Comparative Evaluation of Random Forest and XGBoost for Bearing Capacity Prediction On Slopes

Authors

  • Rahmathiyah Amanda Departement of Civil Engineering, Faculty of Engineering, University of Bengkulu, Bengkulu 38371, Indonesia
  • Lindung Zalbuin Mase Departement Geotechnical Hazard Research Unit, Faculty of Engineering, University of Bengkulu, Bengkulu 3871, Indonesia
  • Aidil Fitriansyah Departement Geotechnical Hazard Research Unit, Faculty of Engineering, University of Bengkulu, Bengkulu 3871, Indonesia
  • Rena Misliniyati Departement Geotechnical Hazard Research Unit, Faculty of Engineering, University of Bengkulu, Bengkulu 3871, Indonesia
  • Muharram Nur Fikri Departement Geotechnical Hazard Research Unit, Faculty of Engineering, University of Bengkulu, Bengkulu 3871, Indonesia

DOI:

10.33395/sinkron.v10i4.16417

Keywords:

Random Forest, XGBoost, machine learning, ultimate bearing capacity, shallow foundations

Abstract

Predicting the ultimate bearing capacity of shallow foundations is crucial in geotechnical planning because it is directly related to the safety and stability of the structure. This is especially true for foundations located at the edge of a slope. However, conventional analytical methods often fail to capture the complex and nonlinear relationships between soil and foundation parameters. This study evaluates the performance of Random Forest (RF) and Extreme Gradient Boosting (XGBoost) ensemble machine learning models for predicting the ultimate bearing capacity (q_ult) of shallow foundations in non-cohesive soils on slopes, with emphasis on methodological rigor and physical model interpretability. The dataset consists of 393 secondary data points obtained from numerical modeling based on the Finite Element Method (FEM) in a previous study. Input variables include slope angle (sin β), foundation width (B), foundation depth (Df), and soil angle of internal friction (tan φ), while ultimate bearing capacity (qult) is used as the output variable. Model performance was evaluated using the coefficient of determination (R²), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and the A20 index.  Both models achieved a test R² of 0.97. XGBoost demonstrated superior generalization with a test RMSE of 7.130 kN/m² and MAPE of 8.833%, while Random Forest achieved a higher A20 index of 88.136% compared to 86.44% for XGBoost.

GS Cited Analysis

Downloads

Download data is not yet available.

References

El-emam, M., El Berizi, Y., Mabrouk, A. B., & Tabsh, S. W. (2023). Bearing capacity of strip footing on top of slope: Numerical parametric study. Ain Shams Engineering Journal, 14(11), 102522. https://doi.org/10.1016/j.asej.2023.102522

Ismail, A., & Kwon, S. (2023). Development of mathematically motivated hybrid soft computing models for improved predictions of ultimate bearing capacity of shallow foundations. Journal of Rock Mechanics and Geotechnical Engineering, 15(3), 747–759. https://doi.org/10.1016/j.jrmge.2022.04.005

Hamidi, A., & Abbeche, K. (2019). Bearing capacity of strip footing built on geogrid-reinforced sand over soft clay slope and subjected to a vertical load. Geotechnical and Geological Engineering, 19(1), 23–32.

Harle, S. M., & Wankhade, R. L. (2025). Machine learning techniques for predictive modelling in geotechnical engineering: A succinct review. Discover Civil Engineering. https://doi.org/10.1007/s44290-025-00224-w

As, M., & Subhiyakto, E. R. (2025). Performance comparison of Random Forest, SVM, and XGBoost algorithms with SMOTE for stunting prediction. Journal of Information Systems and Informatics, 9(4), 1163–1169.

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.

Çınar, Z. M., Nuhu, A. A., Zeeshan, Q., & Korhan, O. (2020). Machine learning in predictive maintenance towards sustainable smart manufacturing in Industry 4.0. Sustainability, 12(19), 8211.

Ma, L., Han, W., & Li, J. (2025). Machine learning based learning user behavior classification and recognition algorithm under multimodal data.

Moayedi, H., Mosallanezhad, M., Jusoh, W. A. W., Muazu, M. A., & others. (2020). A systematic review and meta-analysis of artificial neural network application in geotechnical engineering: Theory and applications. Neural Computing and Applications, 32(2), 495–518. https://doi.org/10.1007/s00521-019-04109-9

Liu, Y., & Liang, Y. (2024). Integrated machine learning for modeling bearing capacity of shallow foundations. Scientific Reports. https://doi.org/10.1038/s41598-024-58534-5

Baghbani, A., Choudhury, T., Costa, S., & Reiner, J. (2022). Application of artificial intelligence in geotechnical engineering: A state-of-the-art review. Earth-Science Reviews, 228, 103991. https://doi.org/10.1016/j.earscirev.2022.103991

Park, K., et al. (2025). Methodology for generating diverse geotechnical datasets using Monte Carlo simulation and genetic algorithms. Computer-Aided Civil and Infrastructure Engineering. https://doi.org/10.1111/mice.70106

Khajehzadeh, M., & Keawsawasvong, S. (2024). Artificial intelligence for bearing capacity evaluation of shallow foundation: An overview. Geotechnical and Geological Engineering, 42, 5401–5424. https://doi.org/10.1007/s10706-024-02863-9

El Gendy, M. (2025). A comparative machine and deep learning approach for predicting ultimate bearing capacity of shallow foundations in cohesionless soil. Scientific Reports. https://doi.org/10.1038/s41598-025-22812-7

Zhang, W., Gu, X., & Ou, Q. (2023). Bearing capacity and failure mechanism of strip footings lying on slopes subjected to various rainfall patterns and intensities. Geological Journal. https://doi.org/10.1002/gj.4882

Zhou, H., Hu, Q., Yu, X., Zheng, G., Liu, X., Xu, H., & Tian, K. (2023). Quantitative bearing capacity assessment of strip footings adjacent to two-layered slopes considering spatial soil variability. Acta Geotechnica. https://doi.org/10.1007/s11440-023-01875-8

Pantelidis, L. (2024). Bearing capacity of shallow foundations: A focus on the depth factors in combination with the respective N-factors. Arabian Journal of Geosciences. https://doi.org/10.1007/s12517-024-11976-7

Asteris, P. G., Skentou, A. D., Bardhan, A., Samui, P., & Pilakoutas, K. (2021). Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models. Cement and Concrete Research, 145, 106449. https://doi.org/10.1016/j.cemconres.2021.106449

Díaz, E., & Spagnoli, G. (2024). A super-learner machine learning model for a global prediction of compression index in clays. Applied Clay Science, 249, 107239. https://doi.org/10.1016/j.clay.2023.107239

Ismail, A., & Kwon, S. (2023). Development of mathematically motivated hybrid soft computing models for improved predictions of ultimate bearing capacity of shallow foundations. Journal of Rock Mechanics and Geotechnical Engineering, 15(3), 747–759. https://doi.org/10.1016/j.jrmge.2022.04.005

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324

Downloads


Crossmark Updates

How to Cite

Amanda, R., Zalbuin Mase, L. ., Fitriansyah, A., Misliniyati, R. ., & Nur Fikri, M. (2026). Comparative Evaluation of Random Forest and XGBoost for Bearing Capacity Prediction On Slopes. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 10(4). https://doi.org/10.33395/sinkron.v10i4.16417

Issue

Vol. 10 No. 4 (2026): Research Articles October 2026

Section

Articles

License

Copyright (c) 2026 Rahmathiyah Amanda, Lindung Zalbuin Mase, Aidil Fitriansyah, Rena Misliniyati, Muharram Nur Fikri

Creative Commons License

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

Crossref
Scopus
Google Scholar
Europe PMC