Rapid evaluation of cost and whole life carbon of buildings using artificial intelligence

Al-Habaibeh, A ORCID: https://orcid.org/0000-0002-9867-6011, Manu, E ORCID: https://orcid.org/0000-0002-9002-3681, Bubaker, S ORCID: https://orcid.org/0000-0003-4534-9196, Selvam, J, Lin, T-H and Clement, T, 2025. Rapid evaluation of cost and whole life carbon of buildings using artificial intelligence. In: Proceedings of 2024 IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT 2024). Institute of Electrical and Electronics Engineers (IEEE). ISBN 9798350367317

Preview

Text 2430735_Al-Habaibeh.pdf - Post-print Download (757kB) | Preview

Abstract

The global drive to reduce carbon footprint and optimise costs in the construction industry has led to integrating Whole Life-Cycle Carbon (WLC) and cost assessments into industry practices. One of the key points is reducing embodied carbon in materials and accounting for emissions and costs during transportation, installation, and the operation of built assets. This study presents a novel approach of using Artificial Intelligence (AI) to rapidly evaluate both Whole Life-Cyle Carbon (WLC) and costs, enabling an enhanced and rapid decision-making during the early design stages. By leveraging data from Building Cost Information Service (BCIS) database and carbon databases from past projects of a top construction firm in UK, AI is found to provide real-time guidance for optimising material choices and configurations, hence balancing sustainability with budget considerations. The proposed integration of using AI techniques such as neural networks into existing carbon and cost estimation tools, such as CarboniCa Software, aims to streamline the current data entry process and provide a rapid data analysis. This not only saves time but also reduces cost of implementation and enhances productivity. This paper outlines the use of AI techniques to predict embodied carbon and cost of construction projects from key characteristic features of buildings. The results show that AI can be used to predict the expected outputs with high accuracy, consequently providing productivity improvements and reducing time and cost of implementation. The suggested approach highlights the future role of AI in driving more sustainable, productive and cost-effective construction practices.

Item Type:	Chapter in book
Description:	Paper presented at IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT 2024), Sharjah, United Arab Emirates, 16-19 December 2024.
Creators:	Al-Habaibeh, A., Manu, E., Bubaker, S., Selvam, J., Lin, T.-H. and Clement, T.
Publisher:	Institute of Electrical and Electronics Engineers (IEEE)
Date:	8 April 2025
ISBN:	9798350367317
Identifiers:	Number Type 10.1109/BDCAT63179.2024.00037 DOI 2430735 Other
Rights:	© 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Divisions:	Schools > School of Architecture, Design and the Built Environment
Record created by:	Laura Borcherds
Date Added:	12 Aug 2025 08:05
Last Modified:	12 Aug 2025 08:07
URI:	https://irep.ntu.ac.uk/id/eprint/54155

Actions (login required)

Edit View

Statistics

Views

Downloads