A hybrid prediction and multi-objective optimization framework for limestone calcined clay cement concrete mixture design
Abstract Limestone calcined clay cement (LC3) is a promising low-carbon construction material in terms of its comparable mechanical performance to ordinary Portland cement (OPC) but a much less embodied carbon footprint. Previous literature have demonstrated that the large-scale implementation of LC...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-05288-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849335112721760256 |
|---|---|
| author | Xi Chen Weiyi Chen Zongao Li Pu Zhang |
| author_facet | Xi Chen Weiyi Chen Zongao Li Pu Zhang |
| author_sort | Xi Chen |
| collection | DOAJ |
| description | Abstract Limestone calcined clay cement (LC3) is a promising low-carbon construction material in terms of its comparable mechanical performance to ordinary Portland cement (OPC) but a much less embodied carbon footprint. Previous literature have demonstrated that the large-scale implementation of LC3 can reduce embodied CO2 emissions associated with OPC production by at least 30%. This study proposes a hybrid framework combining machine learning (ML) and multi-objective optimization (MOO) to design cost-effective and eco-friendly LC3 mixtures. A dataset of 387 LC3 specimens was constructed to develop ML models for predicting compressive strength. Multivariate Imputation by Chained Equations-Extreme Gradient Boosting (MICE-XGBoost) model achieved the highest accuracy of R2 = 0.928 (± 0.009). SHAP analysis identified key factors influencing strength, including water-to-cement/binder ratio, and kaolinite content. The local range of each feature showing more significant contributions was also identified. Non-dominated Sorting Genetic Algorithm-II was employed for MOO, generating Pareto fronts to minimize cost and embodied carbon while meeting strength requirements. A minimum balanced reduction in cost by 13.06% and embodied carbon by 14.83% was obtained. Inflection points on Pareto fronts were identified to guide decision-making for low-medium grade mixtures. A table of optimal mix designs is provided, offering practical solutions for selecting sustainable LC3 formulations. |
| format | Article |
| id | doaj-art-e8f8cdc5e7f148bf9ce7ff03d0b04fbc |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-e8f8cdc5e7f148bf9ce7ff03d0b04fbc2025-08-20T03:45:23ZengNature PortfolioScientific Reports2045-23222025-07-0115112510.1038/s41598-025-05288-3A hybrid prediction and multi-objective optimization framework for limestone calcined clay cement concrete mixture designXi Chen0Weiyi Chen1Zongao Li2Pu Zhang3School of Civil and Environmental Engineering, Nanyang Technological UniversitySchool of Civil Engineering, Zhengzhou UniversitySchool of Civil Engineering, Zhengzhou UniversitySchool of Civil Engineering, Zhengzhou UniversityAbstract Limestone calcined clay cement (LC3) is a promising low-carbon construction material in terms of its comparable mechanical performance to ordinary Portland cement (OPC) but a much less embodied carbon footprint. Previous literature have demonstrated that the large-scale implementation of LC3 can reduce embodied CO2 emissions associated with OPC production by at least 30%. This study proposes a hybrid framework combining machine learning (ML) and multi-objective optimization (MOO) to design cost-effective and eco-friendly LC3 mixtures. A dataset of 387 LC3 specimens was constructed to develop ML models for predicting compressive strength. Multivariate Imputation by Chained Equations-Extreme Gradient Boosting (MICE-XGBoost) model achieved the highest accuracy of R2 = 0.928 (± 0.009). SHAP analysis identified key factors influencing strength, including water-to-cement/binder ratio, and kaolinite content. The local range of each feature showing more significant contributions was also identified. Non-dominated Sorting Genetic Algorithm-II was employed for MOO, generating Pareto fronts to minimize cost and embodied carbon while meeting strength requirements. A minimum balanced reduction in cost by 13.06% and embodied carbon by 14.83% was obtained. Inflection points on Pareto fronts were identified to guide decision-making for low-medium grade mixtures. A table of optimal mix designs is provided, offering practical solutions for selecting sustainable LC3 formulations.https://doi.org/10.1038/s41598-025-05288-3Limestone calcined clayMachine learningMulti-objective optimizationMix design |
| spellingShingle | Xi Chen Weiyi Chen Zongao Li Pu Zhang A hybrid prediction and multi-objective optimization framework for limestone calcined clay cement concrete mixture design Scientific Reports Limestone calcined clay Machine learning Multi-objective optimization Mix design |
| title | A hybrid prediction and multi-objective optimization framework for limestone calcined clay cement concrete mixture design |
| title_full | A hybrid prediction and multi-objective optimization framework for limestone calcined clay cement concrete mixture design |
| title_fullStr | A hybrid prediction and multi-objective optimization framework for limestone calcined clay cement concrete mixture design |
| title_full_unstemmed | A hybrid prediction and multi-objective optimization framework for limestone calcined clay cement concrete mixture design |
| title_short | A hybrid prediction and multi-objective optimization framework for limestone calcined clay cement concrete mixture design |
| title_sort | hybrid prediction and multi objective optimization framework for limestone calcined clay cement concrete mixture design |
| topic | Limestone calcined clay Machine learning Multi-objective optimization Mix design |
| url | https://doi.org/10.1038/s41598-025-05288-3 |
| work_keys_str_mv | AT xichen ahybridpredictionandmultiobjectiveoptimizationframeworkforlimestonecalcinedclaycementconcretemixturedesign AT weiyichen ahybridpredictionandmultiobjectiveoptimizationframeworkforlimestonecalcinedclaycementconcretemixturedesign AT zongaoli ahybridpredictionandmultiobjectiveoptimizationframeworkforlimestonecalcinedclaycementconcretemixturedesign AT puzhang ahybridpredictionandmultiobjectiveoptimizationframeworkforlimestonecalcinedclaycementconcretemixturedesign AT xichen hybridpredictionandmultiobjectiveoptimizationframeworkforlimestonecalcinedclaycementconcretemixturedesign AT weiyichen hybridpredictionandmultiobjectiveoptimizationframeworkforlimestonecalcinedclaycementconcretemixturedesign AT zongaoli hybridpredictionandmultiobjectiveoptimizationframeworkforlimestonecalcinedclaycementconcretemixturedesign AT puzhang hybridpredictionandmultiobjectiveoptimizationframeworkforlimestonecalcinedclaycementconcretemixturedesign |