PhD Studentship: Artificial Intelligence for Building Performance - Optimising Low-Pressure Airtight

Closing Date
Sunday 31 August 2025

Reference
ENG267

PhD Studentship: Artificial Intelligence for Building Performance - Optimising Low-Pressure Airtightness Testing

Supervisors : Dr Christopher Wood (Faculty of Engineering) and Dr Grazziela Figueredo (School of Computer Science)

External Partner : Build Test Solutions Ltd (BTS)

Start Date : 1st October 2025

Eligibility: Home students only | Minimum 2:1 in a relevant discipline

Stipend : Home students only | £20780 + £2500 industry top up (per annum (tax free))

Overview

This exciting, fully-funded PhD opportunity invites applications from candidates with a robust foundation in data science, modelling, and/or engineering, and a keen interest in deploying data analysis and artificial intelligence (AI) to solve real-world problems in the built environment. The project will advance the capabilities of Pulse , an innovative low-pressure airtightness testing technology co-developed by the University of Nottingham and Build Test Solutions Ltd (BTS). This is a fantastic opportunity to work towards a PhD whilst working with both academia and industry. We are looking for a self-motivated student, with an inquiring mind who would revel in pushing the boundaries of technology.

Context and Challenge

The airtightness of a building is a critical parameter in determining energy efficiency, ventilation adequacy, and overall occupant well-being. The Pulse system-currently deployed in over 100,000 field tests-offers a rapid, non-intrusive alternative to conventional testing methods. However, its performance remains constrained by a reliance on manual configurations, suboptimal test conditions, and limited adaptability to varied building typologies.

This research aims to transform Pulse testing through AI integration-specifically leveraging descriptive, predictive, and generative modelling techniques-to enhance test accuracy, usability, and insight into leakage dynamics across diverse constructions.

Research Objectives

The project is structured around three synergistic work packages:
Descriptive Analytics: You will conduct a comprehensive analysis of the extensive Pulse dataset, uncovering latent patterns and taxonomies that define building leakage characteristics.
Surrogate Model Development: You will develop data-driven surrogate models capable of estimating air leakage in unseen building types. These models will be trained and validated against experimental data, ensuring robustness, generalisability, and practical value.
Generative Optimisation: You will implement advanced AI techniques to support next-generation Pulse design, aiming for minimised equipment footprint and enhanced diagnostic capability.

Training and Environment

The successful candidate will benefit from cross-disciplinary supervision by experts in building physics and artificial intelligence. The student will have access to research facilities within the Department of Architecture and Built Environment and the School of Computer Science. They will also undertake industrial placement and mentorship at BTS, where they will interact with practitioners, gain insights into commercial R&D, and participate in government and industry working groups.

Impact and Career Development

This project aligns with EPSRC and University strategic priorities in energy, decarbonisation, and AI technologies. It also directly contributes to several UN Sustainable Development Goals. The student will play a pivotal role in pioneering intelligent diagnostics for sustainable construction and will emerge with transferable expertise applicable across AI-driven domains.

Application Process

To apply, please send a CV, cover letter, and transcripts to Dr Christopher Wood ( ) and Dr Grazziela Figueredo ( ). Informal enquiries are welcomed.
#J-18808-Ljbffr