prediction given origin-destination pairs. The ETA prediction is based on physics and mathematical laws given by the extracted information of probability density-based trajectories constructed. The overall ETA prediction errors are about 0.106 days (i.e. 2.544 hours) on average with 0.549 days (i.e. 13.176 hours) standard deviation, and the proposed approach has an accuracy of 92.08% with 0.959 R-Squared value for overall trajectories between Singapore and Australia ports selected.