PhD student in Machine Learning for Scenario Exploration in the field of Emotional and Behavioural Modelling

DTU Management’s Transport Division would like to invite applications for a 3-year PhD position starting no later than 1 June 2022. The successful candidate will join the Machine Learning for Smart Mobility Group and will work under the supervision of Associate Professor Carlos Azevedo and Full Professor Francisco Pereira.

This PhD project is part of a larger project entitled “eMOTIONAL Cities - Mapping the cities through the senses of those who make them”, funded by the EU Commission’s H2020 Framework and part of the European Cluster on Urban Health.

Project Background
The eMOTIONAL Cities project was designed to provide robust scientific evidence on how the natural and built urban environment affects human cognitive and emotional processing.Furthermore, it aims to map such neurobiological reactivity through time and space as the urban landscape change. Grasping the spatial cognition of the citizens’ behaviour and decisions while interacting with their real-life surroundings will be a breakthrough, as it will foster more inclusive urban design resulting in better individual health and well-being.

The project combines controlled laboratory experiments (Virtual Reality) with field ecological research (mobile sensing) by directly capturing peoples physiological and neurobiological responses (EEG, fMRI, portable bio sensing) while interacting and travelling within specific urban artefacts. The team will develop complex mathematical models for mapping the mental process for emotional valence and arousal under different environmental influences, and its influence in individual travel decisions to adapt or buffer environmental influences. The models are then aimed at increasing the understanding the decision-making process for better urban design and mobility policy decision making through simulation.

This specific PhD project will focus on the latter by exploring new supervised machine learning methods for (simulation) scenario discovery. Scenarios are designed to represent the possible systems states into a finite and tractable set, in which a given policy or strategy can be assessed. Several methods have been proposed in traditional scenario analysis and application across different sectors can be found in the literature including mobility, land use and health. However, it heavily relies on expert inputs regarding the identification of the main driving forces that affect the outcomes present in future scenarios,and is highly constrained by the complexity of the models at stake. New technologies and algorithms allowed for the emergence of new scenario discovery techniques, combining the use of statistical methods and big data to design representative scenarios. Scenario Discovery does not design a set of scenarios beforehand but tries to “discover” regions within the scenario space where a certain strategy or intervention fails or has above average performance.

The successful candidate will explore new machine learning methods, particularly active learning and Bayesian metamodeling in dynamic settings. Aiming at optimizing policies or design experiments, the new methods will explore the space of uncertainty and decision making in the complex simulation models of the environmental-mental-behavioural space of the eMOTIONAL Cities Project.

Together with our team (with a background in machine learning, discrete choice modelling, simulation and technology management) the candidate will review, design, implement and test different scenario discovery methods for selected modelling frameworks and contextual data-sets:

• [Large urban area-level] green/blue infrastructure and the mental health impacts on the different segments of the urban population [London data]
• [Neighbourhood-level] space modification for optimized navigation of elderly [Lisbon data]
• [Individual-level] Mental health gains from changes in daily mobility patterns [Copenhagen]

Overall, this research lies in the intersection between Machine Learning and Behavioural Modelling. This is a unique opportunity to build your research profile under a collaborative large network sustained by a European-funded project.

We are looking for excellent applicants with MSc background on Computer Science, Behavioural Modelling, Cognitive Neuroscience, Mental Health, Transportation, Applied Statistics or related.

Responsibilities and tasks

• Review, design, implement and test new machine learning-based scenario discovery frameworks.
• Contribute to the development of mathematical models of individual behaviour through the mapping of the underlying neuro- and cognitive- processes and its relationship with mental health
• Collaborate with researchers from behavioural modelling, computational and neurosciences in a truly interdisciplinary environment.
• Co-author scientific papers aimed at high-impact journals.
• Participate in international conferences.
• Participate advanced classes to improve academic skills
• Carry out work in the area of dissemination and teaching as part of the overall PhD education.

Qualifications 

• A two-year master's degree (120 ECTS points) in Computer Science (Machine Learning or Simulation), Behavioural Modelling, Applied Statistics, Cognitive Neuroscience, Mental Health, Transportation, or related.
• Excellent background in statistics and probability theory is required.
• Good programming capabilities in at least one scientific language is required.
• Experience with simulation and/or machine learning is favoured.
• Behavioural modelling or mental health disciplines in the education background is favoured.

The following soft skills are also important:

• Curiosity and interest about current and future mobility challenges and digital technologies.
• Good communication skills in English, both written and orally.
• Experience in writing and publishing scientific papers is an advantage.
• Willingness to engage in group-work with a multi-national team.

Approval and Enrolment
The scholarship for the PhD degree is subject to academic approval, and the candidate will be enrolled in one of the general degree programmes at DTU. For information about our enrolment requirements and the general planning of the PhD study programme, please see DTU's rules for the PhD education .

Assessment
The assessment of the applicants will be made until the position is filled and no later than 1 June 2022.

We offer
DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility.

Salary and terms of employment
The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union. The period of employment is 3 years.

You can read more about career paths at DTU here .

Further information
For more information, please contact Carlos Lima Azevedo, [email protected] or Francisco Pereira, [email protected] . 

You can read more about the Machine Learning for Smart Mobility group at http://mlsm.man.dtu.dk/ and DTU Management at www.man.dtu.dk/english .    

If you are applying from abroad, you may find useful information on working in Denmark and at DTU at DTU – Moving to Denmark . 

Application procedure
Your complete online application must be submitted no later than 18 February 2022 (Danish time). Applications must be submitted as one PDF file containing all materials to be given consideration. To apply, please open the link "Apply online", fill out the online application form, and attach all your materials in English in one PDF file. The file must include:

• A letter motivating the application (cover letter)
• Curriculum vitae
• Grade transcripts and BSc/MSc diploma including official description of grading scale

You may apply prior to ob­tai­ning your master's degree but cannot begin before having received it.

Applications received after the deadline will not be considered.

All interested candidates irrespective of age, gender, race, disability, religion or ethnic background are encouraged to apply.

MLSM
The Machine Learning for Smart Mobility group belongs to the Transport division of the Department of Technology, Management and Economics (DTU Management) at DTU. The division conducts research and teaching in the field of traffic and transport behaviour and planning, with particular focus on behaviour modelling, machine learning and simulation.

DTU Management
DTU Management conducts high-level research and teaching with a focus on sustainability, transport, innovation and management science. Our goal is to create knowledge on the societal aspects of technology - including the interaction between technology and sustainability, business growth, infrastructure and prosperity. Therefore, we explore and create value in the areas of management science, innovation and design thinking, business analytics, systems and risk analyses, human behaviour, regulation and policy analysis. The department offers teaching from introductory to advanced courses/projects at BSc, MSc and PhD level. The Department has a staff of app. 350. Read more  here .

Technology for people
DTU develops technology for people. With our international elite research and study programmes, we are helping to create a better world and to solve the global challenges formulated in the UN’s 17 Sustainable Development Goals. Hans Christian Ørsted founded DTU in 1829 with a clear vision to develop and create value using science and engineering to benefit society. That vision lives on today. DTU has 12,900 students and 6,000 employees. We work in an international atmosphere and have an inclusive, evolving, and informal working environment. DTU has campuses in all parts of Denmark and in Greenland, and we collaborate with the best universities around the world.