journal article·2025-12Open access

Interpretable prediction of sulfate resistance in high-performance concrete based on ensemble learning and SHAP analysis

Jiawei Shi, Qiao Wang, Xinqiang Niu, Wei Zhou, Xiaolin Chang, Sifan Zhang

Abstract

Given increasing resource scarcity and environmental pressures, improving high-performance concrete (HPC) durability in marine environments is crucial for sustainable development. Current sulfate resistance assessment suffers from time-consuming and resource-intensive repetitive experimental testing, while existing machine learning approaches focus on isolated durability factors rather than comprehensive multi-variable marine conditions and most studies lack in-depth analysis of complex interactions within available experimental data. To address these limitations, this study develops an ensemble learning framework that leverages existing experimental data to avoid costly repetitive testing, systematically considers multi-variable interactions including SCM types, replacement levels, and employs interpretable analysis to reveal hidden patterns in sulfate resistance mechanisms. A dataset of 241 records from published studies was constructed and evaluated using five ensemble models with the corrosion resistance coefficient (Kf) as target. The Stack model achieved exceptional accuracy (R²=0.961), significantly outperforming individual models. SHAP analysis revealed that GGBS at 15–25 % replacement synergistically enhances durability when combined with fly ash. A cost-durability Pareto optimization framework yielded three mix designs with clear engineering thresholds, providing practical tools for sulfate-rich marine environments.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Concrete and Cement Materials Research · Innovative concrete reinforcement materials · Smart Materials for Construction

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (72)

Show source-provided references
1. Durable performance of recycled aggregate concrete in aggressive environments10.1061/(ASCE)MT.1943-5533.0003253 ↗
2. The confused world of sulfate attack on concrete10.1016/j.cemconres.2004.04.004 ↗
3. Research on the performance evolution of concrete under the coupling effects of sulfate attack and carbonation10.1016/j.jmrt.2023.08.206 ↗
4. Durability of micro-cracked UHPC subjected to coupled freeze-thaw and chloride salt attacks10.1016/j.cemconcomp.2024.105471 ↗
5. Engineering high-performance cementitious matrices for improved projectile impact resistance with silane, micro fibrillated cellulose and fine calcined bauxite aggregate10.1016/j.cemconcomp.2022.104835 ↗
6. Attack on plain and blended cements exposed to aggressive sulfate environments10.1016/S0958-9465(01)00082-8 ↗
7. Macroscopic properties evolution and microstructural analysis of early-age concrete in sulfate saline soil10.1016/j.conbuildmat.2024.136607 ↗
8. GGBS and Fly ash effects on compressive strength by partial replacement of cement concrete10.28991/cej-2019-03091299 ↗
9. Improving the sulfate attack resistance of concrete by using supplementary cementitious materials (SCMs): a review10.1016/j.conbuildmat.2021.122628 ↗
10. Sustainable materials for transportation infrastructures: comparison of three Commercially-Available metakaolin products in binary cementitious systems10.3390/infrastructures3030017 ↗
11. Resistance of plain and blended cement mortars exposed to severe sulfate attacks10.1016/j.conbuildmat.2010.11.106 ↗
12. Mechanical, durability, and microstructural properties of macro synthetic polypropylene (PP) fiber-reinforced rubber concrete10.1016/j.jclepro.2019.06.272 ↗
13. Sulfuric acid resistance of concrete containing coal waste as a partial substitute for fine and coarse aggregates10.1016/j.fuel.2023.128311 ↗
14. Model of time-dependent and stress-dependent chloride penetration of concrete under sustained axial pressure in the marine environment10.1016/j.conbuildmat.2018.03.077 ↗
15. Prediction of time dependent chloride transport in concrete structures exposed to a marine environment10.1016/j.cemconres.2009.09.023 ↗
16. Effect of natural carbonation on chloride binding behaviours in OPC paste investigated by a thermodynamic model
17. Investigation of the low-frequency stray current induced corrosion on reinforced concrete infrastructure in high-speed rail transit power supply system10.1016/j.ijepes.2021.107436 ↗
18. Chemo-mechanical analysis of concrete cracking and degradation due to external sulfate attack: a meso-scale model10.1016/j.cemconcomp.2010.12.001 ↗
19. A coupled phase-field model for sulfate-induced concrete cracking10.1016/j.ijmecsci.2024.109694 ↗
20. Assessment of mechanical, durability and microstructural performance of sulphate-resisting cement concrete over portland cement in the presence of salinity10.1016/j.conbuildmat.2024.135527 ↗
21. Experimental and numerical analysis of the punching behavior of RC isolated footings
22. Analyze the potential for employing internally welded steel plates to improve the shear response of high-strength self-compacting concrete-encased steel beams with large web openings10.1016/j.engstruct.2024.117636 ↗
23. Comparative analysis of shear behavior and mechanism of concrete beams with strip-shaped CFRP or conventional steel stirrups
24. Improving the flexural response of timber beams using externally bonded carbon Fiber-Reinforced polymer (CFRP) sheets10.3390/ma17020321 ↗
25. Modeling slump of ready mix concrete using genetic algorithms assisted training of artificial neural networks10.1016/j.eswa.2014.08.048 ↗
26. Prediction of slump flow of high-performance concrete via parallel hyper-cubic gene-expression programming10.1016/j.engappai.2014.05.005 ↗
27. Prediction of concrete compressive strength and slump by machine learning methods
28. Estimating concrete workability based on slump test with least squares support vector regression10.1155/2016/5089683 ↗
29. Modeling the compressive strength of high-strength concrete: an extreme learning approach10.1016/j.conbuildmat.2019.02.165 ↗
30. Predicting the compressive strength of normal and High-Performance concretes using ANN and ANFIS hybridized with grey wolf optimizer10.1016/j.conbuildmat.2019.117266 ↗
31. Designing sustainable concrete mixture by developing a new machine learning technique10.1016/j.jclepro.2020.120578 ↗
32. Prediction of chloride concentration in Fly ash concrete based on deep learning
33. Modeling chloride penetration in self-consolidating concrete using artificial neural network combined with artificial bee colony algorithm10.1016/j.jobe.2018.12.013 ↗
34. Analysis of training parameters in the ANN learning process to mapping the concrete carbonation depth10.1007/s41024-019-0054-8 ↗
35. C. Zhang, Y. Ma, eds., Ensemble Machine Learning: Methods and Applications, Springer New York, New York, NY, 2012. https://doi.org/10.1007/978-1-4419-9326-7..
36. Evaluating compressive strength of concrete made with recycled concrete aggregates using machine learning approach10.1016/j.conbuildmat.2022.126578 ↗
37. Prediction of shear strength in UHPC beams using machine learning-based models and SHAP interpretation10.1016/j.conbuildmat.2023.133752 ↗
38. Prediction of surface chloride concentration of marine concrete using ensemble machine learning10.1016/j.cemconres.2020.106164 ↗
39. Prediction of the sulfate resistance for recycled aggregate concrete based on ensemble learning algorithms10.1016/j.conbuildmat.2021.125917 ↗
40. Anti-corrosion test of tower foundation concrete for Changji-Guquan ±1100 kv UHVDC power transmission project
41. Degradation prediction of recycled aggregate concrete under sulphate wetting–drying cycles using BP neural network10.1016/j.istruc.2022.11.035 ↗
42. Li · 2015
43. Mix parameter design and crack resistance of abrasion resistant concrete with Fly ash and silica power
44. Fang · 2018
45. Effect of mineral admixtures on durability of concrete in wetting-drying cyclic sulfate environment
46. Jia · 2021
47. Peng · 2019
48. Luo · 2023
49. Effect of mineral admixture on the corrosion resistance of concrete in saline soil area of northwest China
50. Modeling the compressive strength of high-strength concrete: an extreme learning approach10.1016/j.conbuildmat.2019.02.165 ↗
51. Predicting the compressive strength of normal and High-Performance concretes using ANN and ANFIS hybridized with grey wolf optimizer10.1016/j.conbuildmat.2019.117266 ↗
52. Random forests10.1023/A:1010933404324 ↗
53. Boosting algorithms: a review of methods, theory, and applications
54. Greedy function approximation: a gradient boosting machine10.1214/aos/1013203451 ↗
55. XGBoost | Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM Conf. (n.d.). https://doi.org/10.1145/2939672.2939785.10.1145/2939672.2939785 ↗
56. Efficient hyperparameter tuning with grid search for text categorization using kNN approach with BM25 similarity10.1515/comp-2019-0011 ↗
57. S.M. Lundberg, S.-I. Lee, A Unified Approach to Interpreting Model Predictions, (n.d.).
58. A data-driven approach to predict the compressive strength of alkali-activated materials and correlation of influencing parameters using SHapley additive explanations (SHAP) analysis10.1016/j.jmrt.2023.06.207 ↗
59. Integrating experiments, finite element analysis, and interpretable machine learning to evaluate the auxetic response of 3D printed re-entrant metamaterials10.1016/j.jmrt.2023.06.038 ↗
60. Considering uncertainty in life-cycle carbon dioxide emissions of Fly ash concrete
61. Effects of micro-environmental climate on the carbonation depth and the ph value in Fly ash concrete10.1016/j.jclepro.2018.01.155 ↗
62. Potential use of binary and composite limestone cements in concrete production10.1016/j.conbuildmat.2013.12.012 ↗
63. Effect of coarse aggregate type on mechanical properties of high-performance concrete10.1016/S0008-8846(01)00588-9 ↗
64. Influence of supplementary cementitious materials on engineering properties of high strength concrete10.1016/j.conbuildmat.2010.12.013 ↗
65. Durability of cementitious materials in seawater environment: a review on chemical interactions, hardened-state properties and environmental factors10.1016/j.conbuildmat.2022.130224 ↗
66. Study on the deterioration of concrete performance in saline soil area under the combined effect of high low temperatures, chloride and sulfate salts10.1016/j.cemconcomp.2024.105531 ↗
67. The effect of coarse to fine aggregate ratio on the fresh and hardened properties of roller-compacted concrete pavement10.1016/j.conbuildmat.2018.02.216 ↗
68. Effect of W/C ratio on durability and porosity in cement mortar with constant cement amount
69. Saber Peroti, Effect of Water-Cement Ratio on Abrasive Strength, Porosity and Permeability of Nano-Silica Concrete, 2012..
70. Influence of aggregates grading and water/cement ratio in workability and hardened properties of mortars10.1016/j.conbuildmat.2010.11.011 ↗
71. Role of water/cement ratio on strength development of cement mortar10.1016/j.jobe.2015.09.003 ↗
72. Effect of binder content and recycled concrete aggregate on freeze-thaw and sulfate resistance of GGBFS based geopolymer concretes10.1016/j.conbuildmat.2021.124246 ↗