Machine Learning-Enhanced Analysis of Small-Strain Hardening Soil Model Parameters for Shallow Tunnels in Weak Soil

Accurate prediction of tunneling-induced settlements in shallow tunnels in weak soil is challenging, as advanced constitutive models, such as the small-strain hardening soil model (SS-HSM) require several input parameters. In this study, a case study was used as a benchmark to investigate the sensit...

Full description

Saved in:
Bibliographic Details
Main Authors: Tzuri Eilat, Alison McQuillan, Amichai Mitelman
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Geotechnics
Subjects:
Online Access:https://www.mdpi.com/2673-7094/5/2/26
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849472352028459008
author Tzuri Eilat
Alison McQuillan
Amichai Mitelman
author_facet Tzuri Eilat
Alison McQuillan
Amichai Mitelman
author_sort Tzuri Eilat
collection DOAJ
description Accurate prediction of tunneling-induced settlements in shallow tunnels in weak soil is challenging, as advanced constitutive models, such as the small-strain hardening soil model (SS-HSM) require several input parameters. In this study, a case study was used as a benchmark to investigate the sensitivity of the SS-HSM parameters. An automated framework was developed, and 100 finite-element (FE) models were generated, representing realistic input ranges and inter-parameter relationships. The resulting distribution of predicted surface settlements resembled observed outcomes, exhibiting a tightly clustered majority of small displacements (less than 20 mm) alongside a minority of widely scattered large displacements. Subsequently, machine-learning (ML) techniques were applied to enhance data interpretation and assess predictive capability. Regression models were used to predict final surface settlements based on partial excavation stages, highlighting the potential for improved decision-making during staged excavation projects. The regression models achieved only moderate accuracy, reflecting the challenges of precise displacement prediction. In contrast, binary classification models effectively distinguished between small displacements and large displacements. Arguably, classification models offer a more attainable approach that better aligns with geotechnical engineering practice, where identifying favorable and adverse geotechnical conditions is more critical than precise predictions.
format Article
id doaj-art-c420ce60f44944f78a3c184836bd19b1
institution Kabale University
issn 2673-7094
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Geotechnics
spelling doaj-art-c420ce60f44944f78a3c184836bd19b12025-08-20T03:24:33ZengMDPI AGGeotechnics2673-70942025-04-01522610.3390/geotechnics5020026Machine Learning-Enhanced Analysis of Small-Strain Hardening Soil Model Parameters for Shallow Tunnels in Weak SoilTzuri Eilat0Alison McQuillan1Amichai Mitelman2Department of Civil Engineering, Ariel University, Ariel 4077625, IsraelRocscience Inc., Toronto, ON M5T 1V1, CanadaDepartment of Civil Engineering, Ariel University, Ariel 4077625, IsraelAccurate prediction of tunneling-induced settlements in shallow tunnels in weak soil is challenging, as advanced constitutive models, such as the small-strain hardening soil model (SS-HSM) require several input parameters. In this study, a case study was used as a benchmark to investigate the sensitivity of the SS-HSM parameters. An automated framework was developed, and 100 finite-element (FE) models were generated, representing realistic input ranges and inter-parameter relationships. The resulting distribution of predicted surface settlements resembled observed outcomes, exhibiting a tightly clustered majority of small displacements (less than 20 mm) alongside a minority of widely scattered large displacements. Subsequently, machine-learning (ML) techniques were applied to enhance data interpretation and assess predictive capability. Regression models were used to predict final surface settlements based on partial excavation stages, highlighting the potential for improved decision-making during staged excavation projects. The regression models achieved only moderate accuracy, reflecting the challenges of precise displacement prediction. In contrast, binary classification models effectively distinguished between small displacements and large displacements. Arguably, classification models offer a more attainable approach that better aligns with geotechnical engineering practice, where identifying favorable and adverse geotechnical conditions is more critical than precise predictions.https://www.mdpi.com/2673-7094/5/2/26hardening soil modelshallow tunnelsmachine learningtunneling-induced settlementsfinite-element modellinggeotechnical engineering
spellingShingle Tzuri Eilat
Alison McQuillan
Amichai Mitelman
Machine Learning-Enhanced Analysis of Small-Strain Hardening Soil Model Parameters for Shallow Tunnels in Weak Soil
Geotechnics
hardening soil model
shallow tunnels
machine learning
tunneling-induced settlements
finite-element modelling
geotechnical engineering
title Machine Learning-Enhanced Analysis of Small-Strain Hardening Soil Model Parameters for Shallow Tunnels in Weak Soil
title_full Machine Learning-Enhanced Analysis of Small-Strain Hardening Soil Model Parameters for Shallow Tunnels in Weak Soil
title_fullStr Machine Learning-Enhanced Analysis of Small-Strain Hardening Soil Model Parameters for Shallow Tunnels in Weak Soil
title_full_unstemmed Machine Learning-Enhanced Analysis of Small-Strain Hardening Soil Model Parameters for Shallow Tunnels in Weak Soil
title_short Machine Learning-Enhanced Analysis of Small-Strain Hardening Soil Model Parameters for Shallow Tunnels in Weak Soil
title_sort machine learning enhanced analysis of small strain hardening soil model parameters for shallow tunnels in weak soil
topic hardening soil model
shallow tunnels
machine learning
tunneling-induced settlements
finite-element modelling
geotechnical engineering
url https://www.mdpi.com/2673-7094/5/2/26
work_keys_str_mv AT tzurieilat machinelearningenhancedanalysisofsmallstrainhardeningsoilmodelparametersforshallowtunnelsinweaksoil
AT alisonmcquillan machinelearningenhancedanalysisofsmallstrainhardeningsoilmodelparametersforshallowtunnelsinweaksoil
AT amichaimitelman machinelearningenhancedanalysisofsmallstrainhardeningsoilmodelparametersforshallowtunnelsinweaksoil