The durability of reinforced concrete structures in chloride-rich environments remains a major concern in infrastructure design, particularly in coastal regions. While standardized laboratory procedures provide reliable quantification of chloride ingress resistance, they are often time-consuming, costly, and unsuitable for early-stage mix design. This study proposes a data-driven framework for predicting the chloride resistance level of concrete using tree-based machine learning (ML) classifiers. A comprehensive experimental dataset was utilized to train and validate three ML models: Decision Tree Classifier (DTC), Random Forest Classifier (RFC), and CatBoost Classifier (CatBC). Extensive hyperparameter tuning was performed using the Optuna framework with 2000 trials per model to enhance predictive performance. Among the tested models, CatBC outperformed its counterparts with a test accuracy of 0.95 and weighted F1-score of 0.85. Feature importance analyses using SHAP values, Prediction Values Change, and other CatBoost interpretability tools consistently identified the water-to-binder ratio, superplasticizer content, test age, and aggregate proportions as key predictors of chloride resistance. The findings demonstrate that machine learning offers a fast, cost-effective, and accurate alternative for classifying concrete’s chloride resistance, supporting informed decision-making in mix design and service-life assessment.
- Open Access
- Article
Prediction of Chloride Resistance Level in Concrete Using Optimized Tree-Based Machine Learning Models
- Ali Benzaamia 1,
- Mohamed Ghrici 1, *,
- Redouane Rbouh 1,
- Ahmed Abdelghafour Ghrici 1,
- Panagiotis G. Asteris 2
Author Information
Received: 15 Jul 2025 | Revised: 08 Sep 2025 | Accepted: 17 Sep 2025 | Published: 28 Sep 2025
Abstract
Keywords
concrete durability | chloride resistance | machine learning | CatBoost | feature importance
References
- 1.
Liu, J.; Ou, G.; Qiu, Q.; et al. Atmospheric Chloride Deposition in Field Concrete at Coastal Region. Constr. Build. Mater. 2018, 190, 1015–1022. https://doi.org/10.1016/J.CONBUILDMAT.2018.09.094.
- 2.
Houska, C. Deicing Salt–Recognizing the Corrosion Threat. In International Molybdenum Association; TMR Consulting: Pittsburgh, PA, USA, 2007; pp. 1–10.
- 3.
Pontes, J.; Bogas, J.A.; Real, S.; et al. The Rapid Chloride Migration Test in Assessing the Chloride Penetration Resistance of Normal and Lightweight Concrete. Appl. Sci. 2021, 11, 7251. https://doi.org/10.3390/APP11167251.
- 4.
Elfmarkova, V.; Spiesz, P.; Brouwers, H.J.H. Determination of the Chloride Diffusion Coefficient in Blended Cement Mortars. Cem. Concr. 2015, 78, 190–199. https://doi.org/10.1016/J.CEMCONRES.2015.06.014.
- 5.
Life-365TM Service Life Prediction Model TM and Computer Program for Predicting the Service Life and Life-Cycle Cost of Reinforced Concrete Exposed to Chlorides. Available online: https://life-365.org/wp-content/uploads/2024/11/Life-365_v2.2.3_Users_Manual.pdf (accessed on 24 September 2025).
- 6.
Lindvall, A. Duracrete-Probabilistic Performance Based Durability Design of Concrete Structures. Available online: http://fib.bme.hu/proceedings/lindvall.pdf (accessed on 24 September 2025).
- 7.
NT BUILD 492 Concrete, mortar and cement-based repair materials: Chloride migration coefficient from non-steady-state migration experiments. 1999. Available online: https://salmanco.com/wp-content/uploads/2018/10/NT-Build-492.pdf (accessed on 24 September 2025).
- 8.
Tang, L.; Sørensen, H.E. Precision of the Nordic Test Methods for Measuring the Chloride Diffusion/Migration Coefficients of Concrete. Mater. Struct. 2001, 34, 479–485. https://doi.org/10.1007/BF02486496.
- 9.
Taffese, W.Z.; Espinosa-Leal, L. Prediction of Chloride Resistance Level of Concrete Using Machine Learning for Durability and Service Life Assessment of Building Structures. J. Build. Eng. 2022, 60, 105146. https://doi.org/10.1016/J.JOBE.2022.105146.
- 10.
Sari-Ahmed, B.; Benzaamia, A.; Ghrici, M.; et al. Strength Prediction of Fiber-Reinforced Clay Soils Stabilized with Lime Using XGBoost Machine Learning. Civ. Environ. Eng. Rep. 2024, 34, 157–176. https://doi.org/10.59440/CEER/190062.
- 11.
Benzaamia, A.; Ghrici, M.; Rebouh, R.; et al. Predicting the Compressive Strength of CFRP-Confined Concrete Using Deep Learning. Eng. Struct. 2024, 319, 118801. https://doi.org/10.1016/J.ENGSTRUCT.2024.118801.
- 12.
Benzaamia, A.; Ghrici, M.; Rebouh, R.; et al. Shear Strength Modeling for Reinforced Concrete Beams Strengthened with Externally Bonded Fiber-Reinforced Polymer Using Machine Learning. Structures 2025, 76, 108954. https://doi.org/10.1016/J.ISTRUC.2025.108954.
- 13.
Rebouh, R.; Benzaamia, A.; Ghrici, M. MLP Neural Networks for Compressive Strength Assessment of AFRP-Confined Concrete. South Fla. J. Dev. 2024, 5, e4765. https://doi.org/10.46932/sfjdv5n12-023.
- 14.
Cui, J.; Bai, L.; Rao, P.; et al. Prediction Model of Chloride Erosion Concrete Based on Artificial Intelligence Algorithm. Bull. Chin. Ceram. Soc. 2024, 43, 439.
- 15.
Nouri, Y.; Ghanizadeh, A.R.; Safi Jahanshahi, F.; et al. Data-Driven Prediction of Axial Compression Capacity of GFRP-Reinforced Concrete Column Using Soft Computing Methods. J. Build. Eng. 2025, 101, 111831. https://doi.org/10.1016/J.JOBE.2025.111831.
- 16.
Raeisi, A.; Sharbatdar, M.K.; Naderpour, H.; et al. Flexural Capacity Prediction of RC Beams Strengthened in Terms of NSM System Using Soft Computing. J. Soft Comput. Civ. Eng. 2024, 8, 1–26. https://doi.org/10.22115/scce.2024.429316.1761.
- 17.
Liu, K.H.; Zheng, J.K.; Pacheco-Torgal, F.; et al. Innovative Modeling Framework of Chloride Resistance of Recycled Aggregate Concrete Using Ensemble-Machine-Learning Methods. Constr. Build. Mater. 2022, 337, 127613. https://doi.org/10.1016/J.CONBUILDMAT.2022.127613.
- 18.
Fakharian, P.; Nouri, Y.; Ghanizadeh, A.R.; et al. Bond Strength Prediction of Externally Bonded Reinforcement on Groove Method (EBROG) Using MARS-POA. Compos. Struct. 2024, 349, 118532. https://doi.org/10.1016/J.COMPSTRUCT.2024.118532.
- 19.
Marks, M.; Glinicki, M.A.; Gibas, K. Prediction of the Chloride Resistance of Concrete Modified with High Calcium Fly Ash Using Machine Learning. Materials 2015, 8, 8714–8727. https://doi.org/10.3390/MA8125483.
- 20.
Marks, M.; Jóźwiak-NiedzWiedzka, D.; Glinicki, M.A. Automatic Categorization of Chloride Migration into Concrete Modified with CFBC Ash. Comput. Concr. 2012, 9, 375–387. https://doi.org/10.12989/CAC.2012.9.5.375.
- 21.
Hodhod, O.A.; Ahmed, H.I. Developing an Artificial Neural Network Model to Evaluate Chloride Diffusivity in High Performance Concrete. HBRC J. 2013, 9, 15–21.
- 22.
Yao, L.; Ren, L.; Gong, G. Evaluation of Chloride Diffusion in Concrete Using PSO-BP and BP Neural Network. In IOP Conference Series: Earth and Environmental Science; IOP Publishing: Bristol, UK, 2021; Volume 687, p. 012037. https://doi.org/10.1088/1755-1315/687/1/012037.
- 23.
Delgado, J.; Silva FA, N.; Azevedo, A.C.; et al. Artificial Neural Networks to Assess the Useful Life of Reinforced Concrete Elements Deteriorated by Accelerated Chloride Tests. J. Build. Eng. 2020, 31, 101445. https://doi.org/10.1016/J.JOBE.2020.101445.
- 24.
Sari-Ahmed, B.; Ghrici, M.; Benzaamia, A.; et al. Assessment of Unconfined Compressive Strength of Stabilized Soil Using Artificial Intelligence Tools: A Scientometrics Review. Stud. Syst. Decis. Control. 2024, 547, 271–288. https://doi.org/10.1007/978-3-031-65976-8_15.
- 25.
Benzaamia, A.; Ghrici, M.; Rebouh, R. Machine Learning Approaches for Predicting Compressive and Shear Strength of EB FRP-Reinforced Concrete Elements: A Comprehensive Review. In New Advances in Soft Computing in Civil Engineering; Springer: Berlin, Germany, 2024; pp. 221–249. https://doi.org/10.1007/978-3-031-65976-8_12.
- 26.
Quinlan, J.R. Induction of Decision Trees. Mach. Learn. 1986, 1, 81–106. https://doi.org/10.1007/BF00116251.
- 27.
Breiman, L. Random Forests. Mach Learn 2001, 45, 5–32. https://doi.org/10.1023/A:1010933404324/METRICS.
- 28.
Prokhorenkova, L.; Gusev, G.; Vorobev, A.; et al. CatBoost: Unbiased Boosting with Categorical Features. In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017; pp. 6638–6648.
- 29.
Akiba, T.; Sano, S.; Yanase, T.; et al. Optuna: A Next-Generation Hyperparameter Optimization Framework. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Anchorage, AK, USA, 4–8 August 2019; pp. 2623–2631. https://doi.org/10.1145/3292500.3330701.
- 30.
Rebouh, R.; Benzaamia, A.; Ghrici, M. Bayesian-Optimized Tree-Based Models for Predicting the Shear Strength of U-Shaped Externally Bonded FRP-Strengthened RC Beams. Asian J. Civ. Eng. 2025, 26, 1465–1478.
- 31.
Benzaamia, A.; Ghrici, M.; Rebouh, R.; et al. Predicting the Shear Strength of Rectangular RC Beams Strengthened with Externally-Bonded FRP Composites Using Constrained Monotonic Neural Networks. Eng. Struct. 2024, 313, 118192. https://doi.org/10.1016/J.ENGSTRUCT.2024.118192.
- 32.
Kechroud, F.; Benzaamia, A.; Ghrici, M. Optimized Regression-Based Machine Learning Models for Predicting Chloride Diffusion in Concrete. Asian J. Civ. Eng. 2025, 26, 2513–2526. https://doi.org/10.1007/S42107-025-01326-7/METRICS.
- 33.
Ali Aichouba, A.; Benzaamia, A.; Ezziane, M.; et al. TabNet-Based Prediction of Residual Compressive and Flexural Strengths in Hybrid Fiber-Reinforced Self-Compacting Concrete (HFR-SCC) Exposed to Elevated Temperatures. Asian J. Civ. Eng. 2025, 26, 3705–3724. https://doi.org/10.1007/S42107-025-01392-X/METRICS.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com