Job Description

Introduction

The Singapore-ETH Centre's Future Cities Lab Global, in collaboration with the National University of Singapore, has an opening for a post-doctoral researcher in Travel Behavior and Demand Modeling.

Project background

This project translates methods for fusing household travel survey (HTS) data with passively collected mobility data (e.g., transit smart-card records) into the travel demand modelling workflow of the Land Transport Authority (LTA) of Singapore. It will assess whether models estimated from fused, population-scale activity plans can reproduce the behavioural relationships and planning conclusions that LTA currently derives from the HTS, and how far the survey sample can be reduced without compromising them. The project also extends large language model-based population synthesis to generate synthetic activity schedules at an urban scale and evaluates whether these can credibly supplement a reduced survey sample.

Job description

The candidate will mainly work on translating population-scale mobility data fusion methods into operational evidence for transport planning, in collaboration with the Land Transport Authority (LTA) of Singapore.

Transport planning models rely heavily on household travel survey (HTS) data, which poses three challenges. First, the HTS is costly and burdensome to respondents, so it is collected infrequently and covers only a small fraction of the population. Second, it has low spatial resolution and is not dynamic enough to capture system-level changes between survey rounds. Third, although fusing HTS data with large-scale passively collected mobility data (e.g., transit smart-card records) can generate complete daily activity plans for an entire synthetic population, these fused data have so far been validated only against external aggregate benchmarks, not within an agency's own modelling workflow. To address these challenges, the candidate will focus on the following tasks:

Estimating a set of transport models and planning indicators selected with LTA (e.g., trip generation rates and destination, mode and departure-time choice models) from both the complete HTS and the fused population activity plans, and comparing parameter estimates, elasticities, goodness of fit and policy conclusions under agreed test scenarios.
Conducting sample-reduction experiments, fusing progressively smaller HTS samples with smart-card data, to identify the minimum survey sample size required for each application and where fusion offsets the loss of survey observations.
Extending the team's fine-tuned, lightweight, open-source LLM-based population synthesis method to generate full sequential travel diaries, and assessing whether such synthetic diaries can credibly supplement a reduced HTS sample in downstream behavioural models.

The candidate will work on a daily basis with the principal investigator at the National University of Singapore, Assist. Prof. Prateek Bansal, who will lead the research on data fusion and generative modelling. He/she will coordinate closely with LTA's modelling and survey-design staff, including regular technical meetings, a mid-project checkpoint and a final evaluation workshop, and will support capability transfer so that LTA can re-run the analyses independently.

Selection Criteria

The successful candidate for this post-doctoral position will have:

A doctoral degree in spatial planning, transport planning, civil engineering, systems engineering or a related field.
A good grasp of probability theory, optimization, deep learning, discrete choice models, activity-based travel demand modelling, and traffic assignment.
Experience of doing methodological work - reflected through publication record.
Proven experience and strong programming skills in Java, Python and/or R, as well as in the use of GIS tools.
Proficiency in written and spoken English.

Why SEC is your employer of choice

Accredited with 5 Tripartite Standards by Tripartite Alliance for Fair & Progressive Employment Practices (TAFEP) Singapore.
A diverse workplace with 32 nationalities, offering ample opportunities for mutual learning.
Positive and inclusive working environment.
25 days of annual leave for fixed-term contracts.
1 day of Birthday Leave.
Annual dental benefits.
Committed to being a supportive employer as you prioritize your physical and mental wellness.
Comprehensive healthcare insurance coverage.
Flexible hybrid work arrangement (up to 2 days per week from home).
Abundant networking opportunities across various disciplines.
Accredited with NS mark certification.

The Singapore-ETH Centre is an equal opportunity and family-friendly employer. All candidates will be evaluated on their merits and qualifications, without regards to gender, race, age or religion.

Curious So are we.

We look forward to receiving your online application with the following documents:

A first-author publication which has proposed a novel method and showed its superiority.
A curriculum vitae (with a list of publications and contact information of at least two referees).
Grade records of all university courses taken as well as diplomas.

Applications via email or postal services will not be considered.

Work location: 1 Create Way, CREATE Tower, Singapore 138602 (NUS University Town)

Remuneration will be commensurate with the candidate's qualifications and relevant experience.

Further information about The Singapore-ETH Centre can be found on our website: https://sec.ethz.ch/

For further information, please contact: Dr Prateek Bansal (Assistant Professor, National University of Singapore) at [Confidential Information], (strictly no applications)