Abstract
This study examines the prediction of the load-bearing capacity of closed and open-ended piles using machine learning (ML) methods. Full-scale load test results and CPT data are used to gather two comprehensive databases for such piles. ML models are developed employing input features associated with pile geometry and CPT resistances along with the ultimate bearing capacity being the only output feature. Following the training/testing sequences, the interpretability of ML predictions is examined through the Shapley and Joint Shapley value methods. Shapley values for multiple feature combinations allow ML models to decide the number of features necessary to make the most accurate predictions. Using updated input features, the models are rebuilt and predictions are repeated with the new input feature set; hence, the re-evaluation of ML models is focused on at this point. These features are twofold: One has two geometric features attributed to piles: cross-section area and length, and the other is a single feature attributed to soil, the average CPT tip resistance, which are overall sufficient in predicting the load capacity of both closed and open-ended piles. To the best of our knowledge, this study is one of the pioneers of its kind for pile foundations. The results show that the predictions of ML methods aided with strong interpretability techniques prove to be necessary in providing accurate results. As a result, Shapley is determined to be a useful tool for other geotechnical engineering applications as well.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are not publicly available due to the reason that proper permissions must be obtained from TUBITAK owning the data, which is funding this study. Upon such permission, the data will be available from the corresponding author upon reasonable request.
References
Alkroosh I, Nikraz H (2011) Correlation of pile axial capacity and CPT data using gene expression programming. Geotech Geol Eng 29(5):725–748. https://doi.org/10.1007/s10706-011-9413-1
Alkroosh I, Nikraz H (2012) Predicting axial capacity of driven piles in cohesive soils using intelligent computing. Eng Appl Artif Intell 25(3):618–627. https://doi.org/10.1016/j.engappai.2011.08.009
Alkroosh IS, Bahadori M, Nikraz H, Bahadori A (2015) Regressive approach for predicting bearing capacity of bored piles from cone penetration test data. J Rock Mech Geotech Eng 7(5):214. https://doi.org/10.1016/j.jrmge.2015.06.011
Altinok E (2021) Data-driven modeling of ultimate load capacity of closedand open-ended piles using machine learning. Master’s thesis, Istanbul Technical University, Turkey
Ardalan H, Eslami A, Nariman-Zadeh N (2009) Piles shaft capacity from CPT and CPTu data by polynomial neural networks and genetic algorithms. Comput Geotech 36(4):616–625. https://doi.org/10.1016/j.compgeo.2008.09.003
Armaghani D, Shoib RSNSBR, Faizi K, Rashid ASA (2017) Developing a hybrid PSO–ANN model for estimating the ultimate bearing capacity of rock-socketed piles. Neural Comput Appl 28(2):391–405. https://doi.org/10.1007/s00521-015-2072
Asghari V, Leung AY, Hsu MS (2020) Deep neural networks for prediction of undrained shear strength of clays. https://doi.org/10.3850/978-981-11-2725-0-ms2-4-cd
Breiman L (2001) Random forests. Mach Lear. https://doi.org/10.1023/A:1010933404324
Chakraborty D, Awolusi I, Gutierrez L (2021) An explainable machine learning model to predict and elucidate the compressive behavior of high-performance concrete. Res Eng. https://doi.org/10.1016/j.rineng.2021.100245
Chen W, Sarir P, Bui XN, Nguyen H, Tahir MM, Jahed Armaghani D (2020) Neuro-genetic, neuro-imperialism and genetic programing models in predicting ultimate bearing capacity of pile. Eng Comput. https://doi.org/10.1007/s00366-019-00752-x
Ebrahimian B, Movahed V (2017) Application of an evolutionary-based approach in evaluating pile bearing capacity using CPT results. Ships Offshore Struct 12(7):214. https://doi.org/10.1080/17445302.2015.1116243
Friedman JH (1999), Greedy function approximation: a gradient boosting machine. Technical Report, Department of Statistics, Stanford University.
Ghorbani B, Sadrossadat E, Bolouri Bazaz J, Rahimzadeh Oskooei P (2018) Numerical ANFIS-based formulation for prediction of the ultimate axial load bearing capacity of piles through CPT data. Geotech Geol Eng 36(4):245. https://doi.org/10.1007/s10706-018-0445-7
Harandizadeh H, Jahed Armaghani D, Khari M (2021) A new development of ANFIS–GMDH optimized by PSO to predict pile bearing capacity based on experimental datasets. Eng Comput 37:685–700. https://doi.org/10.1007/s00366-019-00849-3
Harris C, Pymar R, Rowat C (2022). Joint shapley values: a measure of joint feature importance. https://doi.org/10.48550/arXiv.2107.11357
Kannangara KKPM, Zhou W, Ding Z, Hng Z (2022) Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method. J Rock Mech Geotech Eng. https://doi.org/10.1016/J.JRMGE.2022.01.002
Kardani N, Zhou A, Nazem M, Shen SL (2020) Estimation of bearing capacity of piles in cohesionless soil using optimised machine learning approaches. Geotech Geol Eng 38(2):254. https://doi.org/10.1007/s10706-019-01085-8
Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Liu TY (2017) LightGBM: a highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems içinde.
Kiefa MAA (1998) General regression neural networks for driven piles in cohesionless soils. J Geotech Geoenviron Eng 124(12):1177–1185. https://doi.org/10.1061/(ASCE)1090-0241(1998)124:12(1177)
Kordjazi A, Pooya Nejad F, Jaksa MB (2014) Prediction of ultimate axial load-carrying capacity of piles using a support vector machine based on CPT data. Comput Geotech 55:91–102. https://doi.org/10.1016/j.compgeo.2013.08.001
Lee B-S (2021) A study of machine learning models to estimate a pile load capacity. J Korea Academia-Industrial Coop Soc 22(10):21. https://doi.org/10.5762/kais.2021.22.10.268
Lee IM, Lee JH (1996) Prediction of pile bearing capacity using artificial neural networks. Comput Geotech 18(3):189–200. https://doi.org/10.1016/0266-352X(95)00027-8
Liang M, Chang Z, Wan Z, Gan Y, Schlangen E, Šavija B (2022) Interpretable ensemble-machine-learning models for predicting creep behavior of concrete. Cement Concrete Compos. https://doi.org/10.1016/j.cemconcomp.2021.104295
Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. Adv Neural Inform Process Syst. https://doi.org/10.48550/arXiv.1705.07874
Luo Z, Hasanipanah M, Bakhshandeh Amnieh H, Brindhadevi K, Tahir MM (2021) GA-SVR: a novel hybrid data-driven model to simulate vertical load capacity of driven piles. Eng Comput. https://doi.org/10.1007/s00366-019-00858-2
Nasiri H, Homafar A, Chelgani SC (2021) Prediction of uniaxial compressive strength and modulus of elasticity for Travertine samples using an explainable artificial intelligence. Res Geophys Sci. https://doi.org/10.1016/j.ringps.2021.100034
Nguyen T-A, Ly H-B, Jaafari A, Pham TB (2020) Estimation of friction capacity of driven piles in clay using artificial neural network. Vietnam J Earth Sci 42(3):265–275. https://doi.org/10.15625/0866-7187/42/3/15182
Pal M, Deswal S (2010) Modelling pile capacity using Gaussian process regression. Comput Geotech. https://doi.org/10.1016/j.compgeo.2010.07.012
Pham TA, Tran VQ, Vu HLT, Ly HB (2020) Design deep neural network architecture using a genetic algorithm for estimation of pile bearing capacity. PLoS ONE. https://doi.org/10.1371/journal.pone.0243030
Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, ve Gulin A (2018) Catboost: unbiased boosting with categorical features. Advances in Neural Information Processing Systems içinde (C. 2018-December). https://doi.org/10.48550/arXiv.1706.09516
Sakib M, Inan K, Rahman I (2022) Integration of explainable artificial intelligence to identify significant landslide causal factors for extreme gradient boosting based landslide susceptibility mapping with improved feature selection. https://doi.org/10.48550/arXiv.2201.03225
Samui P (2008) Support vector machine applied to settlement of shallow foundations on cohesionless soils. Comput Geotech. https://doi.org/10.1016/j.compgeo.2007.06.014
Schalck C, Yankol-Schalck M (2021) Predicting French SME failures: new evidence from machine learning techniques. Appl Econ. https://doi.org/10.1080/00036846.2021.1934389
Shahin MA (2013) Artificial intelligence in geotechnical engineering. Metaheuristics in Water, Geotechnical and Transport Engineering içinde (ss. 169–204). Elsevier. https://doi.org/10.1016/B978-0-12-398296-4.00008-8
Teh CI, Wong KS, Goh ATC, Jaritngam S (1997) Prediction of pile capacity using neural networks. J Comput Civ Eng 11(2):129–138. https://doi.org/10.1061/(ASCE)0887-3801(1997)11:2(129)
Wang L, Wu J, Zhang W, Wang L, ve Cui, W. (2021) efficient seismic stability analysis of embankment slopes subjected to water level changes using gradient boosting algorithms. Front Earth Sci. https://doi.org/10.3389/feart.2021.807317
Acknowledgements
Authors would like to acknowledge the financial support of Scientific and Technological Council of Turkey (TÜBİTAK) through the research project with number 121M736.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Authors have no known conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Karakaş, S., Taşkın, G. & Ülker, M.B.C. Re-evaluation of machine learning models for predicting ultimate bearing capacity of piles through SHAP and Joint Shapley methods. Neural Comput & Applic 36, 697–715 (2024). https://doi.org/10.1007/s00521-023-09053-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-09053-3