DEVELOPMENT OF A PYTHON-BASED MACHINE LEARNING MODEL FOR CALIFORNIA BEARING RATIO (CBR) PREDICTION
Keywords:
Python; Machine Learning; Random Forest Regression; California Bearing Ratio; Subgrade Soil.Abstract
The California Bearing Ratio (CBR) test is the most widely used method for evaluating subgrade strength and for the design of flexible pavements, but the standard soaked CBR procedure typically requires between four and five days to complete, a duration that can be a challenge when infrastructure must be delivered quickly. This study presents a Python-based machine learning approach for the indirect prediction of soaked CBR from index and compaction properties routinely measured in geotechnical practice. Geotechnical laboratory data comprising existing moisture content, liquid limit, plastic limit, plasticity index, percentage passing standard sieve sizes, optimum moisture content, maximum dry density, and specific gravity were compiled for 1,000 soil samples. The dataset was imported into Python using the pandas library and split into training (80%) and testing (20%) subsets. A random forest regression model was then trained to predict soaked CBR values from the remaining variables. On the test set, the model achieved a coefficient of determination (R²) of 0.957, a mean absolute error of 2.43, and a root mean square error of 3.255, indicating strong predictive performance. These results demonstrate that random-forest-based machine learning models can reliably estimate soaked CBR values without the time and material costs of conventional laboratory soaking, offering a practical complement to standard testing, particularly for time-constrained construction projects.References
Aderinola, O. S. (2017). Predicting the California bearing ratio value of low compressible clays with its index and compaction characteristics. International Journal of Scientific & Engineering Research, 8(5), 1460–1472.
Alawi, M. H., & Rajab, M. I. (2013). Prediction of California bearing ratio of subbase layer using multiple linear regression models. Road Materials and Pavement Design, 14(1), 211–219.
Baghbani, A., Nguyen, M. D., Alnedawi, A., Milne, N., Baumgartl, T., & Abuel-Naga, H. (2023). Improving soil stability with alum sludge: An AI-enabled approach for accurate prediction of California bearing ratio. Applied Sciences, 13(8), 4934.
Bardhan, A., Gokceoglu, C., Burman, A., Samui, P., & Asteris, P. G. (2021). Efficient computational techniques for predicting the California bearing ratio of soil in soaked conditions. Engineering Geology, 291, 106239.
Bayamack, J. F. N., Onana, V. L., Mvindi, A. T. N., Ze, A. N. O., Ohandja, H. N., & Eko, R. M. (2019). Assessment of the determination of Californian Bearing Ratio of laterites with contrasted geotechnical properties from simple physical parameters. Transportation Geotechnics, 19, 84–95.
Black, P. B. (1961). Design of flexible pavements using the California Bearing Ratio method. Highway Research Board.
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794.
Chu, X., Dawson, A., & Thom, N. (2021). Prediction of resilient modulus with consistency index for fine-grained soils. Transportation Geotechnics, 31, 100650.
Das, B. M. (2016). Principles of Geotechnical Engineering (9th ed.). Cengage Learning.
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232.
González Farias, I., Araujo, W., & Ruiz, G. (2018). Prediction of California bearing ratio from index properties of soils using parametric and non-parametric models. Geotechnical and Geological Engineering, 36(6), 3485–3498.
Ho, L. S., & Tran, V. Q. (2022). Machine learning approach for predicting and evaluating California bearing ratio of stabilized soil containing industrial waste. Journal of Cleaner Production, 370, 133587.
Kassa, S. M., & Wubineh, B. Z. (2023). Use of machine learning to predict California bearing ratio of soils. Advances in Civil Engineering, 2023, Article 8198648.
Kim, M., Ordu, S., Arslan, O., & Ko, J. (2023). Prediction of California bearing ratio (CBR) for coarse- and fine-grained soils using the GMDH-model. Geomechanics and Engineering, 33(2), 183–195.
Koech, B. K., Osano, S. N., & Nyete, A. M. (2025). Application of machine learning in estimating California bearing ratio from soil index properties in Kenya. East African Journal of Engineering, 8(1), 46–60.
Kurnaz, T. F., & Kaya, Y. (2019). Prediction of the California bearing ratio (CBR) of compacted soils by using a GMDH-type neural network. European Physical Journal Plus, 134, 326.
McKinney, W. (2010). Data structures for statistical computing in Python. Proceedings of the 9th Python in Science Conference, 51–56.
Othman, K., & Abdelwahab, H. (2023). The application of deep neural networks for the prediction of California Bearing Ratio of road subgrade soil. Ain Shams Engineering Journal, 14, 101988.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825–2830.
Rakaraddi, P. G., & Gomarsi, V. (2015). Establishing the relationship between CBR with different soil parameters. International Journal of Research in Engineering and Technology, 4(2), 182–188.
Rehman, A., Farooq, K., & Mujtaba, H. (2017). Prediction of California bearing ratio (CBR) and compaction characteristics of granular soils. Acta Geotechnica Slovenica, 14(1), 62–72.
Shirur, N. B., & Hiremath, S. G. (2014). Establishing relationship between CBR value and physical properties of soil. IOSR Journal of Mechanical and Civil Engineering, 11(5), 26–30.
Suthar, M., & Aggarwal, P. (2018). Predicting CBR value of stabilized pond ash with lime and lime sludge using ANN and MR models. International Journal of Geosynthetics and Ground Engineering, 4, 1–7.
Taha, S., Gabr, A., & El-Badawy, S. (2019). Regression and neural network models for California bearing ratio prediction of typical granular materials in Egypt. Arabian Journal for Science and Engineering, 44(10), 8691–8705.
Taskiran, T. (2010). Prediction of California bearing ratio (CBR) of fine grained soils by AI methods. Advances in Engineering Software, 41(6), 886–892.
Tenpe, A. R., & Patel, A. (2020). Application of genetic expression programming and artificial neural network for prediction of CBR. Road Materials and Pavement Design, 21(5), 1183–1200.
Yildirim, B., & Gunaydin, O. (2011). Estimation of California bearing ratio by using soft computing systems. Expert Systems with Applications, 38(5), 6381–6391.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 ADVANCED JOURNAL OF ENGINEERING AND SCIENTIFIC APPLICATIONS
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.