A pre-trained deep-learning surrogate model for slope stability analysis with spatial variability

Xu, H; He, X; Pradhan, B; Sheng, D

A pre-trained deep-learning surrogate model for slope stability analysis with spatial variability

Xu, H

He, X

Pradhan, B

Sheng, D

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Soils and Foundations, 2023, 63, (3), pp. 101321
Issue Date:: 2023-06-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (3.57 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Xu, H https://orcid.org/0000-0002-6556-8831
dc.contributor.author	He, X https://orcid.org/0000-0001-5336-3663
dc.contributor.author	Pradhan, B https://orcid.org/0000-0001-9863-2054
dc.contributor.author	Sheng, D https://orcid.org/0000-0002-1665-6931
dc.date.accessioned	2024-03-20T20:57:57Z
dc.date.available	2024-03-20T20:57:57Z
dc.date.issued	2023-06-01
dc.identifier.citation	Soils and Foundations, 2023, 63, (3), pp. 101321
dc.identifier.issn	0038-0806
dc.identifier.uri	http://hdl.handle.net/10453/176952
dc.description.abstract	This paper presents a pre-trained deep-learning surrogate model for the slope stability problem, which can be used to accelerate the stochastic analysis of slope stability with spatial variability. One major innovation is that the model is trained with a big dataset (>12000 data) covering common soil properties, spatial variabilities, and slope shapes such that the trained model is ready to make predictions without additional training or numerical simulations required. Other two minor contributions are: (1) special treatments for the irregular and varying boundaries of slopes and (2) novel techniques that allow the use of non-uniform mesh in data acquisitions. The proposed model is accurate with a mean-absolute-percentage-error of about 6% for the testing dataset. Seven cases of unseen data are also used to verify the model performance, including cases of different soil parameters, slope angles, and even different slope surfaces (e.g., concave and convex slopes, which are not used in training). The results show that the predict slope factor of safety is high consistent with the values from finite element simulations, and so is the obtained probability density functions. But the surrogate model takes much less computational effort (several minutes compared with hours of computing) – proving the effectiveness of our model for efficient stochastic analyses.
dc.language	en
dc.publisher	Elsevier
dc.relation.ispartof	Soils and Foundations
dc.relation.isbasedon	10.1016/j.sandf.2023.101321
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0503 Soil Sciences, 0905 Civil Engineering, 0999 Other Engineering
dc.subject.classification	Geological & Geomatics Engineering
dc.subject.classification	4005 Civil engineering
dc.subject.classification	4019 Resources engineering and extractive metallurgy
dc.subject.classification	4106 Soil sciences
dc.title	A pre-trained deep-learning surrogate model for slope stability analysis with spatial variability
dc.type	Journal Article
utslib.citation.volume	63
utslib.for	0503 Soil Sciences
utslib.for	0905 Civil Engineering
utslib.for	0999 Other Engineering
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Civil and Environmental Engineering
pubs.organisational-group	University of Technology Sydney/Strength - CAMGIS - Centre for Advanced Modelling and Geospatial lnformation Systems
utslib.copyright.status	open_access	*
dc.date.updated	2024-03-20T20:57:54Z
pubs.issue	3
pubs.publication-status	Published
pubs.volume	63
utslib.citation.issue	3

Abstract:

This paper presents a pre-trained deep-learning surrogate model for the slope stability problem, which can be used to accelerate the stochastic analysis of slope stability with spatial variability. One major innovation is that the model is trained with a big dataset (>12000 data) covering common soil properties, spatial variabilities, and slope shapes such that the trained model is ready to make predictions without additional training or numerical simulations required. Other two minor contributions are: (1) special treatments for the irregular and varying boundaries of slopes and (2) novel techniques that allow the use of non-uniform mesh in data acquisitions. The proposed model is accurate with a mean-absolute-percentage-error of about 6% for the testing dataset. Seven cases of unseen data are also used to verify the model performance, including cases of different soil parameters, slope angles, and even different slope surfaces (e.g., concave and convex slopes, which are not used in training). The results show that the predict slope factor of safety is high consistent with the values from finite element simulations, and so is the obtained probability density functions. But the surrogate model takes much less computational effort (several minutes compared with hours of computing) – proving the effectiveness of our model for efficient stochastic analyses.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/176952