Dr Gulala Aziz is a researcher specialising in sustainable housing and data-driven analysis. She holds both a bachelor’s and a Master’s degree in Architectural Engineering and has contributed to the design and delivery of residential and institutional construction projects.
She completed her PhD at Leeds Beckett University on damp issues in English Housing and she used a mixed-methods approach to enhance damp diagnostics and predictive modelling. By integrating real-world damp inspection data, expert consultation, and machine learning, her work aims to shift damp management from a reactive to a proactive approach, enabling more informed decision-making, effective inspection prioritisation, and early identification of homes at risk before issues escalate.
Title of thesis:
Data-Driven Insights on Damp in English Housing: Surveying Practices, Remedial Measures, Stock Analysis, and Predictive Modelling
Brief description of the project:
Her research explores how data-driven methods can enhance the diagnosis and management of damp in English housing. Using a mixed-methods approach, it combines qualitative content analysis with quantitative techniques including Analytic Hierarchy Process (AHP), machine learning, and statistical analysis. The study draws on real-world data from housing inspections, surveyor comments, photographic evidence, a specialist questionnaire survey, and the Energy Performance Certificate (EPC) database.
The analysis of current damp management practices reveals a reactive, visually driven approach with inconsistent diagnostics. AHP is used to prioritise diagnostic tools and remedial measures based on cost, effectiveness, and feasibility. Findings indicate that while some advanced methods are valued, they are often deprioritised due to practical limitations.
Machine learning clustering is applied to 1,655 damp homes, identifying three distinct damp-prone profiles based on building characteristics and energy performance. A separate defect analysis highlights condensation as the most prevalent issue, particularly in bathrooms and bedrooms.
A supervised machine learning model is then developed using disrepair data of more than 2000 homes in England, with applying supervised machine learning and SHAP (SHapley Additive exPlanations) analysis to predict damp risk in over 35,000 homes. Key predictors include heating cost, wall efficiency, and construction age.
Director of Studies: Dr Adam Hardy
Supervisor: Professor David Glew