Machine Learning Models for Efficient Port Terminal Operations: Case of Vessels’ Arrival Times Prediction
Sara El Mekkaoui, Loubna Benabbou, Abdelaziz Berrado
Abstract
Port terminals are critical nodes in the maritime transport network and play a significant role in the global supply chain. However, they still suffer from many disruptions entailed by their complex environment leading to many challenges. With the maritime digital transformation, ports and ships produce significant amounts of data offering an opportunity to use Machine Learning techniques to address some issues and support port terminal operations management. This paper addresses the problem of vessel arrival times prediction to destination ports using Machine Learning models and vessels’ historical trajectories data. This paper also provides a structured overview of research work concerning the contribution of Machine Learning techniques in handling port terminal concerns. The existing literature shows that related work has tackled different problems, but further development is needed.