Open PhD position [TSE 134] Generation and Analysis of Synthetic data for TRansport Applications (GASTRA)

At the Chair of Transportation Systems Engineering (TSE) of the Technical University of Munich (TUM), we seek an excellent, motivated doctoral researcher for our DFG-funded research project GASTRA in collaboration with the Technion Institute of Technology (Israel). The research will be jointly supervised by Prof. Constantinos Antoniou (TUM) and Prof. Tomer Toledo (Technion). 

Description of the Chair

The Chair of Transportation Systems Engineering (TSE) undertakes research in the transportation field with a specific focus on modeling and simulating transportation systems, implementing data science and data analytics in transport and human factors analysis, and machine learning and deep learning. The TSE chair researches multimodal and unimodal freight and passenger transport demand and supply modeling, allowing for contributions to the optimization, calibration, and validation of transport models. In this direction, the applications of big data acquisition and analysis, and flexible data-driven models are examined. The TSE chair also contributes to analyzing human factors in transport-related fields such as road safety modeling, behavioral economics applications, and modeling of factors that affect user engagement in transportation systems.

Project description

Synthetic data plays a critical role in the planning, design, and operation of engineered systems, particularly in transportation, where accurate performance predictions under diverse conditions are essential. Transportation systems are inherently complex and nonlinear, driven by human behavior that introduces significant variability and noise. People make heterogeneous choices about travel activities, modes, routes, and vehicle control, often exhibiting inconsistent decisions even in similar situations. These complexities, compounded by the inability to perfectly execute intended actions, necessitate robust models to support prediction-making processes. Synthetic data offers a promising solution to simulate these dynamics, enabling the development and testing of models that capture the intricacies of human behavior and system performance. 

This research aims to explore various methods for generating synthetic data that meet specific requirements, evaluate its quality, and utilize it—either independently or in combination with real data—for training and testing transportation-related models. The project will also focus on applying these models to predict outcomes in “what-if” scenarios. To facilitate widespread adoption, the developed methods will be implemented as an open-source software toolbox, making them accessible to the research and practitioner community. The PhD position includes work on: 

 

• Development of a systematic literature review framework and consolidation of the state of the art: Consolidate the state of the art in traffic data analysis, identifying the gaps in data collection, gathering, and integration in support of its utilization for analysis and prediction 
• Formulation and specification of the synthetic data generation methodology: Create a methodology for imputation, generation, and integration of available datasets, for various classes of data types, using processes of learning from the existing data 
• Development of the open data generation toolbox: Develop an open-source toolbox for applying the methodology, which can be easily further utilized, extended, and deployed by the research community and practitioners. 
• Demonstration of the toolbox in the use cases: Demonstrate the applicability of the toolbox to different domains, in particular, (i) naturalistic driving data and (ii) prediction of traffic flow characteristics 

Requirements

• Have an MSc degree in a relevant field (e.g., transportation engineering, data science, computer science); 
• Be enthusiastic about researching transport-related projects and understand the fundamentals of transportation systems optimization and machine learning models; 
• Have strong analytical skills; 
• Have excellent research, academic writing, and presentation skills; 
• Have a strong programming background and experience using e.g. Python or R; 
• Have excellent working knowledge (written and oral) of English (knowledge of German will be considered a plus); 
• Be able to work with strict deadlines. 
• In addition to the above, candidates must fulfil the general TUM admission requirements: https://www.gs.tum.de/en/gs/path-to-a-doctorate/application/requirements/ 

Conditions of Employment

Following the Public Sector Collective Agreement of Länder (TV-L), TUM offers a competitive compensation package. This position is a 100% TV-L 13. More information on the offered wages can be found at oeffentlicher-dienst.info/tv-l/west/ 

TUM is an equal-opportunity employer. Qualified women are particularly encouraged to apply. Applicants with disabilities are treated with preference, given comparable qualifications.