Assessing the shear strength of sandy soil reinforced with polyethylene-terephthalate: an AI-based approach

This research aimed to investigate the effectiveness of Polyethylene-Terephthalate (PET) as a reinforcement material for sandy soils in enhancing the shear strength. To achieve this, different concentrations of PET were tested, and 118 sets of data were collected. Parameters such as relative density...

Full description

Bibliographic Details
Main Authors: Samaei, Masoud, Alinejad Omran, Morteza, Keramati, Mohsen, Naderi, Reza, Shirani Faradonbeh, Roohollah
Format: Journal Article
Published: Springer Nature 2024
Online Access:http://hdl.handle.net/20.500.11937/95502
_version_ 1848766019024191488
author Samaei, Masoud
Alinejad Omran, Morteza
Keramati, Mohsen
Naderi, Reza
Shirani Faradonbeh, Roohollah
author_facet Samaei, Masoud
Alinejad Omran, Morteza
Keramati, Mohsen
Naderi, Reza
Shirani Faradonbeh, Roohollah
author_sort Samaei, Masoud
building Curtin Institutional Repository
collection Online Access
description This research aimed to investigate the effectiveness of Polyethylene-Terephthalate (PET) as a reinforcement material for sandy soils in enhancing the shear strength. To achieve this, different concentrations of PET were tested, and 118 sets of data were collected. Parameters such as relative density, normal stress in direct shear strength test, and types of PET elements (1 × 1, 1 × 5, and fiber) were also recorded. Subsequently, four decision tree-oriented machine learning (ML) methods—decision tree (DT), random forest (RF), AdaBoost, and XGBoost—were applied to construct models capable of forecasting enhancements in shear strength. The evaluation of these models' effectiveness was conducted using four established statistical metrics: R2, RMSE, VAF, and A-10. The results showed that AdaBoost results in the highest prediction accuracy among other algorithms, representing the high modelling performance of the algorithm in dealing with complex nonlinear problems. The conducted sensitivity analysis also revealed that relative density is the most crucial parameter for all the algorithms in predicting the output, followed by PET percentage and normal stress. Furthermore, to make the developed model in this study more practical and easy to use, a Graphical User Interface (GUI) was created, enabling the engineers and researchers to perform the analysis straightforwardly.
first_indexed 2025-11-14T11:44:29Z
format Journal Article
id curtin-20.500.11937-95502
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:44:29Z
publishDate 2024
publisher Springer Nature
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-955022024-08-30T02:26:19Z Assessing the shear strength of sandy soil reinforced with polyethylene-terephthalate: an AI-based approach Samaei, Masoud Alinejad Omran, Morteza Keramati, Mohsen Naderi, Reza Shirani Faradonbeh, Roohollah This research aimed to investigate the effectiveness of Polyethylene-Terephthalate (PET) as a reinforcement material for sandy soils in enhancing the shear strength. To achieve this, different concentrations of PET were tested, and 118 sets of data were collected. Parameters such as relative density, normal stress in direct shear strength test, and types of PET elements (1 × 1, 1 × 5, and fiber) were also recorded. Subsequently, four decision tree-oriented machine learning (ML) methods—decision tree (DT), random forest (RF), AdaBoost, and XGBoost—were applied to construct models capable of forecasting enhancements in shear strength. The evaluation of these models' effectiveness was conducted using four established statistical metrics: R2, RMSE, VAF, and A-10. The results showed that AdaBoost results in the highest prediction accuracy among other algorithms, representing the high modelling performance of the algorithm in dealing with complex nonlinear problems. The conducted sensitivity analysis also revealed that relative density is the most crucial parameter for all the algorithms in predicting the output, followed by PET percentage and normal stress. Furthermore, to make the developed model in this study more practical and easy to use, a Graphical User Interface (GUI) was created, enabling the engineers and researchers to perform the analysis straightforwardly. 2024 Journal Article http://hdl.handle.net/20.500.11937/95502 10.1007/s12145-024-01398-0 Springer Nature restricted
spellingShingle Samaei, Masoud
Alinejad Omran, Morteza
Keramati, Mohsen
Naderi, Reza
Shirani Faradonbeh, Roohollah
Assessing the shear strength of sandy soil reinforced with polyethylene-terephthalate: an AI-based approach
title Assessing the shear strength of sandy soil reinforced with polyethylene-terephthalate: an AI-based approach
title_full Assessing the shear strength of sandy soil reinforced with polyethylene-terephthalate: an AI-based approach
title_fullStr Assessing the shear strength of sandy soil reinforced with polyethylene-terephthalate: an AI-based approach
title_full_unstemmed Assessing the shear strength of sandy soil reinforced with polyethylene-terephthalate: an AI-based approach
title_short Assessing the shear strength of sandy soil reinforced with polyethylene-terephthalate: an AI-based approach
title_sort assessing the shear strength of sandy soil reinforced with polyethylene-terephthalate: an ai-based approach
url http://hdl.handle.net/20.500.11937/95502