Application of machine learning in asphalt and concrete material testing: A comprehensive review
This literature review explores the application of machine learning (ML) techniques in civil engineering material testing, with a focus on asphalt mixtures, concrete properties, and pavement system classification. The review provides a comprehensive comparison of various ML models, including Artific...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Society for Materials and Structures testing of Serbia
2024-01-01
|
| Series: | Građevinski Materijali i Konstrukcije |
| Subjects: | |
| Online Access: | https://scindeks-clanci.ceon.rs/data/pdf/2217-8139/2024/2217-81392404183K.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554232878039040 |
|---|---|
| author | Khorshidi Meisam Dave Eshan Sias Jo |
| author_facet | Khorshidi Meisam Dave Eshan Sias Jo |
| author_sort | Khorshidi Meisam |
| collection | DOAJ |
| description | This literature review explores the application of machine learning (ML) techniques in civil engineering material testing, with a focus on asphalt mixtures, concrete properties, and pavement system classification. The review provides a comprehensive comparison of various ML models, including Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Random Forest (RF), Gradient Boosting (GB), and Gaussian Process Regression (GPR), assessing their strengths and limitations in predicting material performance. Key findings indicate that ensemble methods, such as Gradient Boosting and XGBoost, consistently outperformed other models in terms of prediction accuracy and handling nonlinear relationships, although they require significant computational power. In contrast, simpler models like SVM and ANN demonstrated strong predictive capabilities with smaller datasets but were prone to overfitting and computational challenges. Additionally, unsupervised learning methods, such as K-means clustering and Principal Component Analysis (PCA), proved effective in classifying pavement conditions and detecting anomalies, with K-means offering simplicity and efficiency at the cost of sensitivity to initialization and cluster definitions. The review concludes by emphasizing the potential of hybrid and ensemble models to improve prediction accuracy and reduce computational costs, highlighting the need for further research to address data availability, model interpretability, and practical implementation challenges in real-world applications. |
| format | Article |
| id | doaj-art-0c9bceedb2f643e68c3463d7712a0dff |
| institution | Kabale University |
| issn | 2335-0229 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Society for Materials and Structures testing of Serbia |
| record_format | Article |
| series | Građevinski Materijali i Konstrukcije |
| spelling | doaj-art-0c9bceedb2f643e68c3463d7712a0dff2025-01-08T16:14:45ZengSociety for Materials and Structures testing of SerbiaGrađevinski Materijali i Konstrukcije2335-02292024-01-0167418320010.5937/GRMK2400012K2217-81392404183KApplication of machine learning in asphalt and concrete material testing: A comprehensive reviewKhorshidi Meisam0https://orcid.org/0009-0003-7603-6747Dave Eshan1https://orcid.org/0000-0001-9788-2246Sias Jo2https://orcid.org/0000-0001-5284-0392University of New Hampshire, Department of Civil and Environmental Engineering, Durham, USAUniversity of New Hampshire, Department of Civil and Environmental Engineering, Durham, USAUniversity of New Hampshire, Department of Civil and Environmental Engineering, Durham, USAThis literature review explores the application of machine learning (ML) techniques in civil engineering material testing, with a focus on asphalt mixtures, concrete properties, and pavement system classification. The review provides a comprehensive comparison of various ML models, including Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Random Forest (RF), Gradient Boosting (GB), and Gaussian Process Regression (GPR), assessing their strengths and limitations in predicting material performance. Key findings indicate that ensemble methods, such as Gradient Boosting and XGBoost, consistently outperformed other models in terms of prediction accuracy and handling nonlinear relationships, although they require significant computational power. In contrast, simpler models like SVM and ANN demonstrated strong predictive capabilities with smaller datasets but were prone to overfitting and computational challenges. Additionally, unsupervised learning methods, such as K-means clustering and Principal Component Analysis (PCA), proved effective in classifying pavement conditions and detecting anomalies, with K-means offering simplicity and efficiency at the cost of sensitivity to initialization and cluster definitions. The review concludes by emphasizing the potential of hybrid and ensemble models to improve prediction accuracy and reduce computational costs, highlighting the need for further research to address data availability, model interpretability, and practical implementation challenges in real-world applications.https://scindeks-clanci.ceon.rs/data/pdf/2217-8139/2024/2217-81392404183K.pdfpredictive modelingmaterial performance predictionpavement distress classificationunsupervised learningensemble methodshybrid modelsartificial neural networks (ann)gaussian process regression (gpr) |
| spellingShingle | Khorshidi Meisam Dave Eshan Sias Jo Application of machine learning in asphalt and concrete material testing: A comprehensive review Građevinski Materijali i Konstrukcije predictive modeling material performance prediction pavement distress classification unsupervised learning ensemble methods hybrid models artificial neural networks (ann) gaussian process regression (gpr) |
| title | Application of machine learning in asphalt and concrete material testing: A comprehensive review |
| title_full | Application of machine learning in asphalt and concrete material testing: A comprehensive review |
| title_fullStr | Application of machine learning in asphalt and concrete material testing: A comprehensive review |
| title_full_unstemmed | Application of machine learning in asphalt and concrete material testing: A comprehensive review |
| title_short | Application of machine learning in asphalt and concrete material testing: A comprehensive review |
| title_sort | application of machine learning in asphalt and concrete material testing a comprehensive review |
| topic | predictive modeling material performance prediction pavement distress classification unsupervised learning ensemble methods hybrid models artificial neural networks (ann) gaussian process regression (gpr) |
| url | https://scindeks-clanci.ceon.rs/data/pdf/2217-8139/2024/2217-81392404183K.pdf |
| work_keys_str_mv | AT khorshidimeisam applicationofmachinelearninginasphaltandconcretematerialtestingacomprehensivereview AT daveeshan applicationofmachinelearninginasphaltandconcretematerialtestingacomprehensivereview AT siasjo applicationofmachinelearninginasphaltandconcretematerialtestingacomprehensivereview |