With many new opportunities emerging from the current wave of digitalization throughout global logistics chains, terminal planning and management need to be revisited with a data-driven perspective. The amount of operational data, such as from a terminal operating system (TOS), together with data from a variety of new data sources, such as sensors and mobile technologies, is growing fast but for the most part remains to a considerable extent too under-analyzed to be of real value. Meanwhile, many current projects and initiatives in the port industry indicate a growing interest in data analytics solutions. One example of applying data analytics is the SAFER project of the Maritime and Port Authority of Singapore (MPA). Under the project, MPA has piloted three IBM analytics-based modules to improve the management of Singapore's growing vessel traffic. Another example is the Navis ATOM Labs, which is investigating the use of Machine Learning (ML) for the optimization and automation of terminal operations. In this technical paper, we provide a brief overview of potential applications of ML in container terminals and discuss some relevant challenges.
Machine Learning in Container Terminals
Dr Leonard Heilig and Dr Eduardo Lalla-Ruiz, Institute of Information Systems, University of Hamburg, Germany