Postdoc Adaptive Optimization and Learning Methods for Transportation Systems

Postdoc Adaptive Optimization and Learning Methods for Transportation Systems

Published Deadline Location
12 Oct 21 Nov Delft

You cannot apply for this job anymore (deadline was 21 Nov 2023).

Browse the current job offers or choose an item in the top navigation above.

Would you be interested in representing the adaptive nature of decision making within agent-based models for transportation?

Job description

One of the biggest challenges for transportation systems is how to wisely utilize the available resources while responding to the demand.  According to Eurostat, 20% of road freight kilometres in the EU in 2020 were driven by empty vehicles and this is similar for other modes of transportation. There are various reasons for the underutilization of transportation capacity. Firstly, there are uncertainties in the system, e.g., demand is fluctuating, the travel and service times vary significantly. In order to cope with that, operators frequently end up allocating more resources than needed. Secondly, transport systems have complex supply-demand interactions which makes it difficult to optimize the decisions on different resources. Underutilization of capacity entails costs that do not generate revenue and contribute to CO2-emissions, whereas the transportation sector is striving for sustainability goals. Being able to adapt the decisions – e.g., the network design, allocation of capacity, routing and scheduling - according to evolving demand and conditions in the transport network is a promising direction to improve the utilization of available resources.

ADAPT-OR project is funded by European Research Commission for Fundamental Research. The aim of ADAPT-OR is to develop self-learning capabilities towards adaptive transportation systems by leveraging the intersection of operations research, behavioural modelling and machine learning methodologies. The idea is to make use of information from the system itself across different decision-making levels, from the users and from the external environment in a self-learning manner in order to continuously adapt the decisions at different levels. For example, with a continuous input from the operational level on the delays in different parts of the network, the fleet allocation can be adapted at the tactical level. Similarly, depending on the trends in behavior for a given delivery service, the network design can be adapted.

This postdoctoral position focuses on the adaptive optimation models within ADAP-OR that will exploit transport optimization models and machine learning hand in hand to reach the self-learning capability. An agent-based framework will be developed where the agents and their interactions in the transport system are represented. Model-based learning will be the core of the self-learning capability where transportation domain knowledge is combined with the data-driven techniques in order to have tractable and effective methodologies. This is challenging as transportation problems are at the network level and involve different entities with different characteristics who are making decisions related to different time scales. As the postdoctoral researcher, you will be interacting with the other researchers working for the ADAPT-OR project in order to make use of the synergies as well as for the development of the case studies to showcase the benefits of the methodologies.

The position is available as of 01 Jan 2024 with flexibility in terms of the start date. You will be joining the group of Bilge Atasoy, working on adaptive transportation and logistics. The group has members with expertise on operations research, behavioural modelling and machine learning with applications in transportation. There is a vivid interaction in the group to foster collaboration and transfer of knowledge. The project will have opportunities for collaborations with leading universities worldwide. You will also have the opportunity to get teaching experience in topic-wise related courses. 


Delft University of Technology (TU Delft)


We are looking for a candidate who has operations research background, is interested in integrating machine learning techniques and optimization and also preferably has transportation research knowledge. As the project is a multi-faceted one, we expect candidates with an appreciation of social challenges in the context of implementing new sustainable frameworks and business models, preferably in combination with economics, behavioral modeling and/or policy analysis.

  • PhD in Operations Research, Transportation, Industrial Engineering, Applied Mathematics or any other related field.
  • Attitude to function both in a team and independently.
  • Willingness to conduct multidisciplinary research in collaboration with both scientific and industrial partners.
  • Drive for excellence in research
  • Good communication skills  

Conditions of employment

Fixed-term contract: 2 years.

Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities. The TU Delft offers a customisable compensation package, discounts on health insurance, and a monthly work costs contribution. Flexible work schedules can be arranged.

For international applicants, TU Delft has the Coming to Delft Service. This service provides information for new international employees to help you prepare the relocation and to settle in the Netherlands. The Coming to Delft Service offers a Dual Career Programme for partners and they organise events to expand your (social) network.


Delft University of Technology

Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context.

At TU Delft we embrace diversity as one of our core values and we actively engage to be a university where you feel at home and can flourish. We value different perspectives and qualities. We believe this makes our work more innovative, the TU Delft community more vibrant and the world more just. Together, we imagine, invent and create solutions using technology to have a positive impact on a global scale. That is why we invite you to apply. Your application will receive fair consideration.

Challenge. Change. Impact!


Faculty Mechanical, Maritime and Materials Engineering

From chip to ship. From machine to human being. From idea to solution. Driven by a deep-rooted desire to understand our environment and discover its underlying mechanisms, research and education at the 3mE faculty focusses on fundamental understanding, design, production including application and product improvement, materials, processes and (mechanical) systems.

3mE is a dynamic and innovative faculty with high-tech lab facilities and international reach. It’s a large faculty but also versatile, so we can often make unique connections by combining different disciplines. This is reflected in 3mE’s outstanding, state-of-the-art education, which trains students to become responsible and socially engaged engineers and scientists. We translate our knowledge and insights into solutions to societal issues, contributing to a sustainable society and to the development of prosperity and well-being. That is what unites us in pioneering research, inspiring education and (inter)national cooperation.

Click here to go to the website of the Faculty of Mechanical, Maritime and Materials Engineering. Do you want to experience working at our faculty? These videos will introduce you to some of our researchers and their work.


  • Postdoc
  • Engineering
  • 36—40 hours per week
  • Doctorate
  • TUD04529


Delft University of Technology (TU Delft)

Learn more about this employer


Mekelweg 2, 2628 CD, Delft

View on Google Maps

Interesting for you