A Neural Network Approach for ETA Prediction in Inland Waterway Transport

Conference paper (2023)

Authors

P.A. Wenzel Transport Engineering and Logistics - Mechanical, Maritime and Materials Engineering
Raka Jovanovic Hamad bin Khalifa University
F. Schulte Transport Engineering and Logistics - Mechanical, Maritime and Materials Engineering
Research Group
Transport Engineering and Logistics (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2023 P.A. Wenzel, Raka Jovanovic, F. Schulte
DOI
help_outline
https://doi.org/10.1007/978-3-031-43612-3_13
Machine Learning Neural Networks Inland Waterway Transport Estimated Time of Arrival Prediction
More Info
expand_more

Published Date

2023

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical, Maritime and Materials Engineering

Department

Marine and Transport Technology

Research Group

Transport Engineering and Logistics

Abstract

Ensuring the accuracy of the estimated time of arrival (ETA) information for ships approaching ports and inland terminals is increasingly critical today. Waterway transportation plays a vital role in freight transportation and has a significant ecological impact. Improving the accuracy of ETA predictions can enhance the reliability of inland waterway shipping, increasing the acceptance of this eco-friendly mode of transportation. This study compares the industry-standard approach for predicting the ETA based on average travel times with a neural network (NN) trained using real-world historical data. This study generates and trains two NN models using historical ship position data. These models are then assessed and contrasted with the conventional method of calculating average travel times for two specific areas in the Netherlands and Germany. The results indicate by using specific input features, the quality of ETA predictions can improve by an average of 20.6% for short trips, 4.8% for medium-length trips, and 13.4% for long-haul journeys when compared to the average calculation.