Machine learning in concrete science: applications, challenges, and best practices
Abstract Concrete, as the most widely used construction material, is inextricably connected with human development. Despite conceptual and methodological progress in concrete science, concrete formulation for target properties remains a challenging task due to the ever-increasing complexity of cemen...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-06-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-022-00810-x |
| _version_ | 1811251446465691648 |
|---|---|
| author | Zhanzhao Li Jinyoung Yoon Rui Zhang Farshad Rajabipour Wil V. Srubar III Ismaila Dabo Aleksandra Radlińska |
| author_facet | Zhanzhao Li Jinyoung Yoon Rui Zhang Farshad Rajabipour Wil V. Srubar III Ismaila Dabo Aleksandra Radlińska |
| author_sort | Zhanzhao Li |
| collection | DOAJ |
| description | Abstract Concrete, as the most widely used construction material, is inextricably connected with human development. Despite conceptual and methodological progress in concrete science, concrete formulation for target properties remains a challenging task due to the ever-increasing complexity of cementitious systems. With the ability to tackle complex tasks autonomously, machine learning (ML) has demonstrated its transformative potential in concrete research. Given the rapid adoption of ML for concrete mixture design, there is a need to understand methodological limitations and formulate best practices in this emerging computational field. Here, we review the areas in which ML has positively impacted concrete science, followed by a comprehensive discussion of the implementation, application, and interpretation of ML algorithms. We conclude by outlining future directions for the concrete community to fully exploit the capabilities of ML models. |
| first_indexed | 2024-04-12T16:20:35Z |
| format | Article |
| id | doaj.art-02d69e52881a48d88440fd8b4915e485 |
| institution | Directory Open Access Journal |
| issn | 2057-3960 |
| language | English |
| last_indexed | 2024-04-12T16:20:35Z |
| publishDate | 2022-06-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj.art-02d69e52881a48d88440fd8b4915e4852022-12-22T03:25:34ZengNature Portfolionpj Computational Materials2057-39602022-06-018111710.1038/s41524-022-00810-xMachine learning in concrete science: applications, challenges, and best practicesZhanzhao Li0Jinyoung Yoon1Rui Zhang2Farshad Rajabipour3Wil V. Srubar III4Ismaila Dabo5Aleksandra Radlińska6Department of Civil and Environmental Engineering, The Pennsylvania State UniversityDepartment of Civil and Environmental Engineering, The Pennsylvania State UniversityDepartment of Civil and Environmental Engineering, The Pennsylvania State UniversityDepartment of Civil and Environmental Engineering, The Pennsylvania State UniversityDepartment of Civil, Environmental, and Architectural Engineering, University of Colorado BoulderDepartment of Materials Science and Engineering, The Pennsylvania State UniversityDepartment of Civil and Environmental Engineering, The Pennsylvania State UniversityAbstract Concrete, as the most widely used construction material, is inextricably connected with human development. Despite conceptual and methodological progress in concrete science, concrete formulation for target properties remains a challenging task due to the ever-increasing complexity of cementitious systems. With the ability to tackle complex tasks autonomously, machine learning (ML) has demonstrated its transformative potential in concrete research. Given the rapid adoption of ML for concrete mixture design, there is a need to understand methodological limitations and formulate best practices in this emerging computational field. Here, we review the areas in which ML has positively impacted concrete science, followed by a comprehensive discussion of the implementation, application, and interpretation of ML algorithms. We conclude by outlining future directions for the concrete community to fully exploit the capabilities of ML models.https://doi.org/10.1038/s41524-022-00810-x |
| spellingShingle | Zhanzhao Li Jinyoung Yoon Rui Zhang Farshad Rajabipour Wil V. Srubar III Ismaila Dabo Aleksandra Radlińska Machine learning in concrete science: applications, challenges, and best practices npj Computational Materials |
| title | Machine learning in concrete science: applications, challenges, and best practices |
| title_full | Machine learning in concrete science: applications, challenges, and best practices |
| title_fullStr | Machine learning in concrete science: applications, challenges, and best practices |
| title_full_unstemmed | Machine learning in concrete science: applications, challenges, and best practices |
| title_short | Machine learning in concrete science: applications, challenges, and best practices |
| title_sort | machine learning in concrete science applications challenges and best practices |
| url | https://doi.org/10.1038/s41524-022-00810-x |
| work_keys_str_mv | AT zhanzhaoli machinelearninginconcretescienceapplicationschallengesandbestpractices AT jinyoungyoon machinelearninginconcretescienceapplicationschallengesandbestpractices AT ruizhang machinelearninginconcretescienceapplicationschallengesandbestpractices AT farshadrajabipour machinelearninginconcretescienceapplicationschallengesandbestpractices AT wilvsrubariii machinelearninginconcretescienceapplicationschallengesandbestpractices AT ismailadabo machinelearninginconcretescienceapplicationschallengesandbestpractices AT aleksandraradlinska machinelearninginconcretescienceapplicationschallengesandbestpractices |