Parametric archetype: An incremental learning model based on a similarity measure for building material stock aggregation

Abstract

To reduce reliance on virgin resources, the building material stock (BMS) serves as a source for material recycling and reuse. However, quantifying BMS in urban areas with scarce material data remains challenging. This paper addresses this challenge by proposing a “parametric archetype” method, which integrates similarity measures in BMS modelling. The similarity in material content between buildings is quantified using an Euclidean distance measure based on multidimensional building feature parameters. By mapping material data to similar buildings, a cohesive dataset can be formed and further enriched, enabling incremental larger-scale BMS aggregation. This model is trained using a dataset with 52 Singapore buildings, achieving a 20.24% error rate in material predictions for all urban buildings. The finding highlights the feasibility of conducting BMS aggregation with quantifiable accuracy even with limited material data points. The proposed model can be integrated with environmental impact analysis of material circularity and support sustainable urban resource management.