Home > Research > Publications & Outputs > AILab - Artificial Intelligence for Low Carbon ...
View graph of relations

AILab - Artificial Intelligence for Low Carbon Buildings

Research output: Contribution to conference - Without ISBN/ISSN Conference paper

Published
Publication date31/01/2025
<mark>Original language</mark>English
EventAI AND ARCHITECTURE SUMMIT 2025: SUSTAINABILITY - Morecambe Wintergardens, Morecambe, United Kingdom
Duration: 31/01/20251/03/2025
https://www.lancaster.ac.uk/arts-and-social-sciences/events/ai-and-architecture-summit-2025/#:~:text=Event%20Details&text=In%20partnership%20with%202024%20Stirling,st%20January%202025%2011.00%20%E2%80%93%2015.00.

Symposium

SymposiumAI AND ARCHITECTURE SUMMIT 2025
Country/TerritoryUnited Kingdom
CityMorecambe
Period31/01/251/03/25
Internet address

Abstract

The AI:Lab asked: how do processes of Artificial Intelligence (AI) target the reduction of carbon expenditure in the design and construction of buildings, and what role do architects, engineers, our students and the public have in the process of de-carbonisation using new tools of AI?

The built environment has a vital role to play in responding to the climate emergency - addressing upfront carbon is a critical and urgent focus. Buildings are currently responsible for 39% of global energy related carbon emissions: 28% from operational emissions with the remaining 11% from embodied carbon in materials and construction.

Working with Grimshaw Architects, and with a focus on Morecambe Bay, our key objective was to establish the Ai:Lab as a vehicle to recognise the cross-disciplinary demands and opportunities of AI, to capture these at an early stage, and produce impactful research in communities and across the construction sector.

The Lab ran during 2024, concluding with a symposium and exhibition on the use of AI in designing low carbon buildings. Four key areas of focus were established:

1. LLM Workflow Integration with BIM for the Zero Carbon Standard
2. Local Knowledge LLM Workflow Integration
3. 3D Shape Generation Using Parsed Image Data
4. Structural Shell Deflection Maps Generated with Linear Regression Models.