A consortium has won £800,000 to develop an embodied carbon analytics AI system that could cut the time it takes to analyse infrastructure carbon impacts from weeks to hours.
Winvic, the University of the West of England (UWE Bristol), Edgetrix Ltd and Costain will employ historic embodied carbon data from previous construction projects and accurate ‘carbon factors’ to develop machine learning models.
The project entitled ‘AI System for Predicting Embodied Carbon in Construction’ (ASPEC) won the Innovate UK cash to help predict the carbon output on building and infrastructure projects 'based on BIM designs, materials carbon data and lessons learnt on past projects'.
The project team aims to deliver the project as early as autumn 2022.
If successful the system could reduce the time it takes to calculate embodied carbon, bringing the process down from days and weeks to just a few hours.
The proposed ASPEC has three components:
- AI-based Embodied Carbon Calculator (ECC) - This system will predict the embodied carbon cost of any project from a scheme’s BIM model using historic embodied carbon data from previous construction projects and accurate ‘carbon factors’ to develop machine learning models.
- Embodied Carbon Analytics and Simulation Platform (ECAS) - This tool will use advanced big data analytics to identify 'what if' alternative design specifications that would reduce the embodied carbon of a project. A user of ECAS will be able to simply change the selection of building material and obtain an instantaneous embodied carbon figure.
- BIM-based Design Support Tool for Embodied Carbon Analytics (B-DST) - This solution will also support design teams during the design stages of construction projects. It will integrate with existing BIM development software via an Application Programming Interface (API).
Tim Reeve, Winvic’s technical director and project lead, commented: 'We believe that utilising the most up-to-date AI and advanced big data analytics techniques in a way that has never been done before will be transformational for Winvic’s green agenda and pave the way for significant changes across the whole industry.
'Having the ability to optimise schemes and see embodied carbon costs as real-time design and material changes are applied will naturally lead to quantifiable reductions in greenhouse gas emissions, and having technology that automatically estimates the embodied carbon cost of any digitally designed project will make the delivery of many project tasks much faster.'
Dr Lukman Akanbi, associate professor at UWE Bristol, said: 'Through the ASPEC project, we as academics hope to contribute our technical know-how and expertise in Big Data Analytics and Artificial Intelligence to help move the UK one step closer towards the realisation of her clean growth strategy and 2050 net-zero carbon target.
'In addition, UWE Bristol is a university that’s environmentally aware and is aiming to be carbon neutral by 2030, so it’s great that we are taking a lead in a project that is looking to help achieve these aims.'