A comparative performance analysis of machine learning models for compressive strength prediction in fly ash-based geopolymers concrete using reference data
Fly ash-based geopolymer (FAGP) is a promising supplementary cementitious material in the concrete industry, which can improve the sustainability and performance of concrete. This study will have made attempt to address the complexities involves in the concrete mix designs process with the aim of ac...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-07-01
|
| Series: | Case Studies in Construction Materials |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2214509525000063 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823864393185624064 |
|---|---|
| author | Muhammad Kashif Anwar Muhammad Ahmed Qurashi Xingyi Zhu Syyed Adnan Raheel Shah Muhammad Usman Siddiq |
| author_facet | Muhammad Kashif Anwar Muhammad Ahmed Qurashi Xingyi Zhu Syyed Adnan Raheel Shah Muhammad Usman Siddiq |
| author_sort | Muhammad Kashif Anwar |
| collection | DOAJ |
| description | Fly ash-based geopolymer (FAGP) is a promising supplementary cementitious material in the concrete industry, which can improve the sustainability and performance of concrete. This study will have made attempt to address the complexities involves in the concrete mix designs process with the aim of achieving the desired 28-day compressive strength for FAGP. This study conducts a comparative performance analysis of the machine learning models for compressive strength prediction of FAGP using comprehensive dataset of 563 samples from 55 literature studies. Seven models such as multiple linear regression (MLR), artificial neural networks (ANNs), support vector machines (SVMs), K-nearest neighbor (KNNs), decision trees (DT), and ensemble methods combining DT with boosting and bootstrapping were employed. Model performance was evaluated using sensitivity analysis and statistical indices such as MSE, MAD, RMSE, MAPE, and SI. The findings indicate that ensemble methods and ANNs deliver superior accuracy, with R² values ranging from 0.88 to 0.92 and minimal errors. The ranking of predictive models is: ANNs > Boosting > Bootstrap SVM > DT > KNN > MLR. The prediction and profiler plots are also confirm the validity of the ANNs model performance. In addition, SHAP (SHapley Additive exPlanations) analysis demonstrated that compressive strength is significantly influenced by fly ash content and curing temperature. This study provides valuable insights for optimizing concrete mix designs, enhancing the performance and sustainability of FAGP, and contributes to the broader understanding of cementitious materials, fulfilling both industrial and environmental goals. |
| format | Article |
| id | doaj-art-45992bf98244415f8ec88aff6acd94bf |
| institution | Kabale University |
| issn | 2214-5095 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Case Studies in Construction Materials |
| spelling | doaj-art-45992bf98244415f8ec88aff6acd94bf2025-02-09T05:00:27ZengElsevierCase Studies in Construction Materials2214-50952025-07-0122e04207A comparative performance analysis of machine learning models for compressive strength prediction in fly ash-based geopolymers concrete using reference dataMuhammad Kashif Anwar0Muhammad Ahmed Qurashi1Xingyi Zhu2Syyed Adnan Raheel Shah3Muhammad Usman Siddiq4Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation Engineering, Tongji University, Shanghai 201804, ChinaDepartment of Bridge Engineering, College of Civil Engineering, Tongji University, Siping Road 1239, Shanghai 200092, ChinaKey Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation Engineering, Tongji University, Shanghai 201804, China; Corresponding author.Department of Civil Engineering, NFC-Institute of Engineering & Technology, Multan 66000, PakistanCivil and Building Services Engineering Division, School of Built Environment and Architecture, London South Bank University, 103 Borough Road, London SE1 0AA, UKFly ash-based geopolymer (FAGP) is a promising supplementary cementitious material in the concrete industry, which can improve the sustainability and performance of concrete. This study will have made attempt to address the complexities involves in the concrete mix designs process with the aim of achieving the desired 28-day compressive strength for FAGP. This study conducts a comparative performance analysis of the machine learning models for compressive strength prediction of FAGP using comprehensive dataset of 563 samples from 55 literature studies. Seven models such as multiple linear regression (MLR), artificial neural networks (ANNs), support vector machines (SVMs), K-nearest neighbor (KNNs), decision trees (DT), and ensemble methods combining DT with boosting and bootstrapping were employed. Model performance was evaluated using sensitivity analysis and statistical indices such as MSE, MAD, RMSE, MAPE, and SI. The findings indicate that ensemble methods and ANNs deliver superior accuracy, with R² values ranging from 0.88 to 0.92 and minimal errors. The ranking of predictive models is: ANNs > Boosting > Bootstrap SVM > DT > KNN > MLR. The prediction and profiler plots are also confirm the validity of the ANNs model performance. In addition, SHAP (SHapley Additive exPlanations) analysis demonstrated that compressive strength is significantly influenced by fly ash content and curing temperature. This study provides valuable insights for optimizing concrete mix designs, enhancing the performance and sustainability of FAGP, and contributes to the broader understanding of cementitious materials, fulfilling both industrial and environmental goals.http://www.sciencedirect.com/science/article/pii/S2214509525000063Fly ash-based geopolymer (FAGP)Compressive strengthMachine learning modelsConcrete mix designsSustainability |
| spellingShingle | Muhammad Kashif Anwar Muhammad Ahmed Qurashi Xingyi Zhu Syyed Adnan Raheel Shah Muhammad Usman Siddiq A comparative performance analysis of machine learning models for compressive strength prediction in fly ash-based geopolymers concrete using reference data Case Studies in Construction Materials Fly ash-based geopolymer (FAGP) Compressive strength Machine learning models Concrete mix designs Sustainability |
| title | A comparative performance analysis of machine learning models for compressive strength prediction in fly ash-based geopolymers concrete using reference data |
| title_full | A comparative performance analysis of machine learning models for compressive strength prediction in fly ash-based geopolymers concrete using reference data |
| title_fullStr | A comparative performance analysis of machine learning models for compressive strength prediction in fly ash-based geopolymers concrete using reference data |
| title_full_unstemmed | A comparative performance analysis of machine learning models for compressive strength prediction in fly ash-based geopolymers concrete using reference data |
| title_short | A comparative performance analysis of machine learning models for compressive strength prediction in fly ash-based geopolymers concrete using reference data |
| title_sort | comparative performance analysis of machine learning models for compressive strength prediction in fly ash based geopolymers concrete using reference data |
| topic | Fly ash-based geopolymer (FAGP) Compressive strength Machine learning models Concrete mix designs Sustainability |
| url | http://www.sciencedirect.com/science/article/pii/S2214509525000063 |
| work_keys_str_mv | AT muhammadkashifanwar acomparativeperformanceanalysisofmachinelearningmodelsforcompressivestrengthpredictioninflyashbasedgeopolymersconcreteusingreferencedata AT muhammadahmedqurashi acomparativeperformanceanalysisofmachinelearningmodelsforcompressivestrengthpredictioninflyashbasedgeopolymersconcreteusingreferencedata AT xingyizhu acomparativeperformanceanalysisofmachinelearningmodelsforcompressivestrengthpredictioninflyashbasedgeopolymersconcreteusingreferencedata AT syyedadnanraheelshah acomparativeperformanceanalysisofmachinelearningmodelsforcompressivestrengthpredictioninflyashbasedgeopolymersconcreteusingreferencedata AT muhammadusmansiddiq acomparativeperformanceanalysisofmachinelearningmodelsforcompressivestrengthpredictioninflyashbasedgeopolymersconcreteusingreferencedata AT muhammadkashifanwar comparativeperformanceanalysisofmachinelearningmodelsforcompressivestrengthpredictioninflyashbasedgeopolymersconcreteusingreferencedata AT muhammadahmedqurashi comparativeperformanceanalysisofmachinelearningmodelsforcompressivestrengthpredictioninflyashbasedgeopolymersconcreteusingreferencedata AT xingyizhu comparativeperformanceanalysisofmachinelearningmodelsforcompressivestrengthpredictioninflyashbasedgeopolymersconcreteusingreferencedata AT syyedadnanraheelshah comparativeperformanceanalysisofmachinelearningmodelsforcompressivestrengthpredictioninflyashbasedgeopolymersconcreteusingreferencedata AT muhammadusmansiddiq comparativeperformanceanalysisofmachinelearningmodelsforcompressivestrengthpredictioninflyashbasedgeopolymersconcreteusingreferencedata |