PhD scholarship - Understanding Mobility Cultures Across Europe using Machine Learning and Big Data - DTU Management

The Transportation Science Division at the Technical University of Denmark (DTU) invites applications for a 3-year PhD position at the intersection of Social Data Science and Computer Science. The successful candidate will join the Intelligent Transportation Systems Section and will work under the supervision of Associate Professor Carlos Lima Azevedo and Professor Sonja Haustein (Human Behaviour Section).

Understanding the role of transport policies and technologies in shaping urban mobility cultures is crucial for guiding sustainable mobility transitions in European cities. This PhD project aims to map and analyse how mobility cultures vary across Europe and how they evolve over time in response to policy and technological changes.

The PhD student will work on clustering cities based on mobility-related open data, including demographic trends, transport infrastructure and performance, economic indicators, and land use across time. The student will be responsible for collecting large public datasets and supporting the design of micro-surveys for large-scale deployment in multiple cities. For investigating how urban mobility cultures differ spatially and evolve in response to key urban feature changes, we will employ state-of-the-art machine learning methods to analyse high-dimensional (time series) data. For the selected candidate, there will be possibilities to influence the project and develop new project ideas within the project frame.

The position involves conducting research, presenting findings at scientific conferences, writing research articles, participating in PhD courses, and gaining experience in teaching and knowledge dissemination.

The PhD position is one of 13 PhD positions in the Marie Skłodowska Curie Action Doctoral Network Scheme TRANSFORM. TRANSFORM focuses on examining whether and to what extent transformative practices are effective mechanisms for activating and consolidating transitions in urban mobility cultures and their resulting socio-spatial effects. For more information on the project and the other 12 PhD positions, please visit the TRANSFORM homepage: www.transformresearch.eu. 

As part of the doctoral network, you will participate in a joint interdisciplinary training programme organized by the participants of TRANSFORM. This includes, e.g., summer schools with your fellow PhDs and secondment at academic and practice partners of the network.

You either have a MSc background in Social Data Science, Computer Science or related areas. Besides showing experience with machine learning, including deep learning, the candidate should be able to demonstrate knowledge about human behaviour, social sciences or psychology (e.g. through courses, applications or student projects), with a preference for experience in handling large survey data.

Responsibilities and qualifications
Urban mobility is a key determinant of sustainability in European cities, influencing sustainability, economic productivity, and overall quality of life and well-being. As urban areas continue to grow, cities must adopt innovative policies to support efficient and sustainable mobility systems. Mobility cultures — comprising mobility behaviours, transport infrastructure, and societal attitudes toward transportation modes — offer a crucial perspective for understanding urban mobility patterns. 

In this study, we introduce a comprehensive typology of mobility cultures spanning several European cities, by integrating large-scale public datasets from various social and economic sectors with machine -learning based analysis. In addition, the study will involve the design and deployment of micro-surveys at the individual level to capture behavioural and attitudinal insights on urban mobility.

To process and analyse these large and complex datasets, we will explore advanced machine learning techniques, including deep-learning, transformer-based and Bayesian clustering for big data. Big data management and processing will be a critical component of the research, ensuring the efficient handling of diverse datasets and optimizing computational workflows.

We explore the implications of this framework for urban planners and policymakers, examining how different mobility cultures influence travel behaviour, modal choices, and sustainability outcomes.

Your primary tasks will be to:

• Explore, develop and evaluate different machine-learning methods for defining urban mobility culture typologies
• Big Data analysis and visualizations
• Collect public data at the urban level for cities across Europe on socio-, economic-, demographic- and mobility-related indicators
• Design and support the collection and analyse large scale micro-survey data
• Analy