Developing a RFR Model to forecast the Rock-Socketed Piles' Ultimate Bearing Capacity

Fan  Liu; Xiongzhi  Peng; Kun  Li; Haowen  Yu; Pingyu  Su

doi:10.6180/jase.202603_29(4).0006

Developing a RFR Model to forecast the Rock-Socketed Piles' Ultimate Bearing Capacity

Civil Engineering Water Resources Engineering

Fan Liu¹, Xiongzhi Peng²This email address is being protected from spambots. You need JavaScript enabled to view it., Kun Li³, Haowen Yu², and Pingyu Su⁴

¹Inner Mongolia Hydrology and Water Resources Center, Hohhot, 010000, Inner Mongolia, China

²College of Civil Engineering, Southwest Jiaotong University, Chengdu 610031, Sichuan, China

³Engineering Department, Huilai Yihong Real Estate Development Co. LTD., Jieyang 522000, Guangdong, China

⁴Engineering Department, China Railway Real Estate Group Corporation Ltd., Chengdu 610031, Sichuan, China

Received: January 1, 2024
Accepted: May 8, 2025
Publication Date: July 27, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202603_29(4).0006

This investigation proposes a novel scheme to address the multifaceted challenges in anticipating the Ultimate Bearing Capacity of rock-socketed piles, which is crucial in rocky terrain foundation engineering. By integrating the Random Foreset Regression (RFR) model with two innovative meta-heuristic optimization tactics, namely the Reptile Search and the Wild Geese Schemes, this research offers unique contributions to forecasting modeling and data analysis. These schemes enhance the accuracy and efficacy of ML patterns through soft computing, aiming to fill a gap in the existing body of knowledge. The novelties of the present study are displayed by the original integration of meta-heuristic optimization tactics with ML tactics to improve the accuracy and efficacy of the prediction of Ultimate Bearing Capacity of rock-socketed piles, moving the state-of-the-art in foundation engineering. Based on the thorough assessment using performance indicators like R², RMSE, MSE, NRMSE, and the U95 index, the RFWG model, as proposed, shows outstanding performance, reaching a maximum R2 of 99.8% and a minimal RMSE of 513.86. In contrast, the single RFR model registered the weakest performance, with 97.8% for R² and 1625.02 for RMSE. These outcomes emphasize the effectiveness of RFWG in real-world scenarios and its promise in driving forward predictive modeling and data analysis within the foundation engineering context.

Keywords: Ultimate Bearing Capacity; Rock-Socketed Piles; Random Forest Regression; Reptile Search Algorithm; Wild Geese Algorithm

[1] M. A. Shahin, (2010)“Intelligent computing for modeling axial capacity of pile foundations "Canadian GeotechnicalJournal47:230–243. DOI: https: //doi.org/10.1139/T09-094.
[2] A.Poorjafar,M.Esmaeili-Falak,andH.Katebi,(2021) “Pile-soilinteraction determined by laterally loaded fixed headpilegroup"Geomechanics and Engineering26: 13–25. DOI: https: //doi.org/10.12989/gae.2021.26.1.013.
[3] G. G. Tejani, B. Sadaghat, and S. Kumar, (2023)“Predictthe maximum dry density of soil based on individual and hybrid methods of machinelearning "Advancesin engineeringandintelligencesystems2:95–106.DOI: 10.22034/aeis.2023.414188.1129.
[4] A.A. Jebur, W. Atherton, R. M. A. Khaddar, and E. Loffill,(2021)“Artificialneuralnetwork(ANN)approach for modelling of pilesettlement of open-ended steel piles subjected to compression load"European Journal of Environmental and Civil Engineering 25:429 451. DOI: https: //doi.org/10.1080/19648189.2018.1531269.
[5] E. Momeni, R. Nazir, D. J. Armaghani, and H. Maizir, (2014)“Prediction of pile bearing capacity using ahybrid genetical gorithm-based ANN "Measurement57:122 131. DOI: https: //doi.org/10.1016/j.measurement.2014.08.007.
[6] B. Sadaghat, A. J. Khiavi, B. Naeim, E. Khajavi, H. Sadaghat, and A. R. T. Khanghah, (2023)“The utilization of anaïvebayes model for predicting the energy consumption of buildings "Journal of Artificial Intelligence and System Modelling1:72–89. DOI:10.22034/jaism.2023.422292.1003.
[7] H. Harandizadeh, M. M. Toufigh, and V. Toufigh, (2019)“Application of improved ANFIS approaches to estimate bearing capacity of piles"Softcomputing23: 9537–9549. DOI: https: //doi.org/10.1007/s00500-018-3517-y.
[8] D. J. Armaghani, E. T. Mohamad, M. Hajihassani, S. Yagiz, and H. Motaghedi, (2016)“Application of several non-linear prediction tools for estimating uniaxial compressive strength of granitic rocks and comparison of their performances "Engineering with Computers 32: 189–206. DOI: https://doi.org/10.1007/s00366-015-0410-5.
[9] R.Singh,A.Kainthola,andT.N.Singh,(2012)“Estimation of elastic constant of rocks using an ANFIS approach"AppliedSoftComputing12:40–45.DOI: https: //doi.org/10.1016/j.asoc.2011.09.010.
[10] R. S. Faradonbeh, M. Monjezi, and D. J. Armaghani, (2016) “Genetic programing and non-linear multiple regression techniques to predict backbreak in blasting opera tion" Engineering with computers 32: 123–133. DOI: https: //doi.org/10.1007/s00366-015-0404-3.
[11] B. Ke, M. Khandelwal, P. G. Asteris, A. D. Skentou, A. Mamou,andD.J. Armaghani, (2021) “Rock-burst occurrence prediction based on optimized Naïve Bayes models" Ieee Access 9: 91347–91360. DOI: 10.1109/ACCESS.2021.3089205.
[12] R. Singh, V. Vishal, T. N. Singh, and P. G. Ranjith, (2013) “A comparative study of generalized regression neural network approach and adaptive neuro-fuzzy inference systems for prediction of unconfined compressive strength of rocks" Neural Computing and Applications 23: 499–506. DOI: https: //doi.org/10.1007/s00521-012-0944-z.
[13] S. Mahdevari, K. Shahriar, S. Yagiz, and M. A. Shirazi, (2014) “A support vector regression model for predicting tunnel boring machine penetration rates" International Journal of Rock Mechanics and Mining Sciences 72: 214–229. DOI: https: //doi.org/10.1016/j.ijrmms.2014.09.012.
[14] B. Ke, M. Khandelwal, P. G. Asteris, A. D. Skentou, A. Mamou, and D. J. Armaghani, (2021) “Rock-burst occurrence prediction based on optimized Naïve Bayes models" Ieee Access 9: 91347–91360. DOI: 10.1109/ACCESS.2021.3089205.
[15] H. Chen and L. Zhang, (2022) “A machine learning based method for predicting end-bearing capacity of rock socketed shafts" Rock Mechanics and Rock Engineering 55: 1743–1757. DOI: https: //doi.org/10.1007/s00603-021-02757-9.
[16] K.-j. Kim and H. Ahn, (2012) “A corporate credit rating model using multi-class support vector machines with an ordinal pairwise partitioning approach" Computers Operations Research 39: 1800–1811. DOI: https: //doi.org/10.1016/j.cor.2011.06.023.
[17] V. Vapnik. The nature of statistical learning theory. Springer science business media, 2013.
[18] J. A. K. Suykens and J. Vandewalle, (1999) “Least squares support vector machine classifiers" Neural processing letters 9: 293–300. DOI: https: //doi.org/10.1023/A:1018628609742.
[19] S. Wang, L. Yu, L. Tang, and S. Wang, (2011) “A novel seasonal decomposition based least squares support vector regression ensemble learning approach for hydropower consumption forecasting in China" Energy 36: 6542 6554. DOI: https: //doi.org/10.1016/j.energy.2011.09.010.
[20] M. A. Rad and M. S. Ayubirad, (2017) “Comparison of artificial neural network and coupled simulated annealing based least square support vector regression models for prediction of compressive strength of high-performance concrete" Scientia Iranica 24: 487–496. DOI: 10.24200/sci.2017.2412.
[21] G.Xie,S.Wang,Y.Zhao,andK.K.Lai,(2013)“Hybrid approaches based on LSSVR model for container through put forecasting: A comparative study" Applied Soft Computing 13: 2232–2241. DOI: https: //doi.org/10.1016/j.asoc.2013.02.002.
[22] X.XueandY.Wei,(2020) “A hybrid modelling approach for prediction of UCS of rock materials" Comptes Rendus. Mécanique 348: 235–243. DOI: 10.5802/crmeca.17.
[23] Y. Lei, S. Zhou, X. Luo, S. Niu, and N. Jiang, (2022) “A comparative study of six hybrid prediction models for uniaxial compressive strength of rock based on swarm intelligence optimization algorithms" Frontiers in Earth Science 10: 930130. DOI: https: //doi.org/10.3389/feart.2022.930130.
[24] D. J. Armaghani, R. S. N. S. B. R. Shoib, K. Faizi, and A.S. A.Rashid,(2017)“Developing a hybrid PSO–ANN model for estimating the ultimate bearing capacity of rock socketed piles" Neural Computing and Applications 28: 391–405. DOI: https: //doi.org/10.1007/s00521-015-2072-z.
[25] L. Breiman, (1984) “Classification and Regression Trees" The Wadsworth Brooks/Cole: DOI: https: //doi.org/10.1201/9781315139470.
[26] L. Breiman, (2001) “Random forests" Machine learning 45: 5–32. DOI: https: //doi.org/10.1023/A:1010933404324.
[27] V. Rodriguez-Galiano, M. Sanchez-Castillo, M. Chica Olmo, and M. Chica-Rivas, (2015) “Machine learning predictive models for mineral prospectivity: An evaluation of neural networks, random forest, regression trees and support vector machines" Ore geology reviews 71: 804 818. DOI: https: //doi.org/10.1016/j.oregeorev.2015.01.001.
[28] A. Liaw and M. Wiener, (2002) “Classification and regression by random Forest" R news 2: 18–22.
[29] L. Abualigah, M. A. Elaziz, P. Sumari, Z. W. Geem, and A. H. Gandomi, (2022) “Reptile Search Algorithm (RSA): A nature-inspired meta-heuristic optimizer" Ex pert Systems with Applications 191: 116158. DOI: https: //doi.org/10.1016/j.eswa.2021.116158.
[30] M. K. Khan, M. H. Zafar, S. Rashid, M. Mansoor, S. K. R. Moosavi, and F. Sanfilippo, (2023) “Improved reptile search optimization algorithm: application on regression and classification problems" Applied Sciences 13: 945. DOI: https: //doi.org/10.3390/app13020945.
[31] S. Mahdavi, M. E. Shiri, and S. Rahnamayan, (2015) “Metaheuristics in large-scale global continues optimization: A survey" Information Sciences 295: 407–428. DOI: https: //doi.org/10.1016/j.ins.2014.10.042.
[32] E. Momeni, D. J. Armaghani, S. A. Fatemi, and R. Nazir, (2018) “Prediction of bearing capacity of thin walled foundation: a simulation approach" Engineering with Computers 34: 319–327. DOI: https: //doi.org/10.1007/s00366-017-0542-x.
[33] T. A. Pham, V. Q. Tran, H.-L. T. Vu, and H.-B. Ly, (2020) “Design deep neural network architecture using a genetic algorithm for estimation of pile bearing capacity" PLoS One 15: e0243030. DOI: https: //doi.org/10.1371/journal.pone.0243030.
[34] E. Momeni, M. B. Dowlatshahi, F. Omidinasab, H. Maizir, and D. J. Armaghani, (2020) “Gaussian process regression technique to estimate the pile bearing capacity" Arabian Journal for Science and Engineering 45: 8255–8267. DOI: https: //doi.org/10.1007/s13369-020-04683-4.
[35] R. U. Kulkarni and D. M. Dewaikar, (2017) “Prediction of interpreted failure loads of rock-socketed piles in Mumbai Region using hybrid artificial neural networks with genetic algorithm" Int J Eng Res 6: 365–372. DOI: 10.17577/IJERTV6IS060196.
[36] D. Li, M.-R. Jiang, M.-W. Li, W.-C. Hong, and R.-Z. Xu, (2023) “A floating offshore platform motion forecasting approach based on EEMD hybrid Conv LSTM and chaotic quantum ALO" Applied Soft Computing 144: 110487. DOI: https: //doi.org/10.1016/j.asoc.2023.110487.