Conference Agenda
Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
|
Daily Overview |
| Session | ||
T-C-03: Advanced Logistics Technologies 3: Data Analytics for Transport and Port Operations
| ||
    | ||
Machine Learning-based Container Flow Forecasting for Better Port Resource Planning 1: Fraunhofer Center for Maritime Logistics and Services, Germany; 2: Hamburger Hafen und Logistik AG; 3: HPC Hamburg Port Consulting GmbH Machine learning approaches are increasingly discussed in port logistics, but practical value depends on whether they can improve real operational decisions. This paper presents an applied machine learning use case for a port terminal operator: forecasting container flow volumes in order to support resource planning, equipment readiness, and operational preparation. The main goal is to investigate the impact of machine learning based forecasts for container volumes under real-world operational conditions and to show that forecasting of container volumes is feasible in a real terminal environment, and to study under which data conditions and forecast horizons the results become useful for practice. The work focuses on shift-level forecasts of inbound and outbound full and empty container volumes—an area where planning still relies on manual estimates, spreadsheets, and simple historical averages. In practice, workloads are shaped by multiple concurrent drivers (e.g., internal moves, planning changes, slot deviations, pre-announcements, weather, holidays, traffic, and disruptions), making the task both highly relevant for machine learning and methodologically challenging. The paper follows a classical machine learning workflow. First, raw operational movement logs and related terminal data are transformed into analytical datasets. Second, extensive feature engineering is applied to represent the operational state of a shift. This includes lag variables, rolling aggregates, calendar and weekday effects, yard-related indicators, planning signals, and selected external variables. A key research question is the extent to which forecast quality improves when internal terminal movement data are combined with external data and planning-related information, instead of relying on movement data alone. Several machine learning approaches are compared, including statistical baseline models, autoregressive learning setups, and tree-based ensemble methods. The paper discusses which model class performs best under volatile port conditions and how feature importance can be used to better understand the drivers of predicted volumes. Special attention is given to model validation in a real operational setting. Historical rolling backtests and holdout-based black-box validation are used to assess not only general forecast error, but also the practically useful forecast horizon. In other words, the paper examines whether the forecast quality is sufficient only a few hours ahead, for the next 24 hours, or even for several days. The expected benefits are both operational and economic. More accurate machine learning-based forecasts can improve staffing and equipment planning, reduce under- and over-planning, stabilize terminal operations, and lower coordination effort with operators and service units. This, in turn, can enhance service reliability for shipping lines and hinterland partners and, over time, strengthen overall port performance and competitiveness. An Adaptive Retraining Framework for Port Operations: A Mixed Reality Based Approach to Safety Training Technical University of Hamburg, Germany Port and crane operations are safety critical activities where human error and inadequate training can contribute substantially to operational accidents. Previous research has shown that over 70% of terminal accidents are associated with human factors, such as inadequate training, communication failures and insufficient supervision. A review of 245 studies revealed that only around 2% investigated immersive technologies as a potential approach for reducing accident risks associated with training deficiencies and human factors. Existing safety interventions therefore continue to be focused on primarily on recurrent instruction, procedural compliance, and modifications of training content. Although the adoption of immersive technologies in training has grown considerably in recent years, their use for adaptive workforce training in port operations remains relatively limited. Building on these findings, this study proposes an adaptive retraining framework for safety critical crane and port operations. Crane-related activities were selected due to their accident relevance, their procedural complexity, and the increasing evidence supporting the use of immersive technologies for training in such environments. The proposed framework focuses on adapting the training process according to trainee performance. Procedural errors trigger different retraining paths, corrective feedback mechanisms, and varying levels of instructional support. Based on the type and frequency of errors, the training workflow can evolve into alternative learning scenarios while also supporting performance based difficulty adjustments. In addition, predefined intervention points allow supervisors to monitor progress and provide guidance when required. This study focuses on the practical application of mixed reality in training the port operations workforce, moving beyond the development of a retraining framework. Particular attention was given to understanding the opportunities and limitations of using mixed reality for training. This included examining the extent to which operational errors, unsafe actions, and corrective learning situations could be realistically represented in a virtual environment. The developed demonstrator was used to examine how training scenarios can be adapted according to trainees' behaviour and to compare simulated learning experiences with the challenges typically encountered in conventional training settings. Furthermore, the framework generates structured performance and feedback data, which can be used to inform the development of future AI-supported training and feedback systems. Thus, this research contributes to the development of more adaptive, data-driven, learner centred approaches to training the maritime logistics workforce. Real-Time Material Tracking in Industrial Environment. Example from Shipyard Material inflows 1: Turku University of Applied Science, Finland; 2: Fidera Ltd, Finland Purpose: Objective of material tracking was to assess whether right materials were in right place at right time. Tracking pilot was used to examine delivery reliability, lead times, storage times, transportation routes, as well as duration of the various stages of supply chain. Study aimed to identify deviations related to material inflows, such as deliveries to incorrect locations, unnecessary material movements, and material loss during supply chain. Methodology: Tracked material consisted of ceiling panels used in ship’s interior. Digital Matter Yabby NB-IoT trackers were installed on the tracked units. Trackers combine GNSS (Global Navigation Satellite System), such as GPS, for location calculation and NB-IoT (Narrowband Internet of Things) for data transmission to a cloud service. Trackers were programmed to transmit a signal every 3 minutes while in motion and every 12 hours when stationary. In addition to these trackers, QR code stickers were attached to the units, enabling users to record events using smartphones, including location updates and shipment statuses such as received and dispatched. Findings: Originality: | ||