Welcome to Bilingual Publishing Group
Bilingual Publishing Group

Interpretable Machine Learning for Wear Depth Prediction in Sustainable Fly Ash Concrete

Authors

  • Payam Ismael Abdulrahman ORCID Civil Engineering Department, Tishk International University, Erbil 44001, Iraq
  • Hemin Said Mohammed Amin ORCID Geomatics Department, College of Engineering, Salahaddin University-Erbil, Erbil 44001, Iraq
  • Ahmed Salih Mohammed Email ORCID Civil Engineering Department, College of Engineering, University of Sulaimani, Sulaymaniyah 46001, Iraq

DOI:

https://doi.org/10.30564/jbms.v8i4.117236
Received: 18 July 2026 | Revised: 6 August 2026 | Accepted: 26 August 2026 | Published Online: 23 October 2026

Abstract

Wear depth is a key indicator of concrete durability under abrasive conditions, but traditional testing methods are labor-intensive, expensive, and slow. This research introduces a materials informatics framework that uses statistical models and machine learning to predict wear depth in fly ash concrete. A database with 439 concrete mixes was assembled from published sources. Input variables included cement, water, fly ash, aggregates, superplasticizer, air-entraining agent, curing age, and testing duration, with wear depth as the output. Four models were created and evaluated: nonlinear regression (NLR), multilinear regression (MLR), full quadratic (FQ) regression, and an artificial neural network (ANN). The models' effectiveness was measured by R2, RMSE (root mean squared error), and MAE (mean absolute error). The ANN outperformed others, with R2 around 0.99, RMSE of 0.097 mm, and MAE of 0.071 mm. Sensitivity analysis showed testing duration and curing age as the most influential factors, emphasizing the need to consider both when estimating wear depth. The results suggest the framework can quickly estimate abrasion resistance and aid in evaluating fly ash concrete mixes. Instead of replacing traditional testing, it provides engineers with a practical tool for mixture assessment and durability analysis based on the existing database.

Keywords:

Materials Informatics, Sustainable Fly Ash Concrete, Wear Depth, Machine Learning, Artificial Neural Network, Durability Prediction

References

[1] Subedi, A., Kim, H., Lee, S.J., et al., 2025. Assessing Abrasion Resistance in Concrete Pavements: A Review. Applied Sciences. 15(4), 2101. DOI: https://doi.org/10.3390/app15042101

[2] Mahmood, W.I., Abdulrahman, P.I., Kakasor, D., et al., 2024. Multiscale modeling for accurate forecasting of concrete wear depth: A comprehensive study on mixture proportions and environmental factors. Multiscale and Multidisciplinary Modeling, Experiments and Design. 7(6), 5971–5989. DOI: https://doi.org/10.1007/s41939-024-00564-7

[3] Khan, A., Khan, M., Ali, M., et al., 2024. Predictive modeling for depth of wear of concrete modified with fly ash: A comparative analysis of genetic programming-based algorithms. Case Studies in Construction Materials. 20, e02744. DOI: https://doi.org/10.1016/J.CSCM.2023.E02744

[4] Amini, K., Vosoughi, P., Ceylan, H., et al., 2019. Effect of mixture proportions on concrete performance. Construction and Building Materials. 212, 77–84. DOI: https://doi.org/10.1016/J.CONBUILDMAT.2019.03.294

[5] Ayanlere, S.A., Ajamu, S.O., Odeyemi, S.O., et al., 2023. Effects of water-cement ratio on bond strength of concrete. Materials Today: Proceedings. 86, 134–139. DOI: https://doi.org/10.1016/J.MATPR.2023.04.686

[6] Shah, H.A., Yuan, Q., Zuo, S., 2021. Air entrainment in fresh concrete and its effects on hardened concrete-a review. Construction and Building Materials. 274, 121835. DOI: https://doi.org/10.1016/J.CONBUILDMAT.2020.121835

[7] Bediako, M., 2024. Superplasticized vs. Conventional Concrete: A Comparative Review. Materials Sciences and Applications. 15(9), 271–284. DOI: https://doi.org/10.4236/msa.2024.159019

[8] Cheng, D., Reiner, D.M., Yang, F., et al., 2023. Projecting future carbon emissions from cement production in developing countries. Nature Communications. 14(1), 8213. DOI: https://doi.org/10.1038/s41467-023-43660-x

[9] Hanifa, M., Agarwal, R., Sharma, U., et al., 2023. A review on CO2 capture and sequestration in the construction industry: Emerging approaches and commercialised technologies. Journal of CO2 Utilization. 67, 102292. DOI: https://doi.org/10.1016/J.JCOU.2022.102292

[10] Schneider, M., 2019. The cement industry on the way to a low-carbon future. Cement and Concrete Research. 124, 105792. DOI: https://doi.org/10.1016/J.CEMCONRES.2019.105792

[11] John, E., Lothenbach, B., 2023. Cement hydration mechanisms through time – a review. Journal of Materials Science. 58(24), 9805–9833. DOI: https://doi.org/10.1007/s10853-023-08651-9

[12] ASTM, 2019. ASTM C618M − 19. Standard Specification for Coal Fly Ash and Raw or Calcined Natural Pozzolan for Use in Concrete. ASTM: West Conshohocken, PA, USA. DOI: https://doi.org/10.1520/C0618-19

[13] Kanthe, V.N., Kulkarni, T.A., Padalkar, P.A., et al., 2024. Strength and Durability Performance of Fly Ash Concrete with and without Superplasticizer. Journal of Physics: Conference Series. 2779(1), 012001. DOI: https://doi.org/10.1088/1742-6596/2779/1/012001

[14] Amran, M., Fediuk, R., Murali, G., et al., 2021. Fly Ash-Based Eco-Efficient Concretes: A Comprehensive Review of the Short-Term Properties. Materials. 14(15), 4264. DOI: https://doi.org/10.3390/ma14154264

[15] Binod, K., Tike, G.K., Nanda, P.K., 2007. Evaluation of Properties of High-Volume Fly-Ash Concrete for Pavements. Journal of Materials in Civil Engineering. 19(10), 906–911. DOI: https://doi.org/10.1061/(ASCE)0899-1561(2007)19:10(906)

[16] Sumer, M., 2012. Compressive strength and sulfate resistance properties of concretes containing Class F and Class C fly ashes. Construction and Building Materials. 34, 531–536. DOI: https://doi.org/10.1016/J.CONBUILDMAT.2012.02.023

[17] Nayak, D.K., Abhilash, P.P., Singh, R., et al., 2022. Fly ash for sustainable construction: A review of fly ash concrete and its beneficial use case studies. Cleaner Materials. 6, 100143. DOI: https://doi.org/10.1016/j.clema.2022.100143

[18] Jiang, J., Lin, J., Jin, L., et al., 2026. Advancements in Machine Learning for the Development of Cementitious Composites Toward an Intelligent and Green Lifecycle: A State-of-the-Art Review. Engineering. in Press. DOI: https://doi.org/10.1016/J.ENG.2026.02.012

[19] Siddique, R., Aggarwal, P., Aggarwal, Y., 2011. Prediction of compressive strength of self-compacting concrete containing bottom ash using artificial neural networks. Advances in Engineering Software. 42(10), 780–786. DOI: https://doi.org/10.1016/J.ADVENGSOFT.2011.05.016

[20] Aiyer, B.G., Kim, D., Karingattikkal, N., et al., 2014. Prediction of compressive strength of self-compacting concrete using least square support vector machine and relevance vector machine. KSCE Journal of Civil Engineering. 18(6), 1753–1758. DOI: https://doi.org/10.1007/S12205-014-0524-0

[21] Sathiparan, N., Jeyananthan, P., 2023. Soft computing techniques to predict the compressive strength of groundnut shell ash-blended concrete. Journal of Engineering and Applied Science. 70(1), 134. DOI: https://doi.org/10.1186/s44147-023-00302-9

[22] Ziyad Sami, B.H., Ziyad Sami, B.F., Kumar, P., et al., 2023. Feasibility analysis for predicting the compressive and tensile strength of concrete using machine learning algorithms. Case Studies in Construction Materials. 18, e01893. DOI: https://doi.org/10.1016/J.CSCM.2023.E01893

[23] Moghaddas, S.A., Bao, Y., 2025. Explainable machine learning framework for predicting concrete abrasion depth. Case Studies in Construction Materials. 22, e04686. DOI: https://doi.org/10.1016/J.CSCM.2025.E04686

[24] Malazdrewicz, S., Sadowski, Ł., 2021. An intelligent model for the prediction of the depth of the wear of cementitious composite modified with high-calcium fly ash. Composite Structures. 259, 113234. DOI: https://doi.org/10.1016/J.COMPSTRUCT.2020.113234

[25] Merabti, S., Meziane, K., Rouabah, S., 2025. Prediction of Shrinkage in Waste Cork Cementitious Composites Using Multilayer Perceptron Neural Networks (MLP). Romanian Journal of Materials/Revista Română de Materiale. 55(3), 171.

[26] Bezari, S., Adda, A., Merabti, S., et al., 2025. Artificial Neural Network Model for Microclimate Performance of Solar Greenhouse with Thermal Storage. Thermal Science. 29(5A), 3603–3614.

[27] Siddique, R., Kapoor, K., Kadri, E.H., et al., 2012. Effect of polyester fibres on the compressive strength and abrasion resistance of HVFA concrete. Construction and Building Materials. 29, 270–278. DOI: https://doi.org/10.1016/J.CONBUILDMAT.2011.09.011

[28] Sargam, Y., Wang, K., Cho, I.H., 2021. Machine learning based prediction model for thermal conductivity of concrete. Journal of Building Engineering. 34, 101956. DOI: https://doi.org/10.1016/J.JOBE.2020.101956

[29] Ghorbanzadeh, S., Armaghani, D.J., Salimi, M., et al., 2026. Predictive models for dynamic properties of soils using machine learning approaches: A comprehensive review. Engineering Applications of Artificial Intelligence. 163, 113014. DOI: https://doi.org/10.1016/j.engappai.2025.113014

[30] Merabti, S., Bezari, S., Boudina, A., 2025. Prediction of the compressive strength in high-strength concrete cores through the destructive method. Sigma: Journal of Engineering & Natural Sciences/Mühendislik ve Fen Bilimleri Dergisi. 43(2), 541.

[31] Shah, M.I., Amin, M.N., Khan, K., et al., 2021. Performance Evaluation of Soft Computing for Modeling the Strength Properties of Waste Substitute Green Concrete. Sustainability. 13(5), 2867. DOI: https://doi.org/10.3390/su13052867

[32] Kakasor Ismael Jaf, D., Ismael Abdulrahman, P., Salih Mohammed, A., et al., 2023. Machine learning techniques and multi-scale models to evaluate the impact of silicon dioxide (SiO2) and calcium oxide (CaO) in fly ash on the compressive strength of green concrete. Construction and Building Materials. 400, 132604. DOI: https://doi.org/10.1016/J.CONBUILDMAT.2023.132604

[33] Fan, H., Xu, J., Armaghani, D.J., 2025. Addressing environmental challenges in blasting: A dual-method data generation framework for peak particle velocity prediction. Applied Soft Computing. 186(Part D), 114263.

[34] Akeed, M.H., Qaidi, S., Ahmed, H.U., et al., 2022. Ultra-high-performance fiber-reinforced concrete. Part III: Fresh and hardened properties. Case Studies in Construction Materials. 17, e01265. DOI: https://doi.org/10.1016/J.CSCM.2022.E01265

[35] Rai, B., Kumar, S., Satish, K., 2014. Effect of Fly Ash on Mortar Mixes with Quarry Dust as Fine Aggregate. Advances in Materials Science and Engineering. 2014(1), 626425. DOI: https://doi.org/10.1155/2014/626425

[36] Marangu, J.M., 2020. Prediction of Compressive Strength of Calcined Clay Based Cement Mortars Using Support Vector Machine and Artificial Neural Network Techniques. Journal of Sustainable Construction Materials and Technologies. 5(1), 392–398. DOI: https://doi.org/10.29187/jscmt.2020.43

[37] Sharaky, I.A., Ghoneim, S.S.M., Abdel Aziz, B.H., et al., 2021. Experimental and theoretical study on the compressive strength of the high strength concrete incorporating steel fiber and metakaolin. Structures. 31, 57–67. DOI: https://doi.org/10.1016/J.ISTRUC.2021.01.061

[38] Golafshani, E.M., Behnood, A., Arashpour, M., 2020. Predicting the compressive strength of normal and High-Performance Concretes using ANN and ANFIS hybridized with Grey Wolf Optimizer. Construction and Building Materials. 232, 117266. DOI: https://doi.org/10.1016/J.CONBUILDMAT.2019.117266

Downloads

Issue

2026 Vol.8 No.4 (In Progress)

Article Type

Article

License

Copyright © 2026 Payam Ismael Abdulrahman, Hemin Said Mohammed Amin, Ahmed Salih Mohammed

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.