2 PhD Positions in Short-Term and Long-Term Transport Planning under Uncertainty

Reshape how cities plan and operate multimodal transport systems, from real-time fleet management to long-term infrastructure expansion, under deep uncertainty in a new ERC-funded project at TU Delft.

PhD positions in short-term and long-term transport planning under uncertainty

Job description

The scientific challenge

Urban transport systems generate ever-growing data streams, yet they continue to fail during disruptions. One key reason is that short-term operations and long-term planning are designed in silos. As a result, supply and demand adjustments occur out of sync, leading to congestion, inefficiencies, and service breakdowns.

The ERC consolidator project TRANSFORM addresses this gap by developing a unified framework for resilient multimodal systems under uncertainty. The project reframes multimodal mobility as a coupled system with three interacting players, mobility service suppliers, infrastructure operators, and users whose decisions and reactions unfold on different time scales. What makes TRANSFORM distinctive is the way it fuses dynamic uncertainty modeling, behaviorally informed demand management, and iterative optimization across multiple decision layers into one coherent methodology.

Your research role

We are recruiting two PhD candidates, each focusing on a different but closely connected layer of this challenge.

PhD position 1: Short-term multimodal transport planning under uncertainty

This position focuses on operational decision-making in dynamic and disrupted environments.

You will:

• Develop next-generation short-term multimodal supply management models under deep uncertainty
• Integrate estimation and combinatorial optimization for large-scale fleet scheduling and service coordination
• Design AI-driven, tractable optimization methods for real-time decision support
• Develop scalable algorithms suitable for high-dimensional, capacity-constrained transport networks

This role would be a great fit for you if you have strong foundations in machine learning (for example causal inference or predictive modelling) and an interest in combinatorial optimization, or vice versa. Experience with simulation modelling is a plus.

PhD position 2: Long-term multimodal transport planning under uncertainty

This position focuses on strategic planning and infrastructure adaptation.

You will:

• Develop robust network expansion and adaptation models under deep and structural uncertainty
• Design new uncertainty quantification approaches for unobserved, heavy-tailed, and cascading disruption effects
• Integrate causal reasoning into large-scale combinatorial optimization for infrastructure planning
• Deliver methods that are both scientifically novel and deployable in real-world strategic planning contexts

This role would be a great fit for you if you have strong foundations in AI-driven modelling and large-scale optimization, and an interest in uncertainty modelling and strategic systems design, or vice versa.

Where you will work

Your home base will be the SUM Lab in the Department of Transport & Planning (T&P) within the Faculty of Civil Engineering and Geosciences. T&P consists of 12 collaborative labs applying advanced technologies such as sensing, data analytics, modelling, and AI to turn scientific research into real-world impact. You will work closely with domain experts Yanan Xin, Ludovic Leclercq, Yousef Maknoon and Oded Cats, and collaborate with fellow PhD colleagues and researchers across behavioral modelling, optimization, and transport systems analysis.

The position is embedded in a prestigious ERC consolidator grant, offering strong scientific visibility and opportunities for international collaboration.

Job requirements

• A Master's degree in a relevant field, i.e. Operations research, Applied mathematics, Machine Learning or Computer science. Engineering degree with strong methodological backgrounds is considered as well.
• Strong background in machine learning (e.g., predictive modelling, causal inference, or uncertainty quantification) and/or combinatorial optimization (mathematical modelling, decomposition methods, heuristics, metaheuristic).
• Advanced programming skills (e.g. Python, C++ or Java).
• Ability to work both in a project team, but also independently and take leadership and responsibility for research tasks.
• Interest in interdisciplinary collaboration and contributing to teaching activities.
• Excellent communication skills in English, both written and oral.

Conditions of employment

Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1.5 year contract with an official go/no go progress assessment within 15 months, followed by an additional contract for the remaining 2.5 years assuming everything goes well and performance requirements are met.

Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from €3059 - €3881 gross per month, from the first year to the fourth year based on a fulltime contract (38 hours), plus 8% holiday allowance and an end-of-year bonus of 8.3%.

As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills. The TU Delft offers a customisable compensation package, discounts on health insurance, and a monthly work costs contribution. Flexible work schedules can be arranged.