We are looking for a highly motivated and curious PhD candidate to contribute to the next generation of real-time, AI-driven decision support for multimodal construction logistics. The successful candidate will join the
Industrial Engineering and Management Sciences (IEMS) section of the
High-tech Business & Entrepreneurship (HBE) department at the University of Twente and will be in collaboration with
Pervasive Systems Research Group at EEMCS Faculty.This PhD position is part of the
MULTIPLIER project, a large cross-disciplinary initiative addressing one of the key challenges of the Dutch construction transition: scaling
prefabricated modular housing while drastically reducing logistics-related emissions.
With the ambition to deliver up to
50,000 prefab houses per year, modular construction creates large, predictable transport flows. MULTIPLIER leverages this as a
demand-side trigger, while
inland waterway transport (IWT) serves as the
supply-side multiplier, offering scalable capacity and significant emission reduction.
The project focuses on
end-to-end planning, connecting prefab factory production schedules with urban construction projects through an
AI-driven decision-support system that synchronises production planning, IWT capacity, terminal availability, and urban delivery constraints.
The consortium includes
University of Twente,
Hogeschool Utrecht, prefab housing factories
Plegt-Vos and
HDO Groep, IT solution providers (
Cape Groep,
Bureau Voorlichting Binnenvaart), logistics and terminal partners (
Peterson Nederland,
Port of Twente,
Metropolitan Hub System), municipalities (
Amsterdam,
Leiden,
Den Haag), ,
Logistics Overijssel and
Logistics Navigators. The academic supervision team includes
Dr. Engin Topan and
Dr. Rob Benthuis.
MULTIPLIER integrates operational data, optimization, and hybrid AI into a decision-support environment that advises
when inland shipping is feasible, and how to bundle, schedule, and synchronise multimodal prefab logistics in zero-emission contexts. This requires an end-to-end planning.
In this PhD project, you will:
-
Develop real-time optimization and hybrid AI models for end-to-end multimodal transport planning under uncertainty.
-
Design synchronization, consolidation, and matchmaking algorithms that align prefab factory production schedules with IWT capacity, terminals, and urban delivery windows.
-
Model multi-level planning decisions, connecting early feasibility assessment and quotation with tactical release planning and real-time operational dispatching.
-
Incorporate urban and site-specific constraints, such as quay availability, zero-emission zones, access windows, and reverse logistics flows.
-
Build explainable, scenario-based decision support that helps planners decide when and how IWT can be applied effectively.
-
Work closely with a large multi-actor consortium, including factories, logistics providers, ports, and municipalities.
-
Contribute to Living Lab pilots that demonstrate real-world applicability and scalable logistics impact.
We expect the PhD candidate to deliver the main deliverables to the consortium before 31 December 2028. In the remaining time of this position, the PhD candidate can write and finalize the thesis.