AI-enabled Circular Built Environments

Challenges and solutions

The building industry is among the most carbon and resource-intensive industries globally. Future-proofing the existing building stock is critical in responding to climate change and mitigating resource depletion. Circular Economy is an emerging approach to sustainable development, which attempts to decouple economic growth from the consumption of finite resources. However, the adoption of circular practices in existing buildings presents significant challenges due to a lack of systemic data and accessible information.

This multi-disciplinary research project proposes leveraging Artificial Intelligence (AI) and Machine Learning (ML) algorithms to address this data gap at scale and support the transition to zero-energy, zero-carbon and zero-waste built environments. This study has huge potential to mitigate the impacts of the building sector on the environment and guide future policy-making.

Research themes

How can AI support transitioning to Circular Built Environments (CBE)?

• How to identify building-specific characteristics and quantify building materials and assemblies from available image data?
• How to assess building envelope performance and infer appropriate strategies for renovation or end-of-life scenarios?

Funding opportunities

The Innovation and Ideas Grant (City of Sydney) prioritises innovative projects that contribute to making Sydney a leading environmental performer, focusing on resilient communities and innovative economies.

Long-term opportunities may include CRC-P, ARC Linkage and ARC Centre of Excellence.

External partners and competition

We are not aware of other groups in Australia working on similar projects.

Potential partners:

• University of New South Wales, CRC for Low Carbon Living
• University of Melbourne, The Retrofit Lab
• Circular Australia

Short- and medium-term goals and KPIs

1. Scoping phase to inform the data collection by identification of relevant parameters and boundaries to be considered.
2. Data collection for building characterization, including identification and quantification of construction materials and systems.
3. Iterative training and validation of ML models.