Compressive strength prediction of fly ash/slag-based geopolymer concrete using EBA-optimised chemistry-informed interpretable deep learning model

Geopolymer concrete (GPC) is a sustainable alternative to conventional Portland cement concrete, utilising industrial by-products like fly ash (FA) and ground-granulated blast-furnace slag (GGBS). However, optimising GPC's compressive strength (CS) often requires costly and time-consuming exper...

Full description

Saved in:
Bibliographic Details
Main Authors: Yang Yu, Iman Munadhil Abbas Al-Damad, Stephen Foster, Ali Akbar Nezhad, Ailar Hajimohammadi
Format: Article
Language:English
Published: Elsevier 2025-10-01
Series:Developments in the Built Environment
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S266616592500136X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849222540402098176
author Yang Yu
Iman Munadhil Abbas Al-Damad
Stephen Foster
Ali Akbar Nezhad
Ailar Hajimohammadi
author_facet Yang Yu
Iman Munadhil Abbas Al-Damad
Stephen Foster
Ali Akbar Nezhad
Ailar Hajimohammadi
author_sort Yang Yu
collection DOAJ
description Geopolymer concrete (GPC) is a sustainable alternative to conventional Portland cement concrete, utilising industrial by-products like fly ash (FA) and ground-granulated blast-furnace slag (GGBS). However, optimising GPC's compressive strength (CS) often requires costly and time-consuming experimental trials. This study develops a deep learning (DL) model based on convolutional neural networks (CNN) to predict the CS of FA/GGBS-based GPC. The model integrates key mix parameters such as material proportions, curing conditions, and the chemical composition of FA/GGBS binders, making it chemistry-informed. The CNN architecture includes two convolution layers, global max-pooling, and two fully connected layers, with 11 input variables and a single output for CS prediction. To optimise model accuracy, the enhanced bat algorithm (EBA) is designed for metaparameter tuning. The model is trained and tested on a comprehensive dataset comprising experimental data extracted from published literature. The results demonstrate that the EBA-optimised CNN outperforms traditional learning models, including support vector machine (SVM), extreme gradient boosting (XGBoost), and artificial neural networks (ANN), with higher performance in terms of R2, MAE, and RMSE. The model achieved R2 values of 0.997 for training and 0.978 for testing. Additionally, the Shapley additive explanations (SHAP) method was used to interpret the model, identifying the Na2O to binder ratio and curing age as the most influential factors on CS. This study highlights the potential of DL techniques, particularly chemistry-informed CNN with metaparameter optimisation, for accurately predicting the strength of GPC, providing a cost-effective solution for mix design and performance evaluation.
format Article
id doaj-art-bb59b69dc2804e2297ee7a02e9096c95
institution Kabale University
issn 2666-1659
language English
publishDate 2025-10-01
publisher Elsevier
record_format Article
series Developments in the Built Environment
spelling doaj-art-bb59b69dc2804e2297ee7a02e9096c952025-08-26T04:14:33ZengElsevierDevelopments in the Built Environment2666-16592025-10-012310073610.1016/j.dibe.2025.100736Compressive strength prediction of fly ash/slag-based geopolymer concrete using EBA-optimised chemistry-informed interpretable deep learning modelYang Yu0Iman Munadhil Abbas Al-Damad1Stephen Foster2Ali Akbar Nezhad3Ailar Hajimohammadi4Centre for Infrastructure Engineering and Safety, School of Civil and Environmental Engineering, The University of New South Wales, Sydney, NSW, 2052, Australia; Corresponding author.Centre for Infrastructure Engineering and Safety, School of Civil and Environmental Engineering, The University of New South Wales, Sydney, NSW, 2052, Australia; Department of Civil Engineering, College of Engineering, University of Baghdad, IraqCentre for Infrastructure Engineering and Safety, School of Civil and Environmental Engineering, The University of New South Wales, Sydney, NSW, 2052, Australia; Corresponding author.Centre for Infrastructure Engineering and Safety, School of Civil and Environmental Engineering, The University of New South Wales, Sydney, NSW, 2052, Australia; Boral Ltd, North Ryde, NSW, 2113, AustraliaCentre for Infrastructure Engineering and Safety, School of Civil and Environmental Engineering, The University of New South Wales, Sydney, NSW, 2052, Australia; Corresponding author.Geopolymer concrete (GPC) is a sustainable alternative to conventional Portland cement concrete, utilising industrial by-products like fly ash (FA) and ground-granulated blast-furnace slag (GGBS). However, optimising GPC's compressive strength (CS) often requires costly and time-consuming experimental trials. This study develops a deep learning (DL) model based on convolutional neural networks (CNN) to predict the CS of FA/GGBS-based GPC. The model integrates key mix parameters such as material proportions, curing conditions, and the chemical composition of FA/GGBS binders, making it chemistry-informed. The CNN architecture includes two convolution layers, global max-pooling, and two fully connected layers, with 11 input variables and a single output for CS prediction. To optimise model accuracy, the enhanced bat algorithm (EBA) is designed for metaparameter tuning. The model is trained and tested on a comprehensive dataset comprising experimental data extracted from published literature. The results demonstrate that the EBA-optimised CNN outperforms traditional learning models, including support vector machine (SVM), extreme gradient boosting (XGBoost), and artificial neural networks (ANN), with higher performance in terms of R2, MAE, and RMSE. The model achieved R2 values of 0.997 for training and 0.978 for testing. Additionally, the Shapley additive explanations (SHAP) method was used to interpret the model, identifying the Na2O to binder ratio and curing age as the most influential factors on CS. This study highlights the potential of DL techniques, particularly chemistry-informed CNN with metaparameter optimisation, for accurately predicting the strength of GPC, providing a cost-effective solution for mix design and performance evaluation.http://www.sciencedirect.com/science/article/pii/S266616592500136XChemistry-informedCompressive strengthConvolutional neural networkEnhanced bat algorithmGeopolymer concrete
spellingShingle Yang Yu
Iman Munadhil Abbas Al-Damad
Stephen Foster
Ali Akbar Nezhad
Ailar Hajimohammadi
Compressive strength prediction of fly ash/slag-based geopolymer concrete using EBA-optimised chemistry-informed interpretable deep learning model
Developments in the Built Environment
Chemistry-informed
Compressive strength
Convolutional neural network
Enhanced bat algorithm
Geopolymer concrete
title Compressive strength prediction of fly ash/slag-based geopolymer concrete using EBA-optimised chemistry-informed interpretable deep learning model
title_full Compressive strength prediction of fly ash/slag-based geopolymer concrete using EBA-optimised chemistry-informed interpretable deep learning model
title_fullStr Compressive strength prediction of fly ash/slag-based geopolymer concrete using EBA-optimised chemistry-informed interpretable deep learning model
title_full_unstemmed Compressive strength prediction of fly ash/slag-based geopolymer concrete using EBA-optimised chemistry-informed interpretable deep learning model
title_short Compressive strength prediction of fly ash/slag-based geopolymer concrete using EBA-optimised chemistry-informed interpretable deep learning model
title_sort compressive strength prediction of fly ash slag based geopolymer concrete using eba optimised chemistry informed interpretable deep learning model
topic Chemistry-informed
Compressive strength
Convolutional neural network
Enhanced bat algorithm
Geopolymer concrete
url http://www.sciencedirect.com/science/article/pii/S266616592500136X
work_keys_str_mv AT yangyu compressivestrengthpredictionofflyashslagbasedgeopolymerconcreteusingebaoptimisedchemistryinformedinterpretabledeeplearningmodel
AT imanmunadhilabbasaldamad compressivestrengthpredictionofflyashslagbasedgeopolymerconcreteusingebaoptimisedchemistryinformedinterpretabledeeplearningmodel
AT stephenfoster compressivestrengthpredictionofflyashslagbasedgeopolymerconcreteusingebaoptimisedchemistryinformedinterpretabledeeplearningmodel
AT aliakbarnezhad compressivestrengthpredictionofflyashslagbasedgeopolymerconcreteusingebaoptimisedchemistryinformedinterpretabledeeplearningmodel
AT ailarhajimohammadi compressivestrengthpredictionofflyashslagbasedgeopolymerconcreteusingebaoptimisedchemistryinformedinterpretabledeeplearningmodel