TU Darmstadt / ULB / TUprints

Influence of Sampling Methods on the Accuracy of Machine Learning Predictions Used for Strain-Dependent Slope Stability

Shakya, Sudan ; Schmüdderich, Christoph ; Machaček, Jan ; Prada-Sarmiento, Luis Felipe ; Wichtmann, Torsten (2024)
Influence of Sampling Methods on the Accuracy of Machine Learning Predictions Used for Strain-Dependent Slope Stability.
In: Geosciences, 2024, 14 (2)
doi: 10.26083/tuprints-00027161
Article, Secondary publication, Publisher's Version

[img] Text
geosciences-14-00044.pdf
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (23MB)
Item Type: Article
Type of entry: Secondary publication
Title: Influence of Sampling Methods on the Accuracy of Machine Learning Predictions Used for Strain-Dependent Slope Stability
Language: English
Date: 14 May 2024
Place of Publication: Darmstadt
Year of primary publication: 5 February 2024
Place of primary publication: Basel
Publisher: MDPI
Journal or Publication Title: Geosciences
Volume of the journal: 14
Issue Number: 2
Collation: 23 Seiten
DOI: 10.26083/tuprints-00027161
Corresponding Links:
Origin: Secondary publication DeepGreen
Abstract:

Supervised machine learning (ML) techniques have been widely used in various geotechnical applications. While much attention is given to the ML techniques and the specific geotechnical problem being addressed, the influence of sampling methods on ML performance has received relatively less scrutiny. This study applies supervised ML to the strain-dependent slope stability (SDSS) method for the prediction of the factor of safety (FoS) using hypoplasticity. It delves into different sampling strategies for training the ML model, emphasizing predictions of soil behavior in lower stress ranges. A novel sampling method is introduced to ensure a more representative distribution of samples in these ranges, which is challenging to achieve through traditional sampling approaches. The ML models were trained using traditional and modified sampling methods. Subsequently, slope stability analyses using SDSS were conducted with ML models trained from six different sampling methods. The results illustrate the impact of sampling methods on the FoS. Besides a noticeable improvement in predictions of shear stresses within the lower stress ranges, a decisive effect on the overall FoS was observed as well.

Uncontrolled Keywords: machine learning, hypoplasticity, sampling, strain-dependent slope stability
Identification Number: Artikel-ID: 44
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-271616
Additional Information:

This article belongs to the Special Issue Benchmarks of AI in Geotechnics and Tunnelling

Classification DDC: 000 Generalities, computers, information > 004 Computer science
500 Science and mathematics > 550 Earth sciences and geology
600 Technology, medicine, applied sciences > 624 Civil engineering and environmental protection engineering
Divisions: 13 Department of Civil and Environmental Engineering Sciences > Institute of Geotechnics
Date Deposited: 14 May 2024 13:42
Last Modified: 23 Sep 2024 06:18
SWORD Depositor: Deep Green
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/27161
PPN: 521640504
Export:
Actions (login required)
View Item View Item