Engineering Better Social Outcomes through Requirements Management and Integrated Asset Data Processing

About the Project

The built environment profoundly influences human wellbeing shaping not only our physical comfort and behaviour, but also our cognitive and emotional states. Yet, despite decades of architectural and environmental psychology research, the mechanisms that link spatial design, perception and neurological response remain poorly quantified. This PhD research seeks to bridge that gap by combining advanced Building Information Modelling (BIM) agentic design, neuroimaging, radiological measurement and AI-based analysis to create a new evidence base for human-centred design.

Building on recent work that has established a three-spoke framework connecting physical, perceptual and neurological data streams, the next stage of this research extends the model into radiology, high-resolution imaging and LLM data processing. It will investigate how features such as light, geometry, materiality and spatial density are encoded and interpreted by the brain, using tools such as EEG, fMRI, CBCT and MRI derived morphometrics to map measurable neural and physiological responses to environmental stimuli, thus closing the “digital loop” between design, asset use and performance.

The research will employ an integrated pipeline of environmental design and simulation, imaging and AI-driven data fusion, enabling multi-modal analysis of how people perceive, process and respond to different spaces and environments. By aligning radiological data with perceptual metrics and physical measurements, the study will explore new ways to model spatial experience, from clinical and therapeutic environments to workplaces, learning settings and functional digital twins of the built environment.

Key themes include:

• The use of radiological and neuroimaging modalities to measure embodied response to architectural and built environment form.
• Development of perceptual frameworks to integrate imaging data with design variables and specification inputs.
• Application of machine learning and graph-based AI models to interpret multi-dimensional datasets linking structure, spatial definition, physical condition and performance, human behaviour and cognition.
• Implications for design policy, healthcare environments and neuro-inclusive architecture.

The successful candidate will have a background in architecture, built environment, environmental design, psychology or biomedical engineering and an interest in human perception, spatial cognition, or data-driven design. Experience with neuroimaging, computational modelling, or building performance analysis would be advantageous but not essential.

This is a unique opportunity to work at the intersection of architecture and the built environment, neuroscience, data science and radiology, advancing a new generation of research methods capable of linking human experience directly to spatial form. The findings will contribute to the emerging field of neuro-informed environmental design and help define measurable pathways to design buildings and cities that truly support human wellbeing.

Supervisor Information

Professor Jason Underwood

Professor Mark Bew

Prof Jason Underwood, Prof Mark Bew, Dr Mustapha Munir, Dr Katy Szczepura

Applications accepted all year round

Self-Funded PhD Students Only