Uncertainty‐guided U‐Net for soil boundary segmentation using Monte Carlo dropout

Tools

Zhou, X. and Sheil, B. and Suryasentana, S. and Shi, P. (2024) Uncertainty‐guided U‐Net for soil boundary segmentation using Monte Carlo dropout. Computer-Aided Civil and Infrastructure Engineering. ISSN 1467-8667 (https://doi.org/10.1111/mice.13396)

[thumbnail of Zhou-etal-CACIE-2024-Uncertainty-guided-U-net-for-soil-boundary-segmentation]
Preview
 Text. Filename: Zhou-etal-CACIE-2024-Uncertainty-guided-U-net-for-soil-boundary-segmentation.pdf
Final Published Version
License: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 logo
Download (6MB)| Preview

Abstract

Accurate soil stratification is essential for geotechnical engineering design. Owing to its effectiveness and efficiency, the cone penetration test (CPT) has been widely applied for subsurface stratigraphy, which relies heavily on empiricism for correlations to soil type. Recently, deep learning techniques have shown great promise in learning the relationship between CPT data and soil boundaries automatically. However, the segmentation of soil boundaries is fraught with model and measurement uncertainty. This paper introduces an uncertainty‐guided U((‐Net (UGU‐Net) for improved soil boundary segmentation. The UGU‐Net consists of three parts: (a) a Bayesian U‐Net to predict a pixel‐level uncertainty map, (b) reinforcement of original labels on the basis of the predicted uncertainty map, and (c) a traditional deterministic U‐Net, which is applied to the reinforced labels for final soil boundary segmentation. The results show that the proposed UGU‐Net outperforms the existing methods in terms of both high accuracy and low uncertainty. A sensitivity study is also conducted to explore the influence of key model parameters on model performance. The proposed method is validated by comparing the predicted subsurface profile with benchmark profiles. The code for this project is available at github.com/Xiaoqi‐Zhou‐suda/UGU‐Net.

ORCID iDs

Zhou, X., Sheil, B., Suryasentana, S. ORCID logoORCID: https://orcid.org/0000-0001-5460-5089 and Shi, P.;
  • Item type:Article
    ID code:91520
    Dates:
    Date
    Event
    8 December 2024
    Published
    8 December 2024
    Published Online
    1 December 2024
    Accepted
    4 January 2024
    Submitted
    Subjects:Science > Geology
    Department:Faculty of Engineering > Civil and Environmental Engineering
    Depositing user: Pure Administrator
    Date deposited:11 Dec 2024 16:03
    Last modified:18 Dec 2024 09:22
    URI:https://strathprints.strath.ac.uk/id/eprint/91520
CORE (COnnecting REpositories)