This project aims to revolutionise the design of low-carbon concrete by leveraging deep learning and swarm optimisation algorithms to determine the optimal mix proportions incorporating supplementary cementitious materials (SCMs). Focusing on reducing the environmental impact of concrete production, the initiative combines comprehensive data collection, cutting-edge predictive models, and advanced optimisation techniques to identify sustainable concrete formulations. By integrating the predictive power of deep learning with the efficiency of swarm intelligence-based multi-objective optimisation algorithms, the project seeks to balance the multiple objectives of achieving desired mechanical properties, workability and durability performance, while minimising carbon footprint. The outcome will be a scalable framework that enables the construction industry to produce high-performance, environmentally friendly concrete, significantly contributing to sustainable construction practices worldwide.


Civil and Environmental Engineering

Research Areas

Construction materials | Sustainability | Artificial intelligence | Machine learning | Optimisation

This project is part of an ARC Linkage Project in collaboration with our industry partner, Boral, who has supplied a comprehensive dataset on the mechanical properties and durability performance of low-carbon concrete with SCMs. The applicant is responsible for data cleaning and the development of deep learning and optimisation methods for the optimal mix proportion design. This will subsequently be evaluated through experimental verification.

A technical report or a conference/journal paper will be produced as the outcome of this project.

Research Associate Yang Yu
Research Associate
Professor of Structural Engineering Stephen Foster
Professor of Structural Engineering
  • Huang, Y., Zhang, J., Tze Ann, F., Ma, G. (2020) Intelligent mixture design of steel fibre reinforced concrete using a support vector regression and firefly algorithm based multi-objective optimization model. Construction and Building Materials, 260, 120457.
  • Zhang, J., Huang, Y., Ma, G., Yuan, Y., Nener, B. (2021) Automating the mixture design of lightweight foamed concrete using multi-objective firefly algorithm and support vector regression. Cement and Concrete Composites, 121, 104103.
  • Hafez, H., Teirelbar, A., Tošić, N., Ikumi, T., de la Fuente, A. (2023) Data-driven optimization tool for the functional, economic, and environmental properties of blended cement concrete using supplementary cementitious materials. Journal of Building Engineering, 67, 106022.