PhD Studentship: AI Optimisation of Green Roofs and Facades for Low-Carbon, Heat-Resilient Buildings

Applications are invited for a funded PhD to develop an AI-enabled framework for optimising building-integrated green infrastructure.

Green roofs and green façades can reduce building energy demand, lower operational carbon emissions and improve local thermal conditions. However, their performance varies according to building type, design, location, vegetation and climate. This project will investigate how artificial intelligence, building-performance modelling and geospatial analysis can be combined to identify effective green-infrastructure solutions for different buildings and urban settings.

Research objectives

The successful candidate will develop and test a decision-support framework to:

• predict the energy, carbon and thermal effects of green roofs and façades;
• identify suitable green-infrastructure configurations for selected building types;
• determine where interventions could provide the greatest benefits;
• evaluate performance under current and future climate conditions;
• balance energy, carbon, thermal and practical considerations through multi-objective optimisation.

The research will integrate building characteristics, weather records, energy data, land-use information and satellite-derived geospatial data. The likely methodology will combine building-performance simulation, machine learning, GIS, remote sensing and optimisation.

Building simulations will evaluate alternative green-roof and façade configurations. Machine-learning models will then predict performance efficiently across a wider range of buildings and climate scenarios. GIS and remote-sensing data will support the spatial assessment of suitable locations and environmental conditions.

The framework will be developed and evaluated using selected building types and case-study areas. The principal outcome will be an AI-enabled decision-support tool or framework to help building owners, designers, planners and policymakers select interventions that reduce operational carbon and improve resilience to overheating.

The project is primarily computational and does not require routine laboratory or fieldwork. Its final scope will be refined with the successful candidate to ensure that it remains achievable within the PhD period.

Candidate profile

Applicants should have, or expect to obtain, a good first degree (First Class or Upper Second Class) and a master’s degree with Merit or Distinction in building engineering, architecture, civil or environmental engineering, computer science, data science, geography or a related discipline.

Overseas applicants from non-English speaking countries must have an IELTS (International English Language Testing System) score of 6.5 overall, with no individual component scoring below 6.0.

Applicants should demonstrate quantitative and analytical ability, together with Python programming experience and experience in artificial intelligence or machine learning. They should also have experience in one or more of the following areas:

• GIS or remote-sensing analysis;
• building-energy or environmental modelling; or
• optimisation and statistical analysis.

Experience across all three additional areas is not required, but applicants should be willing to develop complementary skills during the project. An interest in low-carbon buildings, climate adaptation and urban sustainability is essential.

Funding and eligibility

Funding Full tuition fees and a tax-free stipend of £18,000 per year

Eligibility Home and International candidates

Proposed start September 2027

Duration 36

How to apply

Applications should be submitted through the apply button above.

Applicants must complete an online application form and provide: a research proposal outline prepared using the doctoral application template; a current CV; a transcript of their highest qualification, and proof of English language ability for overseas applicants from non-English speaking countries.

For informal enquiries, please contact Professor Ali Bahadori-Jahromi at ali.jahromi@uwl.ac.uk.

Advert information