Interpretable machine learning models for evaluating strength of ternary geopolymers

Ternary geopolymers incorporating multiple solid wastes such as steel slag (SS), fly ash (FA), and granulated blast furnace slag (GBFS) are considered environmentally friendly and exhibit enhanced performance. However, the mechanisms governing strength development and the design of optimal mixtures...

Full description

Saved in:
Bibliographic Details
Main Authors: Junfei Zhang, Huisheng Cheng, Ninghui Sun, Zehui Huo, Junlin Chen
Format: Article
Language:English
Published: KeAi Communications Co. Ltd. 2025-12-01
Series:Artificial Intelligence in Geosciences
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666544125000243
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849710056451342336
author Junfei Zhang
Huisheng Cheng
Ninghui Sun
Zehui Huo
Junlin Chen
author_facet Junfei Zhang
Huisheng Cheng
Ninghui Sun
Zehui Huo
Junlin Chen
author_sort Junfei Zhang
collection DOAJ
description Ternary geopolymers incorporating multiple solid wastes such as steel slag (SS), fly ash (FA), and granulated blast furnace slag (GBFS) are considered environmentally friendly and exhibit enhanced performance. However, the mechanisms governing strength development and the design of optimal mixtures are not fully understood due to the complexity of their components. This study presents the development of four machine learning models—Artificial Neural Network (ANN), Support Vector Regression (SVR), Extremely Randomized Tree (ERT), and Gradient Boosting Regression (GBR)—for predicting the unconfined compressive strength (UCS) of ternary geopolymers. The models were trained using a dataset comprising 120 mixtures derived from laboratory tests. Shapley Additive Explanations analysis was employed to interpret the machine learning models and elucidate the influence of different components on the properties of ternary geopolymers. The results indicate that ANN exhibits the highest predictive accuracy for UCS (R = 0.949). Furthermore, the UCS of ternary geopolymers is most sensitive to the content of GBFS. This study provides valuable insights for optimizing the mix proportions in ternary blended geopolymer mixtures.
format Article
id doaj-art-5cc60826e577446aa36ef5732f2680bd
institution DOAJ
issn 2666-5441
language English
publishDate 2025-12-01
publisher KeAi Communications Co. Ltd.
record_format Article
series Artificial Intelligence in Geosciences
spelling doaj-art-5cc60826e577446aa36ef5732f2680bd2025-08-20T03:15:03ZengKeAi Communications Co. Ltd.Artificial Intelligence in Geosciences2666-54412025-12-016210012810.1016/j.aiig.2025.100128Interpretable machine learning models for evaluating strength of ternary geopolymersJunfei Zhang0Huisheng Cheng1Ninghui Sun2Zehui Huo3Junlin Chen4Corresponding author.; School of Civil and Transportation Engineering, Hebei University of Technology, Tianjin, 300401, China; School of Minerals and Energy Resources Engineering, University of New South Wales, Sydney, NSW 2052, Australia; School of Chemical and Environmental Engineering, China University of Mining and Technology (Beijing), Beijing, 100083, China; CCCC Tianjin Port Engineering Design & Consulting Co., Ltd., Tianjin, 300461, ChinaSchool of Civil and Transportation Engineering, Hebei University of Technology, Tianjin, 300401, China; School of Minerals and Energy Resources Engineering, University of New South Wales, Sydney, NSW 2052, Australia; School of Chemical and Environmental Engineering, China University of Mining and Technology (Beijing), Beijing, 100083, China; CCCC Tianjin Port Engineering Design & Consulting Co., Ltd., Tianjin, 300461, ChinaCorresponding author.; School of Civil and Transportation Engineering, Hebei University of Technology, Tianjin, 300401, China; School of Minerals and Energy Resources Engineering, University of New South Wales, Sydney, NSW 2052, Australia; School of Chemical and Environmental Engineering, China University of Mining and Technology (Beijing), Beijing, 100083, China; CCCC Tianjin Port Engineering Design & Consulting Co., Ltd., Tianjin, 300461, ChinaSchool of Civil and Transportation Engineering, Hebei University of Technology, Tianjin, 300401, China; School of Minerals and Energy Resources Engineering, University of New South Wales, Sydney, NSW 2052, Australia; School of Chemical and Environmental Engineering, China University of Mining and Technology (Beijing), Beijing, 100083, China; CCCC Tianjin Port Engineering Design & Consulting Co., Ltd., Tianjin, 300461, ChinaSchool of Civil and Transportation Engineering, Hebei University of Technology, Tianjin, 300401, China; School of Minerals and Energy Resources Engineering, University of New South Wales, Sydney, NSW 2052, Australia; School of Chemical and Environmental Engineering, China University of Mining and Technology (Beijing), Beijing, 100083, China; CCCC Tianjin Port Engineering Design & Consulting Co., Ltd., Tianjin, 300461, ChinaTernary geopolymers incorporating multiple solid wastes such as steel slag (SS), fly ash (FA), and granulated blast furnace slag (GBFS) are considered environmentally friendly and exhibit enhanced performance. However, the mechanisms governing strength development and the design of optimal mixtures are not fully understood due to the complexity of their components. This study presents the development of four machine learning models—Artificial Neural Network (ANN), Support Vector Regression (SVR), Extremely Randomized Tree (ERT), and Gradient Boosting Regression (GBR)—for predicting the unconfined compressive strength (UCS) of ternary geopolymers. The models were trained using a dataset comprising 120 mixtures derived from laboratory tests. Shapley Additive Explanations analysis was employed to interpret the machine learning models and elucidate the influence of different components on the properties of ternary geopolymers. The results indicate that ANN exhibits the highest predictive accuracy for UCS (R = 0.949). Furthermore, the UCS of ternary geopolymers is most sensitive to the content of GBFS. This study provides valuable insights for optimizing the mix proportions in ternary blended geopolymer mixtures.http://www.sciencedirect.com/science/article/pii/S2666544125000243GeopolymerSolid wasteMix proportionMachine learningUnconfined compressive strength
spellingShingle Junfei Zhang
Huisheng Cheng
Ninghui Sun
Zehui Huo
Junlin Chen
Interpretable machine learning models for evaluating strength of ternary geopolymers
Artificial Intelligence in Geosciences
Geopolymer
Solid waste
Mix proportion
Machine learning
Unconfined compressive strength
title Interpretable machine learning models for evaluating strength of ternary geopolymers
title_full Interpretable machine learning models for evaluating strength of ternary geopolymers
title_fullStr Interpretable machine learning models for evaluating strength of ternary geopolymers
title_full_unstemmed Interpretable machine learning models for evaluating strength of ternary geopolymers
title_short Interpretable machine learning models for evaluating strength of ternary geopolymers
title_sort interpretable machine learning models for evaluating strength of ternary geopolymers
topic Geopolymer
Solid waste
Mix proportion
Machine learning
Unconfined compressive strength
url http://www.sciencedirect.com/science/article/pii/S2666544125000243
work_keys_str_mv AT junfeizhang interpretablemachinelearningmodelsforevaluatingstrengthofternarygeopolymers
AT huishengcheng interpretablemachinelearningmodelsforevaluatingstrengthofternarygeopolymers
AT ninghuisun interpretablemachinelearningmodelsforevaluatingstrengthofternarygeopolymers
AT zehuihuo interpretablemachinelearningmodelsforevaluatingstrengthofternarygeopolymers
AT junlinchen interpretablemachinelearningmodelsforevaluatingstrengthofternarygeopolymers