Evaluation and prediction of punctuality of vessel arrival at port: a case study of Hong Kong

Abstract

ABSTRACT The punctuality of vessel arrival at port is a crucial issue in contemporary port operations. Uncertainties in vessel arrival can lead to port handling inefficiency and result in economic losses. Although vessels typically report their estimated time of arrival (ETA) en-route to the destination port, their actual time of arrival (ATA) often differs from the reported ETA due to various factors. To address this issue and enhance terminal operational efficiency, we first quantitatively evaluate vessel arrival uncertainty in different time slides prior to arrival at the port using 2021 vessel arrival data for Hong Kong port (HKP). Our results confirm that the overall vessel arrival uncertainty decreases as vessels approach the HKP. Then, we implement a random forest (RF) approach to predict vessel arrival time. Our model reduces the error in ship ATA data prediction by approximately 40% (from 25.5 h to 15.5 h) using the root mean squared error metric and 20% (from 13.8 h to 11.0 h) using the mean absolute error metric compared with the reported ETA data. The proposed vessel arrival time evaluation and prediction models are applicable to port management and operation, laying the foundation for future research on port daily operations.