Project Title: 

AI-Integrated Solutions for decarbonising Architecture, Engineering and Construction (AEC), focused on Façade Systems

Project Summary: 

The Architecture, Engineering, and Construction (AEC) sector significantly contributes to global carbon emissions, making it a critical focus for decarbonisation strategies. Achieving sustainability requires addressing both embodied carbon, which arises from material production and construction, and operational carbon. Among building components, façade systems play a pivotal role due to their significant impact on energy performance, material sustainability, and lifecycle emissions, which are all based on the type of material and the system’s performance. While façade systems alone cannot achieve full decarbonisation, their lifecycle complexity and scalability make them an ideal case study for exploring decarbonisation strategies (Pérez-Lombard et al., 2008; Perini & Rosasco, 2013). 

Despite advancements in Life Cycle Assessment (LCA), key barriers remain in integrating low-carbon materials into façade system design. Existing tools lack compatibility with essential lifecycle metrics like cost, time, and carbon footprint, limiting their utility for informed decision-making (Finkbeiner & Bach, 2021). Additionally, fragmented data flow among stakeholders creates inefficiencies and disconnected decisions, underscoring the need for a robust workflow to enable effective material selection and lifecycle optimisation (Shen et al., 2022). 

Components and Materials in facade systems have shorter lifespans, frequent maintenance requirements, and influence on thermal performance and operational carbon. Thus, studying how selecting materials impacts the performance and carbon footprint provides reliable assessment for sustainable solutions. This research uses computational methods, particularly Graph Neural Networks (GNNs), to optimise the integration of low-carbon materials into façade systems. GNNs dynamically model complex interdependencies between materials, processes, and regulations, providing actionable insights for trade-offs between upfront costs, time, and carbon footprint. 

Accordingly, this research tackles the issue of fragmented data flow and utilises Graph Neural Networks (GNNs) for making informed- decisions regarding façade systems. Additionally, it provides practical guidelines for creating scalable workflows aimed at lifecycle optimisation and offers sustainable solutions applicable to other building systems. 

References: 

Pérez-Lombard, L., Ortiz, J., & Pout, C. (2008). A review on buildings energy consumption information. Energy and Buildings, 40(3), 394–398. https://doi.org/10.1016/j.enbuild.2007.03.007 

Perini, K., & Rosasco, P. (2013). Cost-benefit analysis for green façades and living wall systems. Building and Environment, 70, 110–121. https://doi.org/10.1016/j.buildenv.2013.08.012 

Finkbeiner, M., & Bach, V. (2021). Life cycle assessment of decarbonization options—towards scientifically robust carbon neutrality. In International Journal of Life Cycle Assessment (Vol. 26, Issue 4, pp. 635–639). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/s11367-021-01902-4 

Shen, K., Ding, L., & Wang, C. C. (2022). Development of a Framework to Support Whole-Life-Cycle Net-Zero-Carbon Buildings through Integration of Building Information Modelling and Digital Twins. Buildings, 12(10). https://doi.org/10.3390/buildings12101747