Abstract
Addressing the intricacies of pile analysis and design poses a complex challenge, particularly in leveraging machine learning (ML) approaches to predict the ultimate load-bearing capacity of piles based on field trial data. This study focuses on develo** sophisticated ML prediction models tailored for calculating pile-bearing capacity (Pu). The foundation of this prediction model relies on the least square support vector regression (LSSVR) technique. A distinctive hybrid strategy is employed, combining the giant trevally optimizer (GTO) and flying foxes optimization (FFO) approaches. This unique amalgamation ensures precise and optimal prediction outcomes. The research relies on a meticulously curated dataset encompassing a diverse array of parameters related to piles and soil properties sourced from various literature. These datasets form the robust foundation for training, validating, and testing the models developed in this study. The implemented methodology has yielded remarkably accurate results, affirming the efficacy of the proposed models. This integration has led to the emergence of three hybrid models: LSFF, LSGT, and LSSVR. Particularly noteworthy is the exceptional performance of the LSFF model, demonstrating outstanding accuracy with an impressive R2 value of 0.993 and a minimal RMSE value of 32.916. These metrics underscore a notable achievement in the precise estimation of Pu, establishing the reliability and effectiveness of the approach taken in this research. The unique hybrid strategy, informed by diverse parameters, improves predictive capabilities, ensuring safer and more robust infrastructure projects by precisely understanding load-bearing capacities in different soil conditions.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Amjad M, Ahmad I, Ahmad M, Wróblewski P, Kamiński Pawełand Amjad U (2022) Prediction of pile bearing capacity using XGBoost algorithm: modeling and performance evaluation. Appl Sci 12(4):2126
Biswas R et al (2023) A novel integrated approach of RUNge Kutta optimizer and ANN for estimating the compressive strength of self-compacting concrete. Case Stud Constr Mater 18:e02163
Cao S-G, Liu Y-B, Wang Y-P (2008) A forecasting and forewarning model for methane hazard in working face of coal mine based on LS-SVM. J China Univ Min Technol 18(2):172–176
Chapman T, Marcetteau A (2004) Achieving economy and reliability in piled foundation design for a building project. Struct Eng 82(11):32–37
Chen Q (2023) "Predicting the settlement of pile based on a hybrid form of the model by considering Least Square Support Vector Regression. Multiscale Multidiscip Model Exp Design. https://doi.org/10.1007/s41939-023-00222-4
Chen W, Sarir P, Bui X-N, Nguyen H, Tahir MM, Armaghani DJ (2020) Neuro-genetic, neuro-imperialism, and genetic programming models in predicting the ultimate bearing capacity of the pile. Eng Comput 36:1101–1115
Coyle HM, Castello RR (1981) New design correlations for piles in sand. J Geotech Eng Div 107(7):965–986
Elsherbiny ZH, El Naggar MH (2013) Axial compressive capacity of helical piles from field tests and numerical study. Can Geotech J 50(12):1191–1203
Fletcher R (1987) Practical methods of optimization. Wiley, New York
Ghiasi MM, Shahdi A, Barati P, Arabloo M (2014) Robust modeling approach for estimation of compressibility factor in retrograde gas condensate systems. Ind Eng Chem Res 53(32):12872–12887
Gnananandarao T, Khatri VN, Dutta RK (2020) Bearing capacity and settlement prediction of multi-edge skirted footings resting on sand. Ing Investig 40(3):9–21
Gnananandarao T, Onyelowe KC, Dutta RK, Ebid AM (2023a) Sensitivity analysis and estimation of improved unsaturated soil plasticity index using SVM, M5P, and random forest regression. Artificial intelligence and machine learning in smart city planning. Elsevier, Amsterdam, pp 243–255
Gnananandarao T, Onyelowe KC, Murthy KSR (2023b) Experience in using sensitivity analysis and ANN for predicting the reinforced stone columns’ bearing capacity sited in soft clays. Artificial intelligence and machine learning in smart city planning. Elsevier, Amsterdam, pp 231–241
Gnananandarao T, Khatri VN, Onyelowe KC, Ebid AM (2023c) Implementing an ANN model and relative importance for predicting the under drained shear strength of fine-grained soil. Artificial intelligence and machine learning in smart city planning. Elsevier, Amsterdam, pp 267–277
Haupt RL, Haupt SE (2004) Practical genetic algorithms. Wiley, New York
Jordan MI, Mitchell TM (2015) Machine learning: trends, perspectives, and prospects. Science 349(6245):255–260
Kisi O (2015) Streamflow forecasting and estimation using least square support vector regression and adaptive neuro-fuzzy embedded fuzzy c-means clustering. Water Resour Manag 29:5109–5127
Kisi O, Parmar KS (2016) Application of least square support vector machine and multivariate adaptive regression spline models in long term prediction of river water pollution. J Hydrol (Amst) 534:104–112
Kordjazi A, Nejad FP, Jaksa MB (2014) Prediction of the ultimate axial load-carrying capacity of piles using a support vector machine based on CPT data. Comput Geotech 55:91–102
Kumar M, Kar IN (2009) Non-linear HVAC computations using least square support vector machines. Energy Convers Manag 50(6):1411–1418
Kumar M, Samui P (2022) Reliability analysis of pile foundation using GMDH, GP and MARS BT—CIGOS 2021. In: Ha-Minh C, Tang AM, Bui TQ, Vu XH, Huynh DVK (eds) Emerging technologies and applications for green infrastructure. Springer Nature, Singapore, pp 1151–1159
Kumar S, Tejani GG, Mirjalili S (2019) Modified symbiotic organisms search for structural optimization. Eng Comput 35(4):1269–1296
Kumar M, Bardhan A, Samui P, Hu JW, Kaloop MR (2021a) Reliability analysis of pile foundation using soft computing techniques: a comparative study. Processes 9(3):486
Kumar S, Tejani GG, Pholdee N, Bureerat S (2021b) Multi-objective passing vehicle search algorithm for structure optimization. Expert Syst Appl 169:114511
Kumar M et al (2022a) Hybrid ELM and MARS-based prediction model for bearing capacity of shallow foundation. Processes 10(5):1013
Kumar M, Biswas R, Kumar DR, Pradeep T, Samui P (2022b) Metaheuristic models for the prediction of bearing capacity of pile foundation. Geomech Eng 31(2):129
Kumar M, Kumar V, Rajagopal BG, Samui P, Burman A (2023a) State of art soft computing based simulation models for bearing capacity of pile foundation: a comparative study of hybrid ANNs and conventional models. Model Earth Syst Environ 9(2):2533–2551. https://doi.org/10.1007/s40808-022-01637-7
Kumar M, Biswas R, Kumar DR, Samui P, Kaloop MR, Eldessouki M (2023b) Soft computing-based prediction models for compressive strength of concrete. Case Stud Constr Mater 19:e02321
Liu Z, Jiang P, Wang J, Zhang L (2021) Ensemble forecasting system for short-term wind speed forecasting based on optimal sub-model selection and multi-objective version of mayfly optimization algorithm. Expert Syst Appl 177:114974
Mahmoodi NM, Arabloo M, Abdi J (2014) Laccase immobilized manganese ferrite nanoparticle: synthesis and LSSVM intelligent modeling of decolorization. Water Res 67:216–226
Meyerhof GG (1976) Bearing capacity and settlement of pile foundations. J Geotech Eng Div 102(3):197–228
Momeni E, Dowlatshahi MB, Omidinasab F, Maizir H, Armaghani DJ (2020) Gaussian process regression technique to estimate the pile bearing capacity. Arab J Sci Eng 45(10):8255–8267
Moreno-Salinas D, Chaos D, Besada-Portas E, López-Orozco JA, de la Cruz JM, Aranda J (2013) Semiphysical modeling of the nonlinear dynamics of a surface craft with LS-SVM. Math Probl Eng 2013
Nobile MS, Cazzaniga P, Besozzi D, Colombo R, Mauri G, Pasi G (2018) Fuzzy self-tuning PSO: a settings-free algorithm for global optimization. Swarm Evol Comput 39:70–85
Onyelowe KC, Gnananandarao T, Nwa-David C (2021) Sensitivity analysis and prediction of erodibility of treated unsaturated soil modified with nanostructured fines of quarry dust using novel artificial neural network. Nanotechnol Environ Eng 6(2):37. https://doi.org/10.1007/s41204-021-00131-2
Onyelowe KC, Gnananandarao T, Ebid AM (2022) Estimation of the erodibility of treated unsaturated lateritic soil using support vector machine-polynomial and-radial basis function and random forest regression techniques. Clean Mater 3:100039
Ozok AA (2009) Survey design and implementation in HCI. Human–computer interaction. CRC Press, Boca Raton, pp 269–288
Paik K, Salgado R (2003) Determination of bearing capacity of open-ended piles in sand. J Geotech Geoenviron Eng 129(1):46–57
Pham TA, Ly H-B, Tran VQ, Van Giap L, Vu H-LT, Duong H-AT (2020a) Prediction of pile axial bearing capacity using artificial neural network and random forest. Appl Sci 10(5):1871
Pham TA, Tran VQ, Vu H-LT, Ly H-B (2020b) Design deep neural network architecture using a genetic algorithm for estimation of pile bearing capacity. PLoSÂ One 15(12):e0243030
Randolph MF, Wroth CP (1978) Analysis of deformation of vertically loaded piles. J Geotech Eng Div 104(12):1465–1488
Sadeeq HT, Abdulazeez AM (2022) Giant trevally optimizer (GTO): a novel metaheuristic algorithm for global optimization and challenging engineering problems. IEEE Access 10:121615–121640
Samui P, Kim D (2013) Least square support vector machine and multivariate adaptive regression spline for modeling lateral load capacity of piles. Neural Comput Appl 23(3):1123–1127. https://doi.org/10.1007/s00521-012-1043-x
Schölkopf B (2022) Causality for machine learning. In: Probabilistic and causal inference: the works of Judea Pearl, pp 765–804
Sedaghat B, Tejani GG, Kumar S (2023) Predict the maximum dry density of soil based on individual and hybrid methods of machine learning. Adv Eng Intell Syst. https://doi.org/10.22034/aeis.2023.414188.1129
Shooshpasha I, Hasanzadeh A, Taghavi A (2013) Prediction of the axial bearing capacity of piles by SPT-based and numerical design methods. Geomate J 4(8):560–564
Suykens JAK, Vandewalle J (2000) Kisi, O. Streamflow forecasting and estimation using least square support vector r. IEEE Trans Circuits Syst I Fundam Theory Appl 47(7):1109–1114
Tsafarakis S, Zervoudakis K, Andronikidis A, Altsitsiadis E (2020) Fuzzy self-tuning differential evolution for optimal product line design. Eur J Oper Res 287(3):1161–1169
Zervoudakis K, Tsafarakis S (2022) A global optimizer inspired by the survival strategies of flying foxes. Eng Comput, 1–34
Zhang C, Nguyen GD, Einav I (2013) The end-bearing capacity of piles penetrating into crushable soils. Géotechnique 63(5):341–354
Zhou Z-H (2021) Machine learning. Springer Nature, Singapore
Author information
Authors and Affiliations
Contributions
Ling Chen: Writing—Original draft preparation, Conceptualization, Supervision, Project administration.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
Test dataset | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
D | DSE1 | DSE2 | DSE3 | PTE | Ge | EPTE | Pe | SPTs | SPTt | Pu |
300 | 3.4 | 5.2 | 0 | 3.4 | 3.4 | 3.4 | 12 | 8.6 | 6.73 | 559.8 |
400 | 3.85 | 7.3 | 0 | 2.95 | 3.68 | 3.58 | 14.1 | 11.15 | 7.08 | 1440 |
400 | 4.1 | 2.08 | 0 | 2.7 | 3.58 | 2.7 | 8.88 | 6.18 | 4.86 | 480 |
400 | 4.45 | 8 | 1.18 | 1.95 | 3.58 | 2 | 15.58 | 13.63 | 7.69 | 1032.4 |
300 | 3.4 | 5.2 | 0 | 3.4 | 3.4 | 3.4 | 12 | 8.6 | 6.73 | 559.8 |
300 | 3.4 | 5.2 | 0 | 3.4 | 3.43 | 3.43 | 12 | 8.6 | 6.73 | 661.6 |
300 | 3.4 | 5.25 | 0 | 3.4 | 3.46 | 3.41 | 12.05 | 8.65 | 6.75 | 407.2 |
400 | 3.45 | 8 | 0.22 | 2.95 | 3.57 | 2.95 | 14.62 | 11.67 | 7.53 | 1318 |
400 | 4.25 | 8 | 1.01 | 2.15 | 3.57 | 2.16 | 15.41 | 13.26 | 7.68 | 1248 |
400 | 3.4 | 7.3 | 0 | 3.4 | 3.5 | 3.4 | 14.1 | 10.7 | 7.28 | 958 |
400 | 4.1 | 2.2 | 0 | 2.7 | 3.72 | 2.72 | 9 | 6.3 | 4.94 | 610.7 |
400 | 4.35 | 8 | 1.02 | 2.05 | 3.47 | 4.05 | 15.42 | 13.37 | 7.64 | 1318 |
400 | 4.25 | 8 | 0.9 | 2.15 | 3.53 | 2.23 | 15.3 | 13.15 | 7.61 | 1395 |
400 | 4.25 | 8 | 0.4 | 2.15 | 3.59 | 2.79 | 14.8 | 12.65 | 7.32 | 1551 |
300 | 3.4 | 5.24 | 0 | 3.4 | 3.48 | 3.44 | 12.04 | 8.64 | 6.75 | 559.8 |
400 | 4.25 | 8 | 0.4 | 2.15 | 3.55 | 2.75 | 14.8 | 12.65 | 7.32 | 1392 |
300 | 3.4 | 5.25 | 0 | 3.4 | 3.46 | 3.41 | 12.05 | 8.65 | 6.75 | 661.6 |
400 | 4.05 | 8 | 0.7 | 2.35 | 3.47 | 2.37 | 15.1 | 12.75 | 7.58 | 1318 |
300 | 3.4 | 5.23 | 0 | 3.4 | 3.44 | 3.41 | 12.03 | 8.63 | 6.74 | 585.35 |
400 | 4.35 | 8 | 0.7 | 2.05 | 3.49 | 2.39 | 15.1 | 13.05 | 7.46 | 1392 |
400 | 4.25 | 8 | 1 | 2.15 | 3.57 | 2.17 | 15.4 | 13.25 | 7.67 | 1248 |
400 | 4.25 | 8 | 1 | 2.15 | 3.58 | 2.18 | 15.4 | 13.25 | 7.67 | 1395 |
400 | 4.25 | 8 | 1 | 2.15 | 3.56 | 2.16 | 15.4 | 13.25 | 7.67 | 1395 |
400 | 4.25 | 8 | 1.01 | 2.15 | 3.57 | 2.16 | 15.41 | 13.26 | 7.68 | 1248 |
400 | 4.25 | 8 | 0.1 | 2.15 | 3.53 | 3.03 | 14.5 | 12.35 | 7.14 | 1551 |
400 | 3.5 | 8 | 0.17 | 2.9 | 3.48 | 2.91 | 14.57 | 11.67 | 7.48 | 1056 |
400 | 4.25 | 8 | 1.02 | 2.15 | 3.58 | 2.16 | 15.42 | 13.27 | 7.68 | 1248 |
300 | 3.4 | 5.25 | 0 | 3.4 | 3.46 | 3.41 | 12.05 | 8.65 | 6.75 | 532.4 |
400 | 4.35 | 8 | 0.8 | 2.05 | 3.45 | 2.25 | 15.2 | 13.15 | 7.52 | 1392 |
300 | 3.4 | 5.2 | 0 | 3.4 | 3.45 | 3.45 | 12 | 8.6 | 6.73 | 610.7 |
400 | 4.25 | 8 | 0.98 | 2.15 | 3.54 | 2.16 | 15.38 | 13.23 | 7.66 | 1344 |
400 | 4.25 | 8 | 1 | 2.15 | 3.56 | 2.16 | 15.4 | 13.25 | 7.67 | 1344 |
400 | 3.45 | 8 | 0.25 | 2.95 | 3.6 | 2.95 | 14.65 | 11.7 | 7.55 | 960 |
400 | 4.65 | 7.24 | 0 | 2.15 | 3.54 | 3.5 | 14.04 | 11.89 | 6.76 | 1551 |
400 | 4.25 | 8 | 0.9 | 2.15 | 3.58 | 2.28 | 15.3 | 13.15 | 7.61 | 1395 |
400 | 3.4 | 7.3 | 0 | 3.4 | 3.5 | 3.4 | 14.1 | 10.7 | 7.28 | 900 |
400 | 3.4 | 7.4 | 0 | 3.4 | 3.61 | 3.41 | 14.2 | 10.8 | 7.3 | 1088.8 |
400 | 4.25 | 8 | 0.1 | 2.15 | 3.54 | 3.04 | 14.5 | 12.35 | 7.14 | 1551 |
400 | 3.4 | 7.23 | 0 | 3.4 | 3.43 | 3.4 | 14.03 | 10.63 | 7.26 | 960 |
300 | 3.4 | 5.3 | 0 | 3.4 | 3.52 | 3.42 | 12.1 | 8.7 | 6.76 | 610.7 |
400 | 4.1 | 2 | 0 | 2.7 | 3.55 | 2.75 | 8.8 | 6.1 | 4.8 | 610.7 |
400 | 4.25 | 8 | 1.03 | 2.15 | 3.58 | 2.15 | 15.43 | 13.28 | 7.69 | 1248 |
Test dataset | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
D | DSE1 | DSE2 | DSE3 | PTE | Ge | EPTE | Pe | SPTs | SPTt | Pu |
400 | 3.45 | 8 | 0.12 | 2.95 | 3.47 | 2.95 | 14.52 | 11.57 | 7.47 | 1318 |
400 | 4.25 | 8 | 1 | 2.15 | 3.58 | 2.18 | 15.4 | 13.25 | 7.67 | 1395 |
400 | 4.35 | 8 | 1.11 | 2.05 | 3.56 | 2.05 | 15.51 | 13.46 | 7.69 | 1128.6 |
400 | 4.45 | 7.21 | 0 | 2.35 | 3.41 | 2.4 | 14.01 | 11.66 | 6.83 | 1318 |
400 | 4.65 | 7.38 | 0 | 2.15 | 3.58 | 3.4 | 14.18 | 12.03 | 6.79 | 1551 |
400 | 4.25 | 8 | 1 | 2.15 | 3.56 | 2.16 | 15.4 | 13.25 | 7.67 | 1248 |
400 | 4.25 | 8 | 0.2 | 2.15 | 3.58 | 2.98 | 14.6 | 12.45 | 7.2 | 1551 |
400 | 4.65 | 7.6 | 0 | 2.15 | 3.58 | 3.18 | 14.4 | 12.25 | 6.84 | 1446 |
300 | 3.4 | 5.22 | 0 | 3.4 | 3.44 | 3.42 | 12.02 | 8.62 | 6.74 | 617 |
400 | 4.75 | 7.4 | 0 | 2.05 | 3.52 | 3.32 | 14.2 | 12.15 | 6.76 | 1425 |
400 | 4.65 | 7.4 | 0 | 2.15 | 3.59 | 3.39 | 14.2 | 12.05 | 6.8 | 1392 |
400 | 3.4 | 7.3 | 0 | 3.4 | 3.61 | 3.51 | 14.1 | 10.7 | 7.28 | 1115.2 |
300 | 3.4 | 5.25 | 0 | 3.4 | 3.49 | 3.44 | 12.05 | 8.65 | 6.75 | 559.8 |
300 | 3.4 | 5.25 | 0 | 3.4 | 3.46 | 3.41 | 12.05 | 8.65 | 6.75 | 559.8 |
400 | 4.25 | 8 | 1 | 2.15 | 3.58 | 2.18 | 15.4 | 13.25 | 7.67 | 1395 |
300 | 3.4 | 5.18 | 0 | 3.4 | 3.38 | 3.4 | 11.98 | 8.58 | 6.73 | 559.8 |
400 | 4.25 | 8 | 0.91 | 2.15 | 3.56 | 2.25 | 15.31 | 13.16 | 7.62 | 1473 |
400 | 4.05 | 8 | 0.7 | 2.35 | 3.48 | 2.38 | 15.1 | 12.75 | 7.58 | 1238 |
400 | 4.1 | 2.01 | 0 | 2.7 | 3.53 | 2.72 | 8.81 | 6.11 | 4.8 | 528 |
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
Chen, L. Predicting pile-bearing capacity utilizing least square support vector regression coupled with giant trevally optimizer and the flying foxes optimization. Multiscale and Multidiscip. Model. Exp. and Des. (2024). https://doi.org/10.1007/s41939-024-00430-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s41939-024-00430-6