Call For Paper - Upcoming Conferences
Research Article | Open Access | Download PDF
Volume 13 | Issue 4 | Year 2026 | Article Id. IJCE-V13I4P105 | DOI : https://doi.org/10.14445/23488352/IJCE-V13I4P105

Prediction of Fly Ash Concrete Compressive Strength using Machine Learning: A Data-Driven Study based on Indonesian Mix Designs

Riza Suwondo, Nunung Nurul Qomariyah, Militia Keintjem, Chee Fui Wong

Received Revised Accepted Published
06 Jan 2026 07 Feb 2026 06 Mar 2026 28 Apr 2026

Citation :

Riza Suwondo, Nunung Nurul Qomariyah, Militia Keintjem, Chee Fui Wong, "Prediction of Fly Ash Concrete Compressive Strength using Machine Learning: A Data-Driven Study based on Indonesian Mix Designs," International Journal of Civil Engineering, vol. 13, no. 4, pp. 63-72, 2026. Crossref, https://doi.org/10.14445/23488352/IJCE-V13I4P105

Abstract

Predicting the compressive strength of fly ash concrete plays a crucial role in achieving sustainable mix design and efficient feedback control. Unfortunately, conventional empirical approaches often limit the accuracy of nonlinear interactions between the material proportions and curing age. To address this challenge, this study developed a machine learning-based framework to predict the compressive strength of fly ash concrete using concrete mix data from Indonesia. A total of 250 mix compositions with varying material proportions and curing ages were used as datasets to train and deploy four models: Linear Regression (LR), Artificial Neural Network (ANN), Random Forest (RF), and Gradient Boosting (GB). The model performance was evaluated based on the coefficient of determination (R2), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) using cross-validation and independent testing. The study findings indicate that the nonlinear machine learning-based model significantly outperforms linear regression, confirming that nonlinearity dominates the strength-development process in fly ash concrete. Among the four models tested, gradient boosting performed the best in terms of overall prediction accuracy and generalisability across the strength range of the data. Residual analysis further indicated the absence of a systematic prediction bias. The findings highlight the potential of ensemble-based machine learning models to support preliminary mix design optimisation and construction quality control through reliable estimates of compressive strength.

Keywords

Fly ash concrete, Compressive strength prediction, Machine learning, Gradient boosting, Data-driven modelling.

References

  1. Yutao Bu et al., “Data-Driven Compressive Strength Estimation and Mix Optimization for Ultra-High-Performance Concrete,” Journal of Building Engineering, vol. 114, 2025.
    [CrossRef]  [Google Scholar] [Publisher Link]
  2. Qingqing Chen et al., “Compressive Strength Prediction of High-Performance Concrete: Integrating Multi-Ingredient Influences and Mix Proportion Insights,” Construction and Building Materials, vol. 451, 2024.
    [CrossRef]  [Google Scholar] [Publisher Link]
  3. Hai-Bang Ly, and Thuy-Anh Nguyen, “Enhancing Compressive Strength and Sustainability: A Machine Learning Approach to Recycled Brick and Tile Concrete Mix Design,” Materials Today Communication, vol. 40, 2024.
    [CrossRef]  [Google Scholar] [Publisher Link]
  4. Aslıhan Nida Derinpinar, Mehmet Burhan Karakoç, and Ahmet Özcan, “Performance of Glass Powder Substituted Slag based Geopolymer Concretes Under High Temperature,” Construction and Building Materials, vol. 331, 2022.
    [CrossRef]  [Google Scholar] [Publisher Link]
  5. Alaa M. Rashad, “A Brief on High-Volume Class F Fly Ash as Cement Replacement-A Guide for Civil Engineer,” International Journal of Sustainable Built Environment, vol. 4, no. 2, pp. 278-306, 2015.
    [CrossRef]  [Google Scholar] [Publisher Link]
  6. A. Fernández-Jiménez, A. Palomo, and M. Criado, “Microstructure Development of Alkali-Activated Fly Ash Cement: A Descriptive Model,” Cement and Concrete Research, vol. 35, no. 6, pp. 1204-1209, 2005.
    [CrossRef]  [Google Scholar] [Publisher Link]
  7. Meiri Triani, Kania Dewi, and Addina Shafiyya Ediansjah, “Prediction of Carbon Dioxide Emission from Electricity Generation in ASEAN,” Indonesian Journal of Urban and Environmental Technology, vol. 6, no. 1, pp. 20-35, 2023.
    [CrossRef]  [Google Scholar] [Publisher Link]
  8. Muhammad Sigit Darmawan et al., “Shear Strength of Geopolymer Concrete Beams using High Calcium Content Fly Ash in a Marine Environment,” Buildings, vol. 9, no. 4, pp. 1-13, 2019.
    [CrossRef]  [Google Scholar] [Publisher Link]
  9. M. Sigit Darmawan et al., “A Case Study of Low Compressive Strength of Concrete Containing Fly Ash in East Java Indonesia,” Procedia Engineering, vol. 125, pp. 579-586, 2015.
    [CrossRef]  [Google Scholar] [Publisher Link]
  10. Olivia P. Pfeiffer et al., “Bayesian Design of Concrete with Amortized Gaussian Processes and Multi-Objective Optimization,” Cement and Concrete Research, vol. 177, 2024.
    [CrossRef]  [Google Scholar] [Publisher Link]
  11.  Xianlin Wang et al., “Machine Learning for Design, Optimization and Assessment of Steel-Concrete Composite Structures: A Review,” Engineering Structures, vol. 328, 2025.
    [CrossRef]  [Google Scholar] [Publisher Link]
  12. Shiqi Wang et al., “Multi Objective Optimization of Recycled Aggregate Concrete based on Explainable Machine Learning,” Journal of Cleaner Production, vol. 445, 2024.
    [CrossRef]  [Google Scholar] [Publisher Link]
  13. Oğulcan Canbek et al., “Predicting the Rheology of Limestone Calcined Clay Cements (LC3): Linking Composition and Hydration Kinetics to Yield Stress Through Machine Learning,” Cement and Concrete Research, vol. 160, pp. 1-37, 2022.
    [CrossRef]  [Google Scholar] [Publisher Link]
  14. Chang Gao et al., “Creep Behavior Evaluation of Recycled Aggregate Concrete using Machine Learning Technology,” Journal of Building Engineering, vol. 99, 2025.
    [CrossRef]  [Google Scholar] [Publisher Link]
  15. Afshin Marani, Timileyin Oyinkanola, and Daman K. Panesar, “Probabilistic Deep Learning Prediction of Natural Carbonation of Low-Carbon Concrete Incorporating SCMs,” Cement and Concrete Composites, vol. 152, 2024.
    [CrossRef]  [Google Scholar] [Publisher Link]
  16. Pranjal Tamuly, and Vincenzo Naval, “Machine Learning based Conformal Predictors for Uncertainty-Aware Compressive Strength Estimation of Concrete,” Construction and Building Materials, vol. 487, pp. 1-13, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  17. Bin Chen et al., “Optimization of High-Performance Concrete Mix Ratio Design using Machine Learning,” Engineering Applications of Artificial Intelligence, vol. 122, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  18. Vuong Nguyen-Van et al., “Modelling of 3D Concrete Printing Process: A Perspective on Material and Structural Simulations,” Additive Manufacturing, vol. 61, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  19. Sai Yang et al., “Intelligent Multiobjective Optimization for High-Performance Concrete Mix Proportion Design: A Hybrid Machine Learning Approach,” Engineering Applications of Artificial Intelligence, vol. 126, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  20. Ahmed A. Alawi Al-Naghi et al., “Sustainable Optimisation of GGBS-based Concrete: De-Risking Mix Design Through Predictive Machine Learning Models,” Case Studies in Construction Materials, vol. 23, pp. 1-23, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  21. De-Cheng Feng et al., “Machine Learning-based Compressive Strength Prediction for Concrete: An Adaptive Boosting Approach,” Construction and Building Materials, vol. 230, pp. 1-20, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
  22. Mulusew Aderaw Getahun, Stanley Muse Shitote, and Zachary C. Abiero Gariy, “Artificial Neural Network based Modelling Approach for Strength Prediction of Concrete Incorporating Agricultural and Construction Wastes,” Construction and Building Materials, vol. 190, pp. 517-525, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
  23. Mohsin Ali Khan et al., “Compressive Strength of Fly-Ash-based Geopolymer Concrete by Gene Expression Programming and Random Forest,” Advances in Civil Engineering, vol. 2021, no. 1, pp. 1-17, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
  24. Asad S. Albostami, Rwayda Kh. S. Al-Hamd, and Ali Ammar Al-Matwari, “Data-Driven Predictive Modeling of Steel Slag Concrete Strength for Sustainable Construction,” Buildings, vol. 14, no. 8, pp. 1-25, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  25. Yassir M. Abbas, and Abdulaziz Alsaif, “Explainable Data-Driven Modeling for Optimized Mix Design of 3D-Printed Concrete: Interpreting Nonlinear Synergies among Binder Components and Proportions,” CMES - Computer Modeling in Engineering and Sciences, vol. 145, no. 2, pp. 1789-1819, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  26. M. Solikin, and T. Mulyanto, “Mechanical Properties of Self-Compacting Concrete Incorporated with High Volume Fly Ash,” IOP Conference Series: Materials Science and Engineering, vol. 821, no. 1, pp. 1-8, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
  27. Y. Sunarno et al., “Effect of Accelerators on High Early Strength Concrete (HESC) using High Volume Fly Ash,” IOP Conference Series: Earth and Environmental Science, vol. 1272, no. 1, pp. 1-7, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  28. Eva Arifi, Achfas Zacoeb, and Mitsuhiro Shigeishi, “Effect of Fly Ash on the Strength of Concrete Made from Recycle Aggregate by Pulsed Power,” International Journal of GEOMATE, vol. 7, no. 13, pp. 1009-1016, 2014.
    [Google Scholar] [Publisher Link]
  29. Stefanus A. Kristiawan, Agus Setiya Budi, and Andreas Nur Hadi, “Uniaxial Compressive Stress-Strain Behavior of Self-Compacting Concrete with High-Volume Fly Ash,” International Journal of GEOMATE, vol. 14, no. 41, pp. 77-85, 2018.
    [Google Scholar] [Publisher Link]
  30. Fahrizal Zulkarnain, Satrio Wibowo, and Mohd Zailan Sulieman, “Evaluating the Elastic Modulus of Geopolymer Concrete: The Impact of Fly Ash as a Cement Substitute using a No-Soaking Method for Sustainable Construction,” Journal of Advanced Research Design, vol. 126, no. 1, pp. 53-68, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  31. Y. Sunarno, “The Influence of Fly Ash Characteristics as a Supplementary Cementitious Material (SCM) on Concrete’s Mechanical Properties,” Materials Research Proceedings, vol. 48, pp. 587-596, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  32. Faroq Ali Ali Hussein Qazwan, “The Effect of Using Fly Ash as Supplementary Material on Conventional Concrete,” Diss, Universitas Islam Indonesia, 2024.
    [Google Scholar] [Publisher Link]
  33. Afippullah et al., “Comparison of the Use of Type V and Type I Cement with Fly Ash as Cementitious in Concrete Against Chloride Ion Penetration using the Accelerated Method,” Journal of Global Engineering Research and Science, vol. 2, no. 1, pp. 8-15, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  34. Fadhilah Muslim, and Rachmat Hermawan, “Mechanical Properties and Durability of Concrete Containing Indonesian Coal Fly Ash,” Civil Engineering and Architecture, vol. 13, no. 1, pp. 331-348, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  35. Yohans Sunarno, M. Wihardi Tjaronge, and A. Bakri Muhiddin, “Mechanical Properties of High-Volume Fly Ash Concrete with Varying Fly Ash Content,” ARPN Journal of Engineering and Applied Sciences, vol. 19, no. 16, pp. 1-7, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  36. D. Rantung, S.W.M. Supit, and S. Nicolaas, “Effects of Different Size of Fly Ash as Cement Replacement on Self-Compacting Concrete Properties,” Journal of Sustainable Engineering: Proceedings Series, pp. 180-186, 2019.
    [CrossRef] [Google Scholar]
  37. Yohans Sunarno et al., “Strength and Sustainability in Concrete: The Dual Role of Fly Ash and Accelerators in Reducing Environmental Impacts,” Engineering, Technology and Applied Science Research, vol. 15, no. 3, pp. 23260-23267, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  38. Yohans Sunarno et al., “Utilization of High-Volume Fly Ash as A Supplementary Cementitious Material in Environmentally Friendly Concrete,” Indonesian Journal of Urban and Environmental Technology, vol. 7, no. 1, pp. 106-118, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  39. Wahyuniarsih Sutrisno et al., “A Case Study of Concrete Incorporating High Volume Fly Ash and Bottom Ash for Sustainable Housing,” Civil Engineering and Architecture, vol. 12, no. 5, pp. 3179-3192, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
  40. M. Mujiburrakhman, and S. Widodo, “Study on Partial Replacement of Sand with Fly Ash in Concrete Mixes based on Pozzolanic Cementing Efficiency to the Strength-Weight and Cost-Strength Ratio,” Journal of Physics: Conference Series, vol. 1625, no. 1, pp. 1-11, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
  41. Maizuar et al., “Effect of Graphene Oxide on the Performance of Fly Ash Concrete Exposed to Ambient Temperature,” Civil Engineering Journal (Iran), vol. 11, no. 7, pp. 2736-2750, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  42. Ni Nyoman Kencanawati et al., “Properties of Concrete Containing Type-C Fly Ash Under Elevated Temperature,” Semesta Teknika, vol. 26, no. 2, pp. 194-202, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
  43. Mochamad Solikin et al., “Analysis of the use of Fly Ash Variations as a Partial Cement Substitute for Roller Compacted Concrete (RCC) Mixtures †,” Engineering Proceedings, vol. 84, no. 1, pp. 1-11, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
  44. Muhammad Iqbal Alfaroji et al., “The Effect of using Coal Fly Ash as a Fine Aggregate Substitute on the Compressive Strength of Concrete,” The South East Asian Journal of Advance Engineering and Technology, vol. 2, no. 2, pp. 43-47, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]