Developing advanced datadriven framework to predict the bearing capacity of piles on rock

Abstract Developing accurate predictive models for pile bearing capacity on rock is crucial for optimizing foundation design and ensuring structural stability. This research presents an advanced data-driven framework that integrates multiple machine learning algorithms to predict the bearing capacit...

Full description

Saved in:
Bibliographic Details
Main Authors: Kennedy C. Onyelowe, Shadi Hanandeh, Viroon Kamchoom, Ahmed M. Ebid, Fabián Danilo Reyes Silva, José Luis Allauca Palta, José Luis Llamuca Llamuca, Siva Avudaiappan
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-96186-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849734932520239104
author Kennedy C. Onyelowe
Shadi Hanandeh
Viroon Kamchoom
Ahmed M. Ebid
Fabián Danilo Reyes Silva
José Luis Allauca Palta
José Luis Llamuca Llamuca
Siva Avudaiappan
author_facet Kennedy C. Onyelowe
Shadi Hanandeh
Viroon Kamchoom
Ahmed M. Ebid
Fabián Danilo Reyes Silva
José Luis Allauca Palta
José Luis Llamuca Llamuca
Siva Avudaiappan
author_sort Kennedy C. Onyelowe
collection DOAJ
description Abstract Developing accurate predictive models for pile bearing capacity on rock is crucial for optimizing foundation design and ensuring structural stability. This research presents an advanced data-driven framework that integrates multiple machine learning algorithms to predict the bearing capacity of piles based on geotechnical and in-situ test parameters. A comprehensive dataset comprising key influencing factors such as pile dimensions, geological characteristics, and penetration resistance was utilized to train and validate various models, including Kstar, M5Rules, ElasticNet, XNV, and Decision Trees. The Taylor diagram and statistical evaluations demonstrated the superiority of the proposed models in capturing complex nonlinear relationships, with high correlation coefficients and low root mean square errors indicating robust predictive capabilities. Sensitivity analyses using Hoffman and Gardener’s approach and SHAP values identified the most influential parameters, revealing that penetration resistance, pile embedment depth, and geological conditions significantly impact pile capacity. The findings underscore the effectiveness of machine learning in geotechnical engineering applications, offering a reliable and efficient alternative to traditional empirical and analytical methods. The developed framework provides engineers and practitioners with a powerful tool for improving pile design accuracy, reducing uncertainties, and optimizing construction practices. Future research should focus on expanding the dataset with diverse geological conditions and exploring hybrid modeling techniques to enhance prediction accuracy further.
format Article
id doaj-art-54986e321e294b09b8fd4de444c413de
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-54986e321e294b09b8fd4de444c413de2025-08-20T03:07:40ZengNature PortfolioScientific Reports2045-23222025-04-0115112210.1038/s41598-025-96186-1Developing advanced datadriven framework to predict the bearing capacity of piles on rockKennedy C. Onyelowe0Shadi Hanandeh1Viroon Kamchoom2Ahmed M. Ebid3Fabián Danilo Reyes Silva4José Luis Allauca Palta5José Luis Llamuca Llamuca6Siva Avudaiappan7Department of Civil Engineering, College of Eng & Eng Technology, Michael Okpara University of AgricultureDepartment of Civil Engineering, Faculty of Engineering, Al-Balqa Applied UniversityExcellent Center for Green and Sustainable Infrastructure, Department of Civil Engineering, School of Engineering, King Mongkut’S Institute of Technology Ladkrabang (KMITL)Department of Civil Engineering, Faculty of Engineering, Future University in EgyptFacultad de Ciencias Pecuarias, Escuela Superior Politécnica de Chimborazo (ESPOCH)Instituto Superior Tecnológico General Eloy Alfaro (ISTGEA)Facultad de Administración de Empresas, Escuela Superior Politécnica de Chimborazo (ESPOCH)Departamento de Ciencias de la Construcción, Facultad de Ciencias de la Construcción Ordenamiento Territorial, Universidad Tecnológica MetropolitanaAbstract Developing accurate predictive models for pile bearing capacity on rock is crucial for optimizing foundation design and ensuring structural stability. This research presents an advanced data-driven framework that integrates multiple machine learning algorithms to predict the bearing capacity of piles based on geotechnical and in-situ test parameters. A comprehensive dataset comprising key influencing factors such as pile dimensions, geological characteristics, and penetration resistance was utilized to train and validate various models, including Kstar, M5Rules, ElasticNet, XNV, and Decision Trees. The Taylor diagram and statistical evaluations demonstrated the superiority of the proposed models in capturing complex nonlinear relationships, with high correlation coefficients and low root mean square errors indicating robust predictive capabilities. Sensitivity analyses using Hoffman and Gardener’s approach and SHAP values identified the most influential parameters, revealing that penetration resistance, pile embedment depth, and geological conditions significantly impact pile capacity. The findings underscore the effectiveness of machine learning in geotechnical engineering applications, offering a reliable and efficient alternative to traditional empirical and analytical methods. The developed framework provides engineers and practitioners with a powerful tool for improving pile design accuracy, reducing uncertainties, and optimizing construction practices. Future research should focus on expanding the dataset with diverse geological conditions and exploring hybrid modeling techniques to enhance prediction accuracy further.https://doi.org/10.1038/s41598-025-96186-1PilesRocksBearing capacityAdvanced machine learningFoundations
spellingShingle Kennedy C. Onyelowe
Shadi Hanandeh
Viroon Kamchoom
Ahmed M. Ebid
Fabián Danilo Reyes Silva
José Luis Allauca Palta
José Luis Llamuca Llamuca
Siva Avudaiappan
Developing advanced datadriven framework to predict the bearing capacity of piles on rock
Scientific Reports
Piles
Rocks
Bearing capacity
Advanced machine learning
Foundations
title Developing advanced datadriven framework to predict the bearing capacity of piles on rock
title_full Developing advanced datadriven framework to predict the bearing capacity of piles on rock
title_fullStr Developing advanced datadriven framework to predict the bearing capacity of piles on rock
title_full_unstemmed Developing advanced datadriven framework to predict the bearing capacity of piles on rock
title_short Developing advanced datadriven framework to predict the bearing capacity of piles on rock
title_sort developing advanced datadriven framework to predict the bearing capacity of piles on rock
topic Piles
Rocks
Bearing capacity
Advanced machine learning
Foundations
url https://doi.org/10.1038/s41598-025-96186-1
work_keys_str_mv AT kennedyconyelowe developingadvanceddatadrivenframeworktopredictthebearingcapacityofpilesonrock
AT shadihanandeh developingadvanceddatadrivenframeworktopredictthebearingcapacityofpilesonrock
AT viroonkamchoom developingadvanceddatadrivenframeworktopredictthebearingcapacityofpilesonrock
AT ahmedmebid developingadvanceddatadrivenframeworktopredictthebearingcapacityofpilesonrock
AT fabiandaniloreyessilva developingadvanceddatadrivenframeworktopredictthebearingcapacityofpilesonrock
AT joseluisallaucapalta developingadvanceddatadrivenframeworktopredictthebearingcapacityofpilesonrock
AT joseluisllamucallamuca developingadvanceddatadrivenframeworktopredictthebearingcapacityofpilesonrock
AT sivaavudaiappan developingadvanceddatadrivenframeworktopredictthebearingcapacityofpilesonrock