Digitalization is playing an increasingly important role in the infor-mation flow of today’s supply chains. In particular, in logistics, the adoption of digital technologies such as the Internet of Things, cloud computing, block-chain, or machine learning offers the potential to increase data availability and quality. Using inter-organizational communication systems, private and public stakeholders can integrate their information flows. Within this paper, we ana-lyze with transport planning, tracking, and cargo monitoring three use cases for the adoption of decentralized systems focusing on maritime logistics. For this purpose, a software artifact was developed using the Design Science Research (DSR) approach. During the development process, four central design princi-ples could be identified: user orientation, interoperability, data security, and de-centralization. Based on these principles, a concept was developed for a decen-tralized information system that contributes to further automation and standard-ization of the information flow, while considering requirements such as confi-dentiality, neutrality, and accessibility.

The prediction of accurate vessel arrival times is essential and challenging at the same time to plan vessel arrivals with sufficient accuracy, coordinate berthing manoeuvres and monitor ship traffic efficiently. This paper investigates a new approach by using clusters consisting of deep artificial neural networks (DNNC). For this purpose, the considered coverage area of the Weser river was divided into geospatial domains. An also developed linear regression model (LNNC) served as a reference model, which was generated analogously to the machine learning approach on the clusters.

The estimated time of arrival prediction was evaluated at a distance of 50 kilometres between the estuary of the Weser river into the North Sea and the target industrial port. It could be shown that the mean deviation from the actual travel time at a distance of 50 kilometres is -19.8 minutes for the DNNC and 67.9 minutes for the LNNC. At a distance of 33 kilometres from the industrial port, the mean deviation of the DNNC decreases to 2.85 minutes and for the LNNC to 54.4 minutes. Furthermore, it has been observed that the shorter the distance to the destination port, the more accurate the predictions become.

Vessel delays and increased terminal call sizes negatively impact the ability to properly plan daily operations at seaport container terminals. Such traffic patterns lead to, among others, infrequent peak loads at the seaside of container terminals, complicating terminal operations. Thus, relying on annual or monthly statistics fails to account for these day-to-day fluctuations.

When container terminals are planned, be it a greenfield or brownfield terminal, these variations in operations need to be accounted for. The traditional formula-based approach to design terminals uses annual statistics.

In this study, it is first used to produce estimates for the required yard capacity for three existing exemplary container terminals. These are then compared to the results of numerical experiments using the synthetic container flow generator ConFlowGen. The findings reveal that yard capacity requirements fluctuate considerably depending on the timing of vessel arrivals and their call sizes. This dynamic modeling proved particularly beneficial for planning gateway traffic, offering more accurate storage capacity predictions. Suggestions are made for how to further develop ConFlowGen for handling transshipment traffic better in future versions.