Machine Learning-Based Assessment of Masonry Degradation in Cold and Hot Climates

Heritage masonry buildings are deteriorating at an accelerating rate due to aging, weathering, and environmental exposure. Early and accurate detection of surface defects such as cracks, mortar loss, and spalling is essential to prevent progressive structural damage and enable timely, cost-effective conservation. However, current practice relies predominantly on manual visual inspection, which is subjective, labor-intensive, hazardous, and incapable of producing the quantitative defect data needed for evidence-based maintenance planning. This project develops an automated computer vision inspection system for heritage masonry buildings using deep learning to detect, classify, and quantify surface defects. A dual-climate annotated image dataset spanning heritage sites in Saskatchewan, Canada and Kuwait will be compiled and used to train and validate instance segmentation models. The research will also produce a Masonry Condition Index (MCI) translating model outputs into actionable condition scores for maintenance prioritization. The project establishes a research collaboration between the University of Saskatchewan, Canada and the Australian University, Kuwait, focused on AI-driven heritage infrastructure assessment and the training of a highly qualified person. Outcomes will support more efficient conservation of Canada’s built heritage and contribute to the growing field of automated infrastructure inspection nationally and internationally.

Faculty Supervisor:

Belal AbdelRahman

Student:

Partner:

Australian University (Kuwait)

Discipline:

Engineering

Sector:

Artificial Intelligence; Sustainability and the Environment; Construction

University:

University of Saskatchewan

Program: