Machine learning in concrete science: applications, challenges, and best practices
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Infrastructure Maintenance and Monitoring · Concrete Corrosion and Durability · Concrete and Cement Materials Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (100+)
Show source-provided references
1. Monteiro, P. J., Miller, S. A. & Horvath, A. Towards sustainable concrete. Nat. Mater. 16, 698–699 (2017).10.1038/nmat4930 ↗
2. Mehta, P. K. & Monteiro, P. J. M. Concrete: microstructure, properties, and materials (McGraw-Hill Education, 2014).
3. Van Damme, H. Concrete material science: Past, present, and future innovations. Cem. Concr. Res. 112, 5–24 (2018).10.1016/j.cemconres.2018.05.002 ↗
4. Gagg, C. R. Cement and concrete as an engineering material: An historic appraisal and case study analysis. Eng. Fail. Anal. 40, 114–140 (2014).10.1016/j.engfailanal.2014.02.004 ↗
5. DeRousseau, M. A., Kasprzyk, J. R. & Srubar, W. V. Computational design optimization of concrete mixtures: A review. Cem. Concr. Res. 109, 42–53 (2018).10.1016/j.cemconres.2018.04.007 ↗
6. Soudki, K. A., El-Salakawy, E. F. & Elkum, N. B. Full Factorial Optimization of Concrete Mix Design for Hot Climates. J. Mater. Civ. Eng. 13, 427–433 (2001).10.1061/(ASCE)0899-1561(2001)13:6(427) ↗
7. Garboczi, E. J., Bentz, D. P. & Frohnsdorff, G. J. The past, present, and future of the computational materials science of concrete. In J. Francis Young Symposium (Materials Science of Concrete Workshop, 2000).
8. Bentz, D. P. Three-dimensional computer simulation of portland cement hydration and microstructure development. J. Am. Ceram. Soc. 80, 3–21 (1997).10.1111/j.1151-2916.1997.tb02785.x ↗
9. Bentz, D. P. Modelling cement microstructure: Pixels, particles, and property prediction. Mater. Struct. 32, 187–195 (1999).10.1007/BF02481514 ↗
10. van Breugel, K. Numerical simulation of hydration and microstructural development in hardening cement-based materials (I) theory. Cem. Concr. Res. 25, 319–331 (1995).10.1016/0008-8846(95)00017-8 ↗
11. Navi, P. & Pignat, C. Simulation of cement hydration and the connectivity of the capillary pore space. Adv. Cem. Based Mater. 4, 58–67 (1996).10.1016/S1065-7355(96)90052-8 ↗
12. Bishnoi, S. & Scrivener, K. L. μic: A new platform for modelling the hydration of cements. Cem. Concr. Res. 39, 266–274 (2009).10.1016/j.cemconres.2008.12.002 ↗
13. Lothenbach, B. & Winnefeld, F. Thermodynamic modelling of the hydration of Portland cement. Cem. Concr. Res. 36, 209–226 (2006).10.1016/j.cemconres.2005.03.001 ↗
14. Damidot, D., Lothenbach, B., Herfort, D. & Glasser, F. P. Thermodynamics and cement science. Cem. Concr. Res. 41, 679–695 (2011).10.1016/j.cemconres.2011.03.018 ↗
15. Lothenbach, B. & Zajac, M. Application of thermodynamic modelling to hydrated cements. Cem. Concr. Res. 123, 105779 (2019).10.1016/j.cemconres.2019.105779 ↗
16. Cho, B. H., Chung, W. & Nam, B. H. Molecular dynamics simulation of calcium-silicate-hydrate for nano-engineered cement composites-a review. Nanomaterials 10, 1–25 (2020).10.3390/nano10112158 ↗
17. Thomas, J. J. et al. Modeling and simulation of cement hydration kinetics and microstructure development. Cem. Concr. Res. 41, 1257–1278 (2011).10.1016/j.cemconres.2010.10.004 ↗
18. Dolado, J. S. & Van Breugel, K. Recent advances in modeling for cementitious materials. Cem. Concr. Res. 41, 711–726 (2011).10.1016/j.cemconres.2011.03.014 ↗
19. Scrivener, K. L. & Kirkpatrick, R. J. Innovation in use and research on cementitious material. Cem. Concr. Res. 38, 128–136 (2008).10.1016/j.cemconres.2007.09.025 ↗
20. Park, K. B., Noguchi, T. & Plawsky, J. Modeling of hydration reactions using neural networks to predict the average properties of cement paste. Cem. Concr. Res. 35, 1676–1684 (2005).10.1016/j.cemconres.2004.08.004 ↗
21. Ford, E., Kailas, S., Maneparambil, K. & Neithalath, N. Machine learning approaches to predict the micromechanical properties of cementitious hydration phases from microstructural chemical maps. Constr. Build. Mater. 265, 120647 (2020).10.1016/j.conbuildmat.2020.120647 ↗
22. Akkurt, S., Tayfur, G. & Can, S. Fuzzy logic model for the prediction of cement compressive strength. Cem. Concr. Res. 34, 1429–1433 (2004).10.1016/j.cemconres.2004.01.020 ↗
23. Koniorczyk, M. & Wojciechowski, M. Influence of salt on desorption isotherm and hygral state of cement mortar - Modelling using neural networks. Constr. Build. Mater. 23, 2988–2996 (2009).10.1016/j.conbuildmat.2009.05.001 ↗
24. Yeh, I. C. Modeling of strength of high-performance concrete using artificial neural networks. Cem. Concr. Res. 28, 1797–1808 (1998).10.1016/S0008-8846(98)00165-3 ↗
25. Han, Q., Gui, C., Xu, J. & Lacidogna, G. A generalized method to predict the compressive strength of high-performance concrete by improved random forest algorithm. Constr. Build. Mater. 226, 734–742 (2019).10.1016/j.conbuildmat.2019.07.315 ↗
26. Kaloop, M. R., Kumar, D., Samui, P., Hu, J. W. & Kim, D. Compressive strength prediction of high-performance concrete using gradient tree boosting machine. Constr. Build. Mater. 264, 120198 (2020).10.1016/j.conbuildmat.2020.120198 ↗
27. El-Chabib, H. & Nehdi, M. Effect of mixture design parameters on segregation of self-consolidating concrete. ACI Mater. J. 103, 374–383 (2006).
28. Hendi, A. et al. Mix design of the green self-consolidating concrete: Incorporating the waste glass powder. Constr. Build. Mater. 199, 369–384 (2019).10.1016/j.conbuildmat.2018.12.020 ↗
29. Ramkumar, K. B., Kannan Rajkumar, P. R., Noor Ahmmad, S. & Jegan, M. A Review on Performance of Self-Compacting Concrete - Use of Mineral Admixtures and Steel Fibres with Artificial Neural Network Application. Constr. Build. Mater. 261, 120215 (2020).10.1016/j.conbuildmat.2020.120215 ↗
30. Mu, B., Li, Z. & Peng, J. Short fiber-reinforced cementitious extruded plates with high percentage of slag and different fibers. Cem. Concr. Res. 30, 1277–1282 (2000).10.1016/S0008-8846(00)00333-1 ↗
31. Tong, Z., Gao, J., Wang, Z., Wei, Y. & Dou, H. A new method for CF morphology distribution evaluation and CFRC property prediction using cascade deep learning. Constr. Build. Mater. 222, 829–838 (2019).10.1016/j.conbuildmat.2019.06.160 ↗
32. Tong, Z., Huo, J. & Wang, Z. High-throughput design of fiber reinforced cement-based composites using deep learning. Cem. Concr. Compos. 113, 103716 (2020).10.1016/j.cemconcomp.2020.103716 ↗
33. Zhang, J., Huang, Y., Ma, G., Sun, J. & Nener, B. A metaheuristic-optimized multi-output model for predicting multiple properties of pervious concrete. Constr. Build. Mater. 249, 118803 (2020).10.1016/j.conbuildmat.2020.118803 ↗
34. Xu, J. et al. Parametric sensitivity analysis and modelling of mechanical properties of normal- and high-strength recycled aggregate concrete using grey theory, multiple nonlinear regression and artificial neural networks. Constr. Build. Mater. 211, 479–491 (2019).10.1016/j.conbuildmat.2019.03.234 ↗
35. Han, T., Siddique, A., Khayat, K., Huang, J. & Kumar, A. An ensemble machine learning approach for prediction and optimization of modulus of elasticity of recycled aggregate concrete. Constr. Build. Mater. 244, 118271 (2020).10.1016/j.conbuildmat.2020.118271 ↗
36. Nunez, I. & Nehdi, M. L. Machine learning prediction of carbonation depth in recycled aggregate concrete incorporating SCMs. Constr. Build. Mater. 287, 123027 (2021).10.1016/j.conbuildmat.2021.123027 ↗
37. Alshihri, M. M., Azmy, A. M. & El-Bisy, M. S. Neural networks for predicting compressive strength of structural light weight concrete. Constr. Build. Mater. 23, 2214–2219 (2009).10.1016/j.conbuildmat.2008.12.003 ↗
38. Migallón, V., Navarro-González, F., Penadés, J. & Villacampa, Y. Parallel approach of a Galerkin-based methodology for predicting the compressive strength of the lightweight aggregate concrete. Constr. Build. Mater. 219, 56–68 (2019).10.1016/j.conbuildmat.2019.05.160 ↗
39. Gunasekera, C. et al. Design of Alkali-Activated Slag-Fly Ash Concrete Mixtures Using Machine Learning. ACI Mater. J. 117, 263–278 (2020).
40. Ke, X. & Duan, Y. Coupling machine learning with thermodynamic modelling to develop a composition-property model for alkali-activated materials. Compos. Part B: Eng. 216, 108801 (2021).10.1016/j.compositesb.2021.108801 ↗
41. Kazemian, A., Yuan, X., Davtalab, O. & Khoshnevis, B. Computer vision for real-time extrusion quality monitoring and control in robotic construction. Autom. Constr. 101, 92–98 (2019).10.1016/j.autcon.2019.01.022 ↗
42. Davtalab, O., Kazemian, A., Yuan, X. & Khoshnevis, B. Automated inspection in robotic additive manufacturing using deep learning for layer deformation detection. J. Intell. Manufact. 33, 771–784 (2020).10.1007/s10845-020-01684-w ↗
43. Morgan, D. & Jacobs, R. Opportunities and Challenges for Machine Learning in Materials Science. Annu. Rev. Mater. Res. 50, 71–103 (2020).10.1146/annurev-matsci-070218-010015 ↗
44. Pratt, D. & Sansalone, M. Impact-echo signal interpretation using artificial intelligence. ACI Mater. J. 89, 178–187 (1992).
45. Mo, Y. L. & Lin, S. S. Investigation of framed shearwall behaviour with neural networks. Mag. Concr. Res. 46, 289–299 (1994).10.1680/macr.1994.46.169.289 ↗
46. Martinez, P., Al-Hussein, M. & Ahmad, R. A scientometric analysis and critical review of computer vision applications for construction. Autom Constr. 107, 102947 (2019).10.1016/j.autcon.2019.102947 ↗
47. Li, Z. & Radlińska, A. Artificial intelligence in concrete materials: A scientometric view. In Naser, M. Z. (ed.) Leveraging Artificial Intelligence in Engineering, Management, and Safety of Infrastructure (CRC Press, 2022).
48. Khallaf, R. & Khallaf, M. Classification and analysis of deep learning applications in construction: A systematic literature review. Autom. Constr. 129, 103760 (2021).10.1016/j.autcon.2021.103760 ↗
49. Rafiei, M. H., Khushefati, W. H., Demirboga, R. & Adeli, H. Neural network, machine learning, and evolutionary approaches for concrete material characterization. ACI Mater. J. 113, 781–789 (2016).
50. Ben Chaabene, W., Flah, M. & Nehdi, M. L. Machine learning prediction of mechanical properties of concrete: Critical review. Constr. Build. Mater. 260, 119889 (2020).10.1016/j.conbuildmat.2020.119889 ↗
51. Nunez, I., Marani, A., Flah, M. & Nehdi, M. L. Estimating compressive strength of modern concrete mixtures using computational intelligence: A systematic review. Constr. Build. Mater. 310, 125279 (2021).10.1016/j.conbuildmat.2021.125279 ↗
52. Alpaydin, E. Introduction to machine learning (MIT Press, 2020).10.7551/mitpress/13811.001.0001 ↗
53. Rafiei, M. H., Khushefati, W. H., Demirboga, R. & Adeli, H. Novel approach for concrete mixture design using neural dynamics model and virtual lab concept. ACI Mater. J. 114, 117–127 (2017).
54. Young, B. A., Hall, A., Pilon, L., Gupta, P. & Sant, G. Can the compressive strength of concrete be estimated from knowledge of the mixture proportions?: New insights from statistical analysis and machine learning methods. Cem. Concr. Res. 115, 379–388 (2019).10.1016/j.cemconres.2018.09.006 ↗
55. Sbartaï, Z. M., Laurens, S., Elachachi, S. M. & Payan, C. Concrete properties evaluation by statistical fusion of NDT techniques. Constr. Build. Mater. 37, 943–950 (2012).10.1016/j.conbuildmat.2012.09.064 ↗
56. Amini, K., Jalalpour, M. & Delatte, N. Advancing concrete strength prediction using non-destructive testing: Development and verification of a generalizable model. Constr. Build. Mater. 102, 762–768 (2016).10.1016/j.conbuildmat.2015.10.131 ↗
57. Chun, P. J., Ujike, I., Mishima, K., Kusumoto, M. & Okazaki, S. Random forest-based evaluation technique for internal damage in reinforced concrete featuring multiple nondestructive testing results. Constr. Build. Mater. 253, 119238 (2020).10.1016/j.conbuildmat.2020.119238 ↗
58. Farhidzadeh, A., Mpalaskas, A. C., Matikas, T. E., Farhidzadeh, H. & Aggelis, D. G. Fracture mode identification in cementitious materials using supervised pattern recognition of acoustic emission features. Constr. Build. Mater. 67, 129–138 (2014).10.1016/j.conbuildmat.2014.05.015 ↗
59. Ma, G. & Du, Q. Structural health evaluation of the prestressed concrete using advanced acoustic emission (AE) parameters. Constr. Build. Mater. 250, 118860 (2020).10.1016/j.conbuildmat.2020.118860 ↗
60. Dorafshan, S. & Azari, H. Deep learning models for bridge deck evaluation using impact echo. Constr. Build. Mater. 263, 120109 (2020).10.1016/j.conbuildmat.2020.120109 ↗
61. Omar, T., Nehdi, M. L. & Zayed, T. Rational Condition Assessment of RC Bridge Decks Subjected to Corrosion-Induced Delamination. J. Mater. Civ. Eng. 30, 04017259 (2018).10.1061/(ASCE)MT.1943-5533.0002114 ↗
62. Manca, M., Karrech, A., Dight, P. & Ciancio, D. Image Processing and Machine Learning to investigate fibre distribution on fibre-reinforced shotcrete Round Determinate Panels. Constr. Build. Mater. 190, 870–880 (2018).10.1016/j.conbuildmat.2018.09.141 ↗
63. Liu, Z., Cao, Y., Wang, Y. & Wang, W. Computer vision-based concrete crack detection using U-net fully convolutional networks. Autom. Constr. 104, 129–139 (2019).10.1016/j.autcon.2019.04.005 ↗
64. Flah, M., Suleiman, A. R. & Nehdi, M. L. Classification and quantification of cracks in concrete structures using deep learning image-based techniques. Cem. Concr. Compos. 114, 103781 (2020).10.1016/j.cemconcomp.2020.103781 ↗
65. González-Jorge, H., Gonzalez-Aguilera, D., Rodriguez-Gonzalvez, P. & Arias, P. Monitoring biological crusts in civil engineering structures using intensity data from terrestrial laser scanners. Constr. Build. Mater. 31, 119–128 (2012).10.1016/j.conbuildmat.2011.12.053 ↗
66. Park, S. E., Eem, S. H. & Jeon, H. Concrete crack detection and quantification using deep learning and structured light. Constr. Build. Mater. 252, 119096 (2020).10.1016/j.conbuildmat.2020.119096 ↗
67. Omar, T., Nehdi, M. L. & Zayed, T. Infrared thermography model for automated detection of delamination in RC bridge decks. Constr. Build. Mater. 168, 313–327 (2018).10.1016/j.conbuildmat.2018.02.126 ↗
68. Song, Y., Huang, Z., Shen, C., Shi, H. & Lange, D. A. Deep learning-based automated image segmentation for concrete petrographic analysis. Cem. Concr. Res. 135, 106118 (2020).10.1016/j.cemconres.2020.106118 ↗
69. Tong, Z., Guo, H., Gao, J. & Wang, Z. A novel method for multi-scale carbon fiber distribution characterization in cement-based composites. Constr. Build. Mater. 218, 40–52 (2019).10.1016/j.conbuildmat.2019.05.115 ↗
70. Lorenzoni, R. et al. Semantic segmentation of the micro-structure of strain-hardening cement-based composites (SHCC) by applying deep learning on micro-computed tomography scans. Cem. Concr. Compos. 108, 103551 (2020).10.1016/j.cemconcomp.2020.103551 ↗
71. Lorenzoni, R. et al. Combined mechanical and 3D-microstructural analysis of strain-hardening cement-based composites (SHCC) by in-situ X-ray microtomography. Cem. Concr. Res. 136, 106139 (2020).10.1016/j.cemconres.2020.106139 ↗
72. Park, K. B., Jee, N. Y., Yoon, I. S. & Lee, H. S. Prediction of temperature distribution in high-strength concrete using hydration model. ACI Mater. J. 105, 180–186 (2008).
73. Yan, Y., Ren, Q., Xia, N., Shen, L. & Gu, J. Artificial neural network approach to predict the fracture parameters of the size effect model for concrete. Fatigue Fract. Eng. Mater. Struct. 38, 1347–1358 (2015).10.1111/ffe.12309 ↗
74. Alnaggar, M. & Bhanot, N. A machine learning approach for the identification of the Lattice Discrete Particle Model parameters. Eng. Fract. Mech. 197, 160–175 (2018).10.1016/j.engfracmech.2018.04.041 ↗
75. Kobayashi, K. et al. Machine learning potentials for tobermorite minerals. Comput. Mater. Sci. 188, 110173 (2021).10.1016/j.commatsci.2020.110173 ↗
76. Schmidt, J., Marques, M. R., Botti, S. & Marques, M. A. Recent advances and applications of machine learning in solid-state materials science. npj Comput. Mater. 5, 83 (2019).10.1038/s41524-019-0221-0 ↗
77. Wang, A. Y. T. et al. Machine Learning for Materials Scientists: An Introductory Guide toward Best Practices. Chem. Mater. 32, 4954–4965 (2020).10.1021/acs.chemmater.0c01907 ↗
78. Tao, Q., Xu, P., Li, M. & Lu, W. Machine learning for perovskite materials design and discovery. npj Comput. Mater. 7, 1–18 (2021).10.1038/s41524-021-00495-8 ↗
79. Zhao, S. et al. Dataset of tensile strength development of concrete with manufactured sand. Data Brief. 11, 469–472 (2017).10.1016/j.dib.2017.02.043 ↗
80. Ng, A. Machine learning yearning: Technical strategy for AI engineers in the era of deep learning (GitHub, 2018). http://www.mlyearning.org.
81. Teschendorff, A. E. Avoiding common pitfalls in machine learning omic data science. Nat. Mater. 18, 422–427 (2019).10.1038/s41563-018-0241-z ↗
82. Kassraian-Fard, P., Matthis, C., Balsters, J. H., Maathuis, M. H. & Wenderoth, N. Promises, pitfalls, and basic guidelines for applying machine learning classifiers to psychiatric imaging data, with autism as an example. Front. Psychiatry 7, 177 (2016).10.3389/fpsyt.2016.00177 ↗
83. Bellman, R. E. Adaptive control processes: a guided tour (Princeton University Press, 1961).10.1515/9781400874668 ↗
84. Scott, D. W. Multivariate density estimation: theory, practice, and visualization (John Wiley & Sons, 2015).10.1002/9781118575574 ↗
85. Pestov, V. An axiomatic approach to intrinsic dimension of a dataset. Neural Netw. 21, 204–213 (2008).10.1016/j.neunet.2007.12.030 ↗
86. Kutner, M. H. et al. Applied linear statistical models (McGraw-Hill Irwin, 2005).
87. Zheng, A. & Casari, A. Feature engineering for machine learning: principles and techniques for data scientists (O’Reilly Media, 2018).
88. Kuhn, M. & Johnson, K. Feature engineering and selection: A practical approach for predictive models (CRC Press, 2019).10.1201/9781315108230 ↗
89. Müller, A. C. & Guido, S. Introduction to machine learning with Python: a guide for data scientists (O’Reilly Media, 2016).
90. Suresh, H. & Guttag, J. A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle. In Equity and Access in Algorithms, Mechanisms, and Optimization, 1–9 (2021).10.1145/3465416.3483305 ↗
91. Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K. & Galstyan, A. A Survey on Bias and Fairness in Machine Learning. ACM Comput. Surv. 54, 1–35 (2021).10.1145/3457607 ↗
92. Olteanu, A., Castillo, C., Diaz, F. & Kícíman, E. Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries. Front. Big Data 2, 13 (2019).10.3389/fdata.2019.00013 ↗
93. ASTM Committee. ASTM C618-19 Standard Specification for Coal Fly Ash and Raw or Calcined Natural Pozzolan for Use (2019).
94. Bažant, Z. R. & Li, G. H. Unbiased statistical comparison of creep and shrinkage prediction models. ACI Mater. J. 105, 610–621 (2008).
95. Wendner, R., Hubler, M. H. & Bažant, Z. P. Optimization method, choice of form and uncertainty quantification of Model B4 using laboratory and multi-decade bridge databases. Mater. Struct. 48, 771–796 (2015).10.1617/s11527-014-0515-0 ↗
96. Hubler, M. H., Wendner, R. & Bažant, Z. P. Comprehensive database for concrete creep and shrinkage: Analysis and recommendations for testing and recording. ACI Mater. J. 112, 547–558 (2015).
97. DeRousseau, M. A., Laftchiev, E., Kasprzyk, J. R., Rajagopalan, B. & Srubar, W. V. A comparison of machine learning methods for predicting the compressive strength of field-placed concrete. Constr. Build. Mater. 228, 116661 (2019).10.1016/j.conbuildmat.2019.08.042 ↗
98. Kaufman, S., Rosset, S., Perlich, C. & Stitelman, O. Leakage in data mining: Formulation, detection, and avoidance. ACM Trans. Knowl. Discov. Data 6, 1–21 (2012).10.1145/2382577.2382579 ↗
99. Vabalas, A., Gowen, E., Poliakoff, E. & Casson, A. J. Machine learning algorithm validation with a limited sample size. PLoS ONE 14, 1–20 (2019).10.1371/journal.pone.0224365 ↗
100. Ouyang, B. et al. Predicting concrete’s strength by machine learning: Balance between accuracy and complexity of algorithms. ACI Mater. J. 117, 125–134 (2020).