A scalable data collection, characterization, and accounting framework for urban material stocks

Building stocks represent an extensive reservoir of secondary resources. However, common bottom-up characterization of these, often based on archetypal classification of buildings and their corresponding material intensity, are still not suitable to adequately inform circular economic strategies. Indeed, these approaches typically result in a loss of building-specific details, and a building stock characterization in terms of material mass, for example, glass, rather than component, for example, window. To deliver this higher resolution of details, a scalable approach to urban stock characterization, that enables a bottom-up estimation of building stocks at the building component level, is needed. In this paper, we present a framework to automate the characterization of urban stock. By using and combining a mobile-sensing approach with computer vision, urban stocks can be captured as 3D surface maps allowing the identification and semantic classification of stock objects, components, and materials. We demonstrate the potential of this framework through a case study of a neighborhood in Sheffield, UK, by using a prototype workflow comprising a custom-made mobile-sensing platform and an existing suite of neural network models to calculate an estimate count of buildings external doors and windows. The prototype implementation of the framework achieves comparable total and building-level component counts with those achieved through manual human counts. Such automated estimation of components enables an understanding of opportunities across the circular economic hierarchies and informs stakeholders across the supply chain to better prepare for the implementation of circular strategies including building refurbishments.