iBuildGreen

The spatiotemporal dynamics of building stocks are key to circular economy and green transition but remain hitherto poorly characterized due largely to the enormous amount of data needed. Can we harness the increasingly available remote sensing and machine learning techniques to automate building stock characterization? What added values would such high-resolution understanding bring to discussions on societal circular and green transition? These are the fundamental questions we aim to answer based on a multidisciplinary and novel set of methodologies, using Denmark as an example. If successful, this could enable a paradigm shift in building stock modelling and pave the way towards a win-win-win for digitalization, circular economy, and climate strategies in a green transition.

This project is carried out in partnership with South-Denmark University (SDU). The focus at Aalborg University has been primarily on the development of a macro-component model of the building stock, describing buildings' material content based on publicly available data from the national building registry.