starting point: 

How is design knowledge embedded in Architecture, Engineering, and Construction (AEC) sector data (BIM, CAD, etc.) and what methods (for example, artificial intelligence, machine learning) are available for harvesting design data embedded in past projects?

This topic may include consideration of: the usefulness of design data and its security; along with legal, ethical, and commercial challenges to using design data.

project summary: 

Urban metabolism describes how cities consume, transform, and discard resources through their material “bones and muscles”—buildings and infrastructure (Fu et al., 2023). Understanding and assessing these processes is a foundation for promoting sustainable urban development. Current studies often rely on material flow analysis, dynamic stock models, and life cycle assessment to measure material and energy flows, analyse building stocks, and explore the spatial distribution of metabolic processes (Yuan and Lu, 2024). 

However, most research focuses on single cities or regions and overlooks the diversity of metabolism patterns shaped by differences in urban growth and demand. For example, expansion-oriented metabolism is marked by rapid growth in building stocks and large inflows of construction materials, while renewal-oriented metabolism is dominated by renovation, retrofitting, and demolition (Mao et al., 2022). Hybrid cases combine both (Liang et al., 2022). These patterns show different intensities of material inflows and outflows, which in turn create distinct environmental and social impacts (Bao et al., 2023, EEA, 2022). Thus, dynamic evaluation of metabolism patterns and management strategies is essential. Traditional statistical and linear models often struggle with high-dimensional, non-linear, and spatially diverse data, limiting their ability to capture dynamics or simulate interventions. By contrast, advances in machine learning and AI make it possible to extract hidden features from complex datasets, classify metabolism patterns more accurately, and model the effects of sustainability-oriented strategies. 

This study aims to develop a data-driven framework to dynamically assess and classify regional building metabolism and evaluate management interventions. It will integrate multiple data sources—OSM, Google Maps, remote sensing, demographic and economic data, and so on—together with machine learning and AI technologies. The objectives are: (1) to identify metabolism types (expansion, renewal, hybrid); (2) to build a framework for cross-regional comparison; and (3) to use scenario simulations to assess the impacts of interventions. The findings will improve understanding of metabolism diversity at the regional scale and provide evidence for strategies that support resource efficiency, carbon reduction, and sustainable urban development. 

References: 

1. Bao, Z. K., Lu, W., Peng, Z., Ng, S. T. (2023). Balancing economic development and construction waste management in emerging economies: A longitudinal case study of Shenzhen, China guided by the environmental Kuznets curve. Journal of Cleaner Production, 396, 136547. https://doi.org/10.1016/j.jclepro.2023.136547. 

2. European Environment Agency（EEA，2022）《Building renovation: where circular economy and climate meet》 

3. Fu, C., Deng, T. & Zhang, Y. (2023).  Urban metabolic flow in China’s megacities doubled by material stock accumulation since the 21st century. npj Urban Sustainability 3, 52. https://doi.org/10.1038/s42949-023-00132-x 

4. Liang, H., Bian, X., Dong, L., Shen, W., Chen, S.S., & Wang, Q. (2022). Mapping the evolution of building material stocks in three eastern coastal urban agglomerations of China. Resources, Conservation and Recycling, 190, 106651. https://doi.org/10.1016/j.resconrec.2022.106651. 

5. Mao, T., Liu, Y., Chen, W.Q., Li, N., Dong, N., & Shi, Y. (2022). Quantifying spatiotemporal dynamics of urban building and material metabolism by combining a random forest model and GIS-based material flow analysis. Frontiers in Earth Science, 10. https://doi.org/10.3389/feart.2022.944865. 

6. Yuan, L., Lu, W (2024). Centennial evolution of Hong Kong 1910–2050: a building material metabolism perspective. Energy. Ecology and Environment. 9, 215–229. https://doi.org/10.1007/s40974-024-00322-y.