Predicting Ships Estimated Time of Arrival based on AIS Data

Abstract

Using appropriate tools to verify and ascertain the accuracy of the estimated time of arrival (ETA) provided by ships during their approach to ports has never been more needed than it is today. This is owed to the traffic increase and the considerable variations in ETAs that port actors are suffering from. But now the opportunity presents itself with the maritime digital transformation enabling ports and ships to produce important amounts of data that can serve in building predictive systemsfor ships' arrival time projection. This paper presents the existing approaches to predict ETAs, outlines three of the data sources that can serve in ETAs' prediction, and shows the results of Neural Networks (NN) models prediction of the arrival time of a ship to its destination using AIS data.