Machine learning for efficient CO2 sequestration in cementitious materials: a data-driven method

Abstract Extensive experimental work has proved that CO2 sequestration by cementitious materials offers a promising venue for addressing the rising carbon emissions problem. However, relying merely on experiments on specific materials or some simple empirical methods makes it difficult to provide a...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanjie SUN, Chen ZHANG, Yuan-Hao WEI, Haoliang JIN, Peiliang SHEN, Chi Sun POON, He YAN, Xiao-Yong WEI
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:npj Materials Sustainability
Online Access:https://doi.org/10.1038/s44296-025-00053-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850265571899211776
author Yanjie SUN
Chen ZHANG
Yuan-Hao WEI
Haoliang JIN
Peiliang SHEN
Chi Sun POON
He YAN
Xiao-Yong WEI
author_facet Yanjie SUN
Chen ZHANG
Yuan-Hao WEI
Haoliang JIN
Peiliang SHEN
Chi Sun POON
He YAN
Xiao-Yong WEI
author_sort Yanjie SUN
collection DOAJ
description Abstract Extensive experimental work has proved that CO2 sequestration by cementitious materials offers a promising venue for addressing the rising carbon emissions problem. However, relying merely on experiments on specific materials or some simple empirical methods makes it difficult to provide a comprehensive understanding. To address these challenges, this paper applies three advanced machine-learning techniques (Decision Tree, Random Forest, and eXtreme Gradient Boosting (XGBoost)), with existing datasets coupling with data collected from the literature. The results show that the XGBoost model significantly outperforms traditional linear regression approaches. In addition, aiding in the SHapley Additive exPlanations(SHAP), apart from the widely recognized factors, cement type was also investigated and shown its crucial role in affecting carbonation depth. CEM II/B-LL and CEM II/B-M are two types having high carbonation potential. The results enable the identification of key factors influencing CO2 sequestration through cement and provide insights into optimizing experimental design.
format Article
id doaj-art-ddc0aa98a4484f69a506b095a8ff6a44
institution OA Journals
issn 2948-1775
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series npj Materials Sustainability
spelling doaj-art-ddc0aa98a4484f69a506b095a8ff6a442025-08-20T01:54:22ZengNature Portfolionpj Materials Sustainability2948-17752025-04-01311910.1038/s44296-025-00053-zMachine learning for efficient CO2 sequestration in cementitious materials: a data-driven methodYanjie SUN0Chen ZHANG1Yuan-Hao WEI2Haoliang JIN3Peiliang SHEN4Chi Sun POON5He YAN6Xiao-Yong WEI7Department of Computing, The Hong Kong Polytechnic UniversityDepartment of Computing, The Hong Kong Polytechnic UniversityDepartment of Computing, The Hong Kong Polytechnic UniversityDepartment of Materials Science and Engineering, University of SheffieldDepartment of Civil and Environmental Engineering, The Hong Kong Polytechnic UniversityDepartment of Civil and Environmental Engineering, The Hong Kong Polytechnic UniversityDepartment of Chemistry, Hong Kong University of Science and TechnologyDepartment of Computing, The Hong Kong Polytechnic UniversityAbstract Extensive experimental work has proved that CO2 sequestration by cementitious materials offers a promising venue for addressing the rising carbon emissions problem. However, relying merely on experiments on specific materials or some simple empirical methods makes it difficult to provide a comprehensive understanding. To address these challenges, this paper applies three advanced machine-learning techniques (Decision Tree, Random Forest, and eXtreme Gradient Boosting (XGBoost)), with existing datasets coupling with data collected from the literature. The results show that the XGBoost model significantly outperforms traditional linear regression approaches. In addition, aiding in the SHapley Additive exPlanations(SHAP), apart from the widely recognized factors, cement type was also investigated and shown its crucial role in affecting carbonation depth. CEM II/B-LL and CEM II/B-M are two types having high carbonation potential. The results enable the identification of key factors influencing CO2 sequestration through cement and provide insights into optimizing experimental design.https://doi.org/10.1038/s44296-025-00053-z
spellingShingle Yanjie SUN
Chen ZHANG
Yuan-Hao WEI
Haoliang JIN
Peiliang SHEN
Chi Sun POON
He YAN
Xiao-Yong WEI
Machine learning for efficient CO2 sequestration in cementitious materials: a data-driven method
npj Materials Sustainability
title Machine learning for efficient CO2 sequestration in cementitious materials: a data-driven method
title_full Machine learning for efficient CO2 sequestration in cementitious materials: a data-driven method
title_fullStr Machine learning for efficient CO2 sequestration in cementitious materials: a data-driven method
title_full_unstemmed Machine learning for efficient CO2 sequestration in cementitious materials: a data-driven method
title_short Machine learning for efficient CO2 sequestration in cementitious materials: a data-driven method
title_sort machine learning for efficient co2 sequestration in cementitious materials a data driven method
url https://doi.org/10.1038/s44296-025-00053-z
work_keys_str_mv AT yanjiesun machinelearningforefficientco2sequestrationincementitiousmaterialsadatadrivenmethod
AT chenzhang machinelearningforefficientco2sequestrationincementitiousmaterialsadatadrivenmethod
AT yuanhaowei machinelearningforefficientco2sequestrationincementitiousmaterialsadatadrivenmethod
AT haoliangjin machinelearningforefficientco2sequestrationincementitiousmaterialsadatadrivenmethod
AT peiliangshen machinelearningforefficientco2sequestrationincementitiousmaterialsadatadrivenmethod
AT chisunpoon machinelearningforefficientco2sequestrationincementitiousmaterialsadatadrivenmethod
AT heyan machinelearningforefficientco2sequestrationincementitiousmaterialsadatadrivenmethod
AT xiaoyongwei machinelearningforefficientco2sequestrationincementitiousmaterialsadatadrivenmethod