Author(s)

Linyuan Tang ¹

Affiliation(s)

¹ Department of Electronic Information and Computer Engineering, Engineering & Technical College of Chengdu University of Technology, Leshan, 614000, China

Corresponding Author

Linyuan Tang

ABSTRACT

In contemporary civil engineering, concrete stands as a preeminent construction material, with its compressive strength serving as a core parameter for the safety assessment of engineering structures. This study proposes constructing multiple integrated regression learning models for predictive analysis, supported by interpretable model frameworks to enhance the accuracy of predicting concrete compressive strength. Leveraging the public dataset from the Heywhale community, a comparative analysis of model architectures reveals that the CatBoost model demonstrates optimal comprehensive performance, achieving an R² value of 0.92. By employing the advanced SHAP-based DeepExplainer framework, it is identified that Age and Cement are the primary positive influencing factors. Correspondingly, a three-dimensional parameter optimization system is proposed. This approach not only shortens the testing cycle for concrete compressive strength and optimizes concrete mix design but also provides an efficient and convenient tool for real-time project quality monitoring.

KEYWORDS

Concrete compressive strength prediction; SHAP interpretable model analysis; CatBoost model; RF model; XGBR model

CITE THIS PAPER

Linyuan Tang, Machine Learning-Based Prediction of Concrete Compressive Strength and Interpretability Analysis. Journal of Civil Engineering and Urban Planning (2025) Vol. 7: 122-133. DOI: http://dx.doi.org/10.23977/jceup.2025.070217.

REFERENCES

[1] Shi Y , Li J , Zhang Y ,et al. Interpretable Machine Learning Method for Compressive Strength Prediction and Analysis of Pure Fly Ash-based Geopolymer Concrete[J]. Journal of Wuhan University of Technology-Mater. Sci. Ed.  2025, 40(1):65-78.DOI:10.1007/s11595-025-3041-8.
[2] Ouyang B. Concrete's Strength Prediction Using Machine Learning Method[J]. Engineering Computer, 2024, 000(000):138.
[3] Shahab M , Shakeel M , Gulaly L ,et al. Predicting the compressive strength of self-compacting concrete containing recycled aggregate and supplementary cementitious materials using machine learning techniques[J]. Progress in Engineering Science, 2025, 2(2). DOI:10.1016/j.pes.2025.100077.
[4] Jesse W ,Brennan B ,Marc M . Creating a Universal Depth-to-Load Conversion Technique for the Conterminous United States Using Random Forests[J].Journal of Cold Regions Engineering,2022,36(1).
[5] Ji Y ,Shang H ,Yi J , et al.Machine learning-based models to predict type 2 diabetes combined with coronary heart disease and feature analysis-based on interpretable SHAP[J]. Acta Diabetologica,2025, (prepublish):1-16.
[6] Yixiao Z ,Zhongguo Z ,Jianghua Z . CatBoost: A new approach for estimating daily reference crop evapotranspiration in arid and semi-arid regions of Northern China[J]. Journal of Hydrology,2020,588(prepublish)
[7] Geng C ,Chew W K ,Yeo S K , et al. Physically-based RF model for metal-oxide-metal capacitors[J]. Electronics Letters,2000,36(5):425-427.
[8] Zhang Y, Chen L, Tian Y. A Method for Evaluating the Interpretability of Machine Learning Models in Predicting Bond Default Risk Based on LIME and SHAP[J]. Progress in Computer Science, 2025.
[9] Celal C ,Yaren A ,Gebrail B , et al. Interpretable Predictive Modelling of Basalt Fiber Reinforced Concrete Splitting Tensile Strength Using Ensemble Machine Learning Methods and SHAP Approach.[J]. Materials (Basel, Switzerland),2023,16(13).
[10] Meiting Z ,Haichen G ,Yinghao X .Exploration of Teaching Reform in the Course of Concrete Structure Design Principles in the Context of the New Era[J]. World Journal of Educational Research,2024,11(6).

Sponsors, Associates, and Links

---

• Journal of Sustainable Development and Green Buildings
  
  
• Landscape and Urban Horticulture
  
  
• Bridge and Structural Engineering
  
  
• Soil Mechanics and Geotechnical Engineering
  
  
• Journal of Municipal Engineering
  
  
• Heating, Ventilation and Air Conditioning
  
  
• Indoor Air Quality and Climate
  
  
• Computer Aided Architecture Design