This study develops a synchromodal transport model with real-time replanning using a Double-Dueling Deep Q-Network (D3QN) agent. The hinterland port-hinterland leg dominates supply-chain costs and remains vulnerable to disruptions. We simulate realistic disruptions using varying occurrence and severity levels and train a D3QN agent to decide whether an affected shipment should wait or reassign to another mode. Model performance is evaluated in a Rhine-Alpine corridor case study against two baselines strategies (Always Wait, Always Reassign) and a tabular Q-learning benchmark. The results show that the D3QN policy achieves the lowest costs on a combined set of disruptions, outperforming alternatives overall. In particular, D3QN excels under high-occurrence, low-severity disruptions but appears less effective under rare, high-severity events. The integration of the D3QN with parallel simulation greatly sped up training (roughly 4 times faster convergence) without degrading policy quality. It is discussed how classifying disruptions by occurrence and severity helps tractability, and show that the D3QN learns to reassign shipments more effectively. The findings indicate that deep reinforcement learning can improve synchromodal resilience, particularly in large-scale settings where conventional RL or heuristics fail.

Future demand for container transport is expected to increase, placing pressure on the port-hinterland system of the Rhine river. To meet European climate goals and relieve the congested road freight system, inland waterway transport (IWT) is promoted as a sustainable alternative. However, IWT is vulnerable to low water levels as a result of climate change, as evidenced by significant drought periods in 2018. This research investigates how the strategic establishment of transshipment hubs can enhance the climate resilience of the port-hinterland system of the Rhine river under varying river discharge scenarios. The focus is on three critical bottlenecks in terms of available draught: Druten, Duisburg, and Kaub. This study quantifies the impact of new hubs on the total cost and CO2-equivalent emissions by developing a mathematical location routing model, which is used for a scenario-based analysis with varying river discharge levels and rail capacity levels. Results show that hub establishment significantly reduces both total transport costs and CO2-equivalent emissions during low discharge scenarios, without requiring expansion of existing terminals. The establishment of hubs depends on location and multimodal accessibility, with rail connections only becoming economically viable when the remaining hub-destination distance exceeds certain distance thresholds. The findings provide actionable insights for policymakers and transport authorities on strategic decisions of infrastructure investments to improve the climate-resilience of freight transport along the Rhine corridor to minimize total costs, reduce CO2-equivalent emissions, and relieve congested road networks.

In vendor-to-retailer systems where retailers with limited inventory capacity place orders and vendors dispatch trucks within soft time windows, trucks may arrive before sufficient space is available, requiring them to wait on site resulting in inventory-driven delays. Since no existing formulation incorporates inventory-dependent service times, this study models the dispatch problem as a discrete-time Markov Decision Process (MDP) with inventory-dependent service times, solved using Approximate Dynamic Programming (ADP) with a Partial Value Function Approximation (PVFA) that ranks outstanding orders based on urgency. The model is implemented at an Ethiopian brewery and benchmarked against a First-In First-Out (FIFO) policy across three replenishment strategies: Retailer-Managed Inventory (RMI) with Poisson-generated orders, threshold-based replenishment with a fixed lead time, and Vendor-Managed Inventory (VMI) where order timing is optimized. Results show that, depending on the replenishment strategy, the PVFA reduces unmet demand by 53–98%, lowers extended service times by 65–93%, and frees 8–16% of fleet capacity to be repurposed, with the total number of orders served ranging from a 5% decrease to a 22% increase. These findings demonstrate that inventory-driven delays can be effectively incorporated into a dispatch model, enabling soft handling of inventory constraints. The PVFA consistently outperforms the FIFO benchmark across all scenarios, demonstrating its ability to anticipate even in reactive systems. It also exhibits lower variance on Key Performance Indicators (KPIs), indicating robustness under different replenishment settings. As such, the model is well suited for environments where order policies vary or inventory-driven delays are common. Future work may address dynamic order generation, parameter uncertainty, and extensions toward the general Inventory Routing Problem (IRP).

Freight transport is vital for urban economic growth, yet its increasing demand exacerbates congestion and emissions. The integration of freight delivery within public transport networks presents a sustainable alternative, leveraging underutilised transit capacity. While prior studies focus on operational aspects, limited research addresses strategic hub locations within public transit networks. This study introduces a novel framework for selecting public transport stations as freight hubs using a Multi-Criteria Decision Analysis (MCDA) approach with the Best-Worst Method (BWM). The framework evaluates key factors, such as accessibility, capacity, and costs, to determine optimal hub locations. A simulation is subsequently conducted to assess real-world viability, demonstrating the trade-offs between network reach, handling efficiency, and financial constraints. The results indicate that strategic hub placement significantly impacts network scalability and efficiency. Future research can expand
upon this framework to refine urban freight delivery models tailored to specific implementation areas.

Container terminals are vital hubs in global trade, facilitating the seamless transfer of goods between maritime and inland transportation networks. Truck turnaround time serves as a critical performance metric for container terminals, provides direct feedback on port congestion and efficiency. This study focuses on developing a predictive framework for truck turnaround time (TTT) at the Port of Rotterdam by integrating multi-source data and employing advanced machine learning techniques.
Previous studies on truck turnaround time prediction have largely relied on limited datasets and methodologies, such as utilizing historical truck arrival flows or terminal operation logs and using statistical methods. This research employs diverse datasets, including Bluetooth detection records, container arrival information, and environmental condition. By combining these data sources, a harmonized dataset was constructed to represent the complexities of port operations. A stacked Long Short-Term Memory (LSTM) network was employed as the predictive model, utilizing its ability to capture temporal dependencies and nonlinear interactions between variables. This approach allows for more comprehensive and accurate TTT predictions compared to conventional methods.
To process the noisy and incomplete Bluetooth data, a robust trip identification pipeline was developed. The pipeline employed spatial clustering, temporal filtering, and dual verification to accurately identify container truck trips, achieving an accuracy exceeding 90%. Using this processed data, the stacked LSTM model demonstrated superior predictive performance, effectively capturing periodic trends and long-term dependencies. Benchmarking results showed that the stacked LSTM outperformed traditional methods, including Random Forest and XGBoost. Sensitivity analysis highlighted the critical role of truck arrival flows and wind conditions in determining truck turnaround time variability.
In summary, this study provides a novel and scalable framework for TTT prediction, integrating multi-source data and advanced modeling techniques to address key limitations of existing approaches. The findings offer actionable insights for optimizing terminal operations and reducing congestion. Future research could focus on expanding data sources, enhancing model interpretability, and validating the framework across diverse port environments to ensure broader applicability.

Efficient Port Operations are essential for minimiming delays and ensuring the safe
movement of vessels. Tugboats play a critical role in assisting ships during berthing,
unberthing, and navigating port waters. This thesis uses DRL4Route, a deep reinforcement learning (DRL) framework aimed at optimising tugboat routes and pick-up
locations. By using historical towage data and adapting to the dynamic conditions of
the Port of Rotterdam, DRL4Route provides real-time recommendations that streamline tugboat operations, reduce delays, and improve safety.
The core of the DRL4Route framework lies in its ability to continuously learn and adapt
to real-world conditions. Unlike traditional static models, DRL4Route leverages spatiotemporal data to predict optimal tugboat routes. This allows for real-time evaluations
that can help the predicted route match closely with the actual route which helps tugboats arrive at the right location at the right times. The framework’s focus on optimising
both pick-up and drop-off points helps port operators avoid inefficiencies that can arise
from poorly coordinated tugboat movements.
By improving the efficiency of tugboat operations, DRL4Route contributes to a more
sustainable and resilient port ecosystem. The system’s adaptability and potential for
real-time decision-making make it a strong candidate for future automation of tugboat
operations. This thesis highlights how advanced machine learning techniques can
enhance the performance of ports like Rotterdam, driving economic benefits and reducing the environmental impact of maritime operations.

More than 6% of global carbon dioxide emissions are caused by freight transport by road dominating emissions from the freight transport sector. To keep climate targets in reach, a rapid decarbonisation is necessary, while holistically considering trade-offs with other environmental impacts. This study compares the environmental impact profiles of road freight transport to the alternative via rail, under different prospective scenarios for the transport fleets and the socio-economic landscape in 2050, using prospective Life Cycle Assessment (pLCA). To do so the database ecoinvent v3.9.1 is systematically modified according to scenarios of the Integrated Assessment Model (IAM) REMIND, using the Python library premise. The Life Cycle Impact Assessment (LCIA) is performed in ActivityBrowser (AB) using the impact assessment method Environmental Footprint (EF) v3.1. Results show that
all environmental impacts categories across scenarios are significantly lower for rail than for road freight transport, due to the higher energy and material efficiencies of trains. Depending on the scenario and year, relative climate change impacts per tonne kilometre (tkm) by rail freight transport only make up between 15-26% of the impacts from road freight transport. Absolute climate change impacts can be reduced with a higher share of freight transport by
rail, decreased absolute freight transport growth, and increased electrification of the vehicle fleets, while the later increases most impact category results if applied to lorries.

The increasing volume of global freight trade, coupled with economic growth, necessitates ongoing innovation in optimizing freight operations. Over the past decade, the concept of synchromodality has been explored to encourage a modal shift from unimodal to multimodal transport. Synchromodality, with its flexibility feature, can create more resilient freight transport systems. Various models employing different techniques have been proposed to establish a resilient synchromodal framework capable of reacting to disruptions. However, there are only few studies addressing the unknown duration of disruptions. This research proposes a learning-based modular framework comprising to capture the dynamics of disruptions in multimodal transport and learn to make more effective decisions, thus addressing the challenge of limited prior knowledge about disruptions and enabling fast responses to disruptions.

E-commerce is rapidly growing and is expected to encompass a quarter of all global sales by 2025. This growth pressures e-commerce warehouses to enhance efficiency. A promising innovation is the Robotic Mobile Fulfilment System (RMFS), which optimises warehouse operations by using robots to manage storage and retrieval tasks, thus significantly improving productivity, speed and accuracy. This research focuses on how inventory allocation (slotting) decisions with RMFS can optimise operational performance. In particular, how the slotting decision of Stock Keeping Unit (SKU) distribution across movable storage racks (pods) based on SKU turnover can maximise order throughput rates and optimise operational performance. The research question guiding this study is: What is the optimal demand-based slotting decision to maximise the order throughput rate in a Robotic Mobile Fulfilment System? This question aims to provide insights into how different slotting configurations impact the efficiency and performance of ecommerce warehouses. The research approach is twofold. A general analysis is conducted to understand the impact of turnover-based slotting decisions using synthesised demand profiles derived from literature. This is followed by a detailed case study for Gall&Gall using demand profiles derived from real-world data to find specific optimal slotting configurations and validate the synthesised demand results. The methodology involves three main steps: determining demand configurations, generating slotting configurations with a mathematical model, and simulating these configurations to evaluate performance. Each demand configuration results in multiple slotting configurations, which are evaluated with the simulation to gain insights into the effect of slotting decisions on performance. The different demand profiles consist of total SKU quantity, total item quantity, and SKU classification into three classes (A, B and C) based on their item turnover. The different slotting configurations consist of different distributions of the three classes over the pods. These slotting configurations are obtained with a mathematical model that prioritises class distribution based on given weights. The simulation tool RawSim-O assesses the slotting configurations on key performance indicators such as total order throughput rate and the number of items picked from a pod in one go (pile-on). Key findings provide that pile-on and travel distance significantly affect the order throughput rate, with performance variations of up to 40 orders handled in 30 minutes. High performance often arises with configurations aiming for an equal number of items per pod across classes and maximising the number of pods for SKUs in class A. While synthetic demand profiles show high performance with class A distributed over the maximum number of pods or equal items per pod for all classes, the Gall&Gall demand profiles perform better with class B distributed over slightly more pods, indicating variability in optimal slotting approaches based on specific demand characteristics. Overall, turnover-based slotting decisions significantly impact order throughput rates in RMFS, and tailoring slotting configurations to specific demand characteristics is crucial for optimal operational efficiency. In addition to general slotting insights, this research developed a method that allows warehouses to input their specific demand characteristics and receive insights on optimal slotting approaches. Furthermore, the method enables the readjustment of warehouse-specific details, such as a warehouse’s unique layout, for extra applicability and realism, and allows the integration of additional decision problems, such as order batching and routing, to broaden the method’s scope. This supports warehouses with the design of a tailored, robust and effective slotting strategy for operational performance improvement

Port systems face numerous challenges, including limited storage capacity at terminal yards, congestion in road port access due to overwhelmed infrastructure, and inefficient inter-terminal transportation. Close dry ports, situated between 10-40 km from the port, offer a potential solution, but lack flexible and reliable transport connections that efficiently handle transportation without adding extra handling moves. Recent technological advances in rail systems, particularly fully automated magnetic levitation (maglev) cargo shuttles, provide promising solutions for connecting dry ports with seaport terminals.

This research explores the integration of maglev technology into port logistics, focusing on connecting a dry port terminal to seaport terminals, with a direct connection to the berth. Using the Transport System Bögl (TSB) Cargo system as a reference, five different designs were developed for integration. These designs required a redesign of the dry port and terminal yard, as well as the design of the system’s berth connection and connections between all terminals.

Simulation modeling using Siemens Tecnomatix Plant Simulation software evaluated the performance of these designs under various scenarios based on Port of Hamburg demand input data. Results showed that all designs improved median berth times compared to the German benchmark of 18.96 hours, with Design 5 demonstrating the best performance together with Design 2.

Recommendations include continued collaboration with port authorities through simulation case studies, serving as proof of performance for potential integration projects, and exploration of collaboration opportunities with smaller scale ports facing space availability and road access issues. Further research should expand the model to accommodate new export container loading requirements and include all terminals, while studying new algorithms to balance the volumes and requests of all three terminals. This research demonstrates the feasibility of integrating maglev systems into port logistics, challenging the ’status quo’ and opening up new possibilities for improving port operations. Through a systematic approach, this study offers valuable insights for the integration of maglev technology into port logistics, paving the way for future advancements in the field.

As societies worldwide grapple with the urgent need to mitigate carbon emissions, one domain where substantial strides can be made is heavy-duty road freight transport. Electrification has emerged as a practical and technologically mature solution to address this challenge. However, the widespread adoption of electrification in this sector is met with formidable obstacles. These obstacles encompass the inadequacy of charging infrastructure, restrictions in driving range on a single charge, the demand for robust and high-capacity onboard batteries, and the looming specter of potential battery shortages.

Within the European context, discussions revolve around sustainable solutions that can pave the way for a cleaner and greener future. Among the contenders in this realm, the electric road system (ERS) has risen to prominence. ERS introduces a groundbreaking concept where trucks can recharge their batteries while in motion on highways, promising an array of ecological and economic benefits. However, the journey toward the implementation of ERS infrastructure is not without its intricacies. It necessitates the installation of specialized charging infrastructure, which can take the form of overhead catenaries accessed by a pantograph or embedded road equipment. Moreover, there is a substantial financial commitment required to equip entire truck fleets with the necessary batteries, adding to the complexity of the endeavor.

The central challenge in this landscape revolves around the meticulous design of an optimal ERS network that adeptly balances infrastructure costs with battery expenses. This research aims to address this multifaceted challenge by posing a fundamental question: How to determine the optimal ERS network, given the trade-off between infrastructure and battery costs?

To tackle this question head-on, this paper introduces a sophisticated multi-objective optimization model. This model is a computational framework that concurrently minimizes the costs associated with infrastructure investment, encompassing the installation and maintenance of ERS components, and the total transport expenses. These total transport costs encompass a range of factors, including the procurement of batteries, energy consumption, and toll charges. This comprehensive approach takes into account the diverse perspectives and interests of both investors and logistics companies, providing a holistic view of the intricate challenges associated with ERS adoption.

One pivotal advantage of ERS becomes evident in its capacity to extend the lifespan of batteries by reducing wear and tear during typical driving conditions. The model thoughtfully incorporates this aspect, factoring in battery purchase costs that hinge on projected lifespans. These projected lifespans, in turn, are influenced by the chosen route's electrification rate (ERS implementation).

To validate the model's effectiveness and practicality, it is subjected to a rigorous real-world case study. This case study delves into the intricacies of road freight transport in Germany, the Netherlands, Belgium, and Luxembourg. Additionally, this research introduces an enhanced Genetic algorithm, complemented by an Elitism strategy. These enhancements are designed to optimize solutions effectively within the confines of this practical context.

The findings derived from this rigorous analysis reveal a diverse Pareto set. This set showcases the delicate equilibrium between infrastructure investment and total annual transport costs. Notably, when budget constraints are absent, investing in ERS consistently proves advantageous. The total reductions in transport costs demonstrably surpass the initial ERS investment. For instance, the comprehensive electrification of 27,114 kilometers of highway results in a remarkable 30% reduction in total transport costs...