News

On 25 May, BuiltHub hosted its second of six workshops. Entitled "Supporting building stock transformation and a circular economy," the session was attended by 36 participants.

The session kicked off with a brief update on BuiltHub news by project Coordinator Ulrich Filippi (Senior Researcher Institute for Renewable Energy, EURAC Research). Ulrich provided an update of the BuiltHub data platform and the latest data collected. 

The first part featured experts Mikael Mangold, Tim Johansson and Pei-Yu Wu from the Research Institutes of Sweden (RISE), who introduced their latest work on "Machine learning methods to predict building data". Examples of how machine learning can be applied in building stock analysis was demonstrated with two practical examples. The first was the prediction of the presence of hazardous waste in the building stock and the second the prediction of cultural heritage values in relation to energy efficiency requirements.

This was followed by a presentation on "Construction & demolition waste data analysis to support a circular economy", by Gianluca Grazieschi and Simon Pezzutto from Eurac Research, Institute for Renewable Energy. They introduced how the BuiltHub platform can provide relevant data and insights to inform and support circular economy strategies and practices in the construction sector. Such data - including volumes per member state and potential for recovery of waste - can support further analyses, as well as the development and application of new eco-design tools based on life-cycle assessment (LCA) and life-cycle costing (LCC).

The sessions featured thoughtful points and questions from the audience, including questions on literature about machine-learning algorithms, analysis of data on hazardous waste such as asbestos & PCP (pentachlorophenol), the different carbon impacts of building materials, and soil material contamination.

The presentations are available above and the recording of the session will be available online soon!
Stay tuned here for more BuiltHub events.