Prediction of Vessel Arrival Time to Pilotage Area Using Multi-Data Fusion and Deep Learning

TL;DR

This study presents a deep learning framework that fuses multiple data sources to accurately predict vessel arrival times to pilotage areas, demonstrating improved performance over existing methods on real-world Singapore data.

Contribution

The paper introduces a novel multi-data fusion approach combined with a residual Temporal Convolutional Network for vessel arrival time prediction, outperforming state-of-the-art baselines.

Findings

Fusion of pilotage booking and meteorological data enhances accuracy.

Discrete embedding of meteorological data yields better results.

The proposed TCN achieves MAE around 4.7 minutes, with over 89% residuals within 10 minutes.

Abstract

This paper investigates the prediction of vessels' arrival time to the pilotage area using multi-data fusion and deep learning approaches. Firstly, the vessel arrival contour is extracted based on Multivariate Kernel Density Estimation (MKDE) and clustering. Secondly, multiple data sources, including Automatic Identification System (AIS), pilotage booking information, and meteorological data, are fused before latent feature extraction. Thirdly, a Temporal Convolutional Network (TCN) framework that incorporates a residual mechanism is constructed to learn the hidden arrival patterns of the vessels. Extensive tests on two real-world data sets from Singapore have been conducted and the following promising results have been obtained: 1) fusion of pilotage booking information and meteorological data improves the prediction accuracy, with pilotage booking information having a more significant impact; 2) using discrete embedding for the meteorological data performs better than using continuous embedding; 3) the TCN outperforms the state-of-the-art baseline methods in regression tasks, exhibiting Mean Absolute Error (MAE) ranging from 4.58 min to 4.86 min; and 4) approximately 89.41% to 90.61% of the absolute prediction residuals fall within a time frame of 10 min.