PhD Studentship: Deep Learning for Traffic Prediction and Analysis

Start date: April 2025

Full-time: 3 years

Project details

We are excited to offer a fully funded PhD position at the intersection of machine learning and transportation. The transport sector, both in the UK and globally, faces critical challenges, including severe congestion—which costs London alone £5 billion in lost productivity annually and accounts for 5% of the UK’s GDP. Additionally, domestic transport remains the UK’s highest carbon-emitting sector, contributing to air pollution linked to 43,000 premature deaths annually.

Machine learning holds great promise for tackling these issues; however, effectively integrating diverse data sources – such as weather conditions, event schedules, and multi-sensor data – remains a significant challenge. This PhD position will focus on developing foundational models to address these limitations, aiming to enhance prediction accuracy and model explainability, ultimately contributing to more efficient, sustainable, and resilient transport systems.

We seek a candidate with a strong quantitative background and a passion for advancing machine learning methodologies in traffic prediction. The successful candidate will have the opportunity to collaborate with leading researchers within the UK and internationally, with additional funding available for travel and conference attendance.

Supervisors: Primary Supervisor: Haitao He

Entry requirements

Our entry requirements are listed using standard UK undergraduate degree classifications i.e. first-class honours, upper second-class honours and lower second-class honours.

Entry requirements for United Kingdom

Candidates should have, or expect to achieve, a first-class or 2:1 honours degree (or equivalent) in computer science, data science, mathematics, or a related field. The candidate should have strong analytical and programming skills. Previous experience with deep learning, multitask learning, agent-based systems, transport simulations, or a relevant master’s degree and/or employment experience will be an advantage.

English language requirements

Applicants must meet the minimum English language requirements. Further details are available on the International website.

Fees and funding

Tuition fees for 2024-25 entry

UK fee: Fully funded Full-time degree per annum

International fee: £27,500 Full-time degree per annum

Tuition fees for 2025-26 entry

UK fee: Fully funded Full-time degree per annum

International fee: £28,600 Full-time degree per annum

Fees for the 2024-25 academic year apply to projects starting in October 2024, January 2025, April 2025 and July 2025. Fees for the 2025-26 academic year apply to projects starting in October 2025.

Tuition fees cover the cost of your teaching, assessment and operating University facilities such as the library, IT equipment and other support services. University fees and charges can be paid in advance and there are several methods of payment, including online payments and payment by instalment. Fees are reviewed annually and are likely to increase to take into account inflationary pressures.

The studentship is for three years and will provide the successful applicant (UK or international) with a tax-free stipend of £19,237 per annum (2024/25 rate) for the duration of the studentship.

How to apply

All applications must be made online via the above ‘Apply’ button and must include a completed studentship application form (instead of a personal statement) and a two-page research proposal based on the project description outlining how you would approach the project and what methods you would use. Under programme name, please select 'Architecture, Building and Civil Engineering'. Please quote reference number ABCE-HH2-24.

To avoid delays in processing your application, please ensure that you submit the minimum supporting documents including an up-to-date CV. A personal statement is not required. ABCE will use these selection criteria to make a decision on your application.

Application deadline: 15 December 2024

Advert information