Explainable AutoML models for predicting the strength of high-performance concrete using Optuna, SHAP and ensemble learning
Accurately predicting key engineering properties, such as compressive and tensile strength, remains a significant challenge in high-performance concrete (HPC) due to its complex and heterogeneous composition. Early selection of optimal components and the development of reliable machine learning (ML)...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Materials |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmats.2025.1542655/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592444024160256 |
|---|---|
| author | Muhammad Salman Khan Tianbo Peng Tianbo Peng Muhammad Adeel Khan Asad Khan Mahmood Ahmad Mahmood Ahmad Kamran Aziz Mohanad Muayad Sabri Sabri N. S. Abd EL-Gawaad |
| author_facet | Muhammad Salman Khan Tianbo Peng Tianbo Peng Muhammad Adeel Khan Asad Khan Mahmood Ahmad Mahmood Ahmad Kamran Aziz Mohanad Muayad Sabri Sabri N. S. Abd EL-Gawaad |
| author_sort | Muhammad Salman Khan |
| collection | DOAJ |
| description | Accurately predicting key engineering properties, such as compressive and tensile strength, remains a significant challenge in high-performance concrete (HPC) due to its complex and heterogeneous composition. Early selection of optimal components and the development of reliable machine learning (ML) models can significantly reduce the time and cost associated with extensive experimentation. This study introduces four explainable Automated Machine Learning (AutoML) models that integrate Optuna for hyperparameter optimization, SHapley Additive exPlanations (SHAP) for interpretability, and ensemble learning algorithms such as Random Forest (RF), Extreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGB), and Categorical Gradient Boosting (CB). The resulting interpretable AutoML models O-RF, O-XGB, O-LGB, and O-CB are applied to predict the compressive and tensile strengths of HPC. Compared to a baseline model from the literature, O-LGB achieved significant improvements in predictive performance. For compressive strength, it reduced the Mean Absolute Error (MAE) by 87.69% and the Root Mean Squared Error (RMSE) by 71.93%. For tensile strength, it achieved a 99.41% improvement in MAE and a 96.67% reduction in RMSE, along with increases in R2. Furthermore, SHAP analysis identified critical factors influencing strength, such as cement content, water, and age for compressive strength, and curing age, water-binder ratio, and water-cement ratio for tensile strength. This approach provides civil engineers with a robust and interpretable tool for optimizing HPC properties, reducing experimentation costs, and supporting enhanced decision-making in structural design, risk assessment, and other applications. |
| format | Article |
| id | doaj-art-fc6ad052e0e041c194355fdae5a788dd |
| institution | Kabale University |
| issn | 2296-8016 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Materials |
| spelling | doaj-art-fc6ad052e0e041c194355fdae5a788dd2025-01-21T08:37:07ZengFrontiers Media S.A.Frontiers in Materials2296-80162025-01-011210.3389/fmats.2025.15426551542655Explainable AutoML models for predicting the strength of high-performance concrete using Optuna, SHAP and ensemble learningMuhammad Salman Khan0Tianbo Peng1Tianbo Peng2Muhammad Adeel Khan3Asad Khan4Mahmood Ahmad5Mahmood Ahmad6Kamran Aziz7Mohanad Muayad Sabri Sabri8N. S. Abd EL-Gawaad9Department of Bridge Engineering, College of Civil Engineering, Tongji University, Shanghai, ChinaDepartment of Bridge Engineering, College of Civil Engineering, Tongji University, Shanghai, ChinaState Key Laboratory of Disaster Reduction in Civil Engineering, Tongji University, Shanghai, ChinaDepartment of Bridge Engineering, College of Civil Engineering, Tongji University, Shanghai, ChinaDepartment of Bridge Engineering, College of Civil Engineering, Tongji University, Shanghai, ChinaInstitute of Energy Infrastructure, Universiti Tenaga Nasional, Kajang, MalaysiaDepartment of Civil Engineering, University of Engineering and Technology Peshawar (Bannu Campus), Bannu, PakistanThe Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, Shanghai, ChinaPeter the Great St. Petersburg Polytechnic University, Saint Petersburg, RussiaMuhayil Asir, Applied College, King Khalid University, Abha, Saudi ArabiaAccurately predicting key engineering properties, such as compressive and tensile strength, remains a significant challenge in high-performance concrete (HPC) due to its complex and heterogeneous composition. Early selection of optimal components and the development of reliable machine learning (ML) models can significantly reduce the time and cost associated with extensive experimentation. This study introduces four explainable Automated Machine Learning (AutoML) models that integrate Optuna for hyperparameter optimization, SHapley Additive exPlanations (SHAP) for interpretability, and ensemble learning algorithms such as Random Forest (RF), Extreme Gradient Boosting (XGB), Light Gradient Boosting Machine (LGB), and Categorical Gradient Boosting (CB). The resulting interpretable AutoML models O-RF, O-XGB, O-LGB, and O-CB are applied to predict the compressive and tensile strengths of HPC. Compared to a baseline model from the literature, O-LGB achieved significant improvements in predictive performance. For compressive strength, it reduced the Mean Absolute Error (MAE) by 87.69% and the Root Mean Squared Error (RMSE) by 71.93%. For tensile strength, it achieved a 99.41% improvement in MAE and a 96.67% reduction in RMSE, along with increases in R2. Furthermore, SHAP analysis identified critical factors influencing strength, such as cement content, water, and age for compressive strength, and curing age, water-binder ratio, and water-cement ratio for tensile strength. This approach provides civil engineers with a robust and interpretable tool for optimizing HPC properties, reducing experimentation costs, and supporting enhanced decision-making in structural design, risk assessment, and other applications.https://www.frontiersin.org/articles/10.3389/fmats.2025.1542655/fullhigh performance concretemachine learningensemble learning algorithmSHAPOptunacompressive strength |
| spellingShingle | Muhammad Salman Khan Tianbo Peng Tianbo Peng Muhammad Adeel Khan Asad Khan Mahmood Ahmad Mahmood Ahmad Kamran Aziz Mohanad Muayad Sabri Sabri N. S. Abd EL-Gawaad Explainable AutoML models for predicting the strength of high-performance concrete using Optuna, SHAP and ensemble learning Frontiers in Materials high performance concrete machine learning ensemble learning algorithm SHAP Optuna compressive strength |
| title | Explainable AutoML models for predicting the strength of high-performance concrete using Optuna, SHAP and ensemble learning |
| title_full | Explainable AutoML models for predicting the strength of high-performance concrete using Optuna, SHAP and ensemble learning |
| title_fullStr | Explainable AutoML models for predicting the strength of high-performance concrete using Optuna, SHAP and ensemble learning |
| title_full_unstemmed | Explainable AutoML models for predicting the strength of high-performance concrete using Optuna, SHAP and ensemble learning |
| title_short | Explainable AutoML models for predicting the strength of high-performance concrete using Optuna, SHAP and ensemble learning |
| title_sort | explainable automl models for predicting the strength of high performance concrete using optuna shap and ensemble learning |
| topic | high performance concrete machine learning ensemble learning algorithm SHAP Optuna compressive strength |
| url | https://www.frontiersin.org/articles/10.3389/fmats.2025.1542655/full |
| work_keys_str_mv | AT muhammadsalmankhan explainableautomlmodelsforpredictingthestrengthofhighperformanceconcreteusingoptunashapandensemblelearning AT tianbopeng explainableautomlmodelsforpredictingthestrengthofhighperformanceconcreteusingoptunashapandensemblelearning AT tianbopeng explainableautomlmodelsforpredictingthestrengthofhighperformanceconcreteusingoptunashapandensemblelearning AT muhammadadeelkhan explainableautomlmodelsforpredictingthestrengthofhighperformanceconcreteusingoptunashapandensemblelearning AT asadkhan explainableautomlmodelsforpredictingthestrengthofhighperformanceconcreteusingoptunashapandensemblelearning AT mahmoodahmad explainableautomlmodelsforpredictingthestrengthofhighperformanceconcreteusingoptunashapandensemblelearning AT mahmoodahmad explainableautomlmodelsforpredictingthestrengthofhighperformanceconcreteusingoptunashapandensemblelearning AT kamranaziz explainableautomlmodelsforpredictingthestrengthofhighperformanceconcreteusingoptunashapandensemblelearning AT mohanadmuayadsabrisabri explainableautomlmodelsforpredictingthestrengthofhighperformanceconcreteusingoptunashapandensemblelearning AT nsabdelgawaad explainableautomlmodelsforpredictingthestrengthofhighperformanceconcreteusingoptunashapandensemblelearning |