Interpretable machine learning approach for TBM tunnel crown convergence prediction with Bayesian optimization

Accurate prediction of crown convergence in Tunnel Boring Machine (TBM) tunnels is critical for ensuring construction safety, optimizing support design, and improving construction efficiency. This study proposes an interpretable machine learning method based on Bayesian optimization (BO) and SHapley...

Full description

Saved in:
Bibliographic Details
Main Authors: Wanrui Hu, Kai Wu, Heng Liu, Weibang Luo, Xingxing Li, Peng Guan
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Earth Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/feart.2025.1608468/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849426690270298112
author Wanrui Hu
Kai Wu
Kai Wu
Heng Liu
Weibang Luo
Xingxing Li
Peng Guan
author_facet Wanrui Hu
Kai Wu
Kai Wu
Heng Liu
Weibang Luo
Xingxing Li
Peng Guan
author_sort Wanrui Hu
collection DOAJ
description Accurate prediction of crown convergence in Tunnel Boring Machine (TBM) tunnels is critical for ensuring construction safety, optimizing support design, and improving construction efficiency. This study proposes an interpretable machine learning method based on Bayesian optimization (BO) and SHapley Additive exPlanations (SHAP) for predicting crown convergence (CC) in TBM tunnels. Firstly, a dataset comprising 1,501 samples was constructed using tunnel engineering data. Then, six classical ML models, namely, Support Vector Regression, Decision Tree, Random Forest, Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting, and K-nearest neighbors—were developed, and BO was applied to tune the hyperparameters of each model to achieve accurate prediction of CC. Subsequently, the SHAP method was adopted to interpret the LightGBM model, quantifying the contribution of each input feature to the model’s predictions. The results indicate that the LightGBM model achieved the best prediction performance on the test set, with root mean squared error, mean absolute error, mean absolute percentage error, and determination coefficient values of 0.9122 mm, 0.6027 mm, 0.0644, and 0.9636, respectively; the average SHAP values for the six input features of the LightGBM model were ranked as follows: Time (0.1366) > Rock grade (0.0871) > Depth ratio (0.0528) > Still arch (0.0200) > Saturated compressive strength (0.0093) > Rock quality designation (0.0047). Validation using data from a TBM water conveyance tunnel in Xinjiang, China, confirmed the method’s practical utility, positioning it as an effective auxiliary tool for safer and more efficient TBM tunnel construction.
format Article
id doaj-art-3921fbafca2e463982793d9c00a0a27f
institution Kabale University
issn 2296-6463
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Earth Science
spelling doaj-art-3921fbafca2e463982793d9c00a0a27f2025-08-20T03:29:18ZengFrontiers Media S.A.Frontiers in Earth Science2296-64632025-06-011310.3389/feart.2025.16084681608468Interpretable machine learning approach for TBM tunnel crown convergence prediction with Bayesian optimizationWanrui Hu0Kai Wu1Kai Wu2Heng Liu3Weibang Luo4Xingxing Li5Peng Guan6CISPDR Corporation, Wuhan, ChinaHubei Shenlong Geological Engineering Investigation Institute Co., Ltd., Wuhan, ChinaFaculty of Engineering, China University of Geosciences, Wuhan, ChinaCISPDR Corporation, Wuhan, ChinaXinjiang Survey and Design Institute for Water Resources and Hydropower, Engineering Economics Institute, Urumqi, ChinaXinjiang Water Conservancy Development and Construction Group Co., Ltd., Urumqi, ChinaFaculty of Engineering, China University of Geosciences, Wuhan, ChinaAccurate prediction of crown convergence in Tunnel Boring Machine (TBM) tunnels is critical for ensuring construction safety, optimizing support design, and improving construction efficiency. This study proposes an interpretable machine learning method based on Bayesian optimization (BO) and SHapley Additive exPlanations (SHAP) for predicting crown convergence (CC) in TBM tunnels. Firstly, a dataset comprising 1,501 samples was constructed using tunnel engineering data. Then, six classical ML models, namely, Support Vector Regression, Decision Tree, Random Forest, Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting, and K-nearest neighbors—were developed, and BO was applied to tune the hyperparameters of each model to achieve accurate prediction of CC. Subsequently, the SHAP method was adopted to interpret the LightGBM model, quantifying the contribution of each input feature to the model’s predictions. The results indicate that the LightGBM model achieved the best prediction performance on the test set, with root mean squared error, mean absolute error, mean absolute percentage error, and determination coefficient values of 0.9122 mm, 0.6027 mm, 0.0644, and 0.9636, respectively; the average SHAP values for the six input features of the LightGBM model were ranked as follows: Time (0.1366) > Rock grade (0.0871) > Depth ratio (0.0528) > Still arch (0.0200) > Saturated compressive strength (0.0093) > Rock quality designation (0.0047). Validation using data from a TBM water conveyance tunnel in Xinjiang, China, confirmed the method’s practical utility, positioning it as an effective auxiliary tool for safer and more efficient TBM tunnel construction.https://www.frontiersin.org/articles/10.3389/feart.2025.1608468/fullTBM tunnelcrown convergence predictionmachine learningmodel explanationbayesian optimization
spellingShingle Wanrui Hu
Kai Wu
Kai Wu
Heng Liu
Weibang Luo
Xingxing Li
Peng Guan
Interpretable machine learning approach for TBM tunnel crown convergence prediction with Bayesian optimization
Frontiers in Earth Science
TBM tunnel
crown convergence prediction
machine learning
model explanation
bayesian optimization
title Interpretable machine learning approach for TBM tunnel crown convergence prediction with Bayesian optimization
title_full Interpretable machine learning approach for TBM tunnel crown convergence prediction with Bayesian optimization
title_fullStr Interpretable machine learning approach for TBM tunnel crown convergence prediction with Bayesian optimization
title_full_unstemmed Interpretable machine learning approach for TBM tunnel crown convergence prediction with Bayesian optimization
title_short Interpretable machine learning approach for TBM tunnel crown convergence prediction with Bayesian optimization
title_sort interpretable machine learning approach for tbm tunnel crown convergence prediction with bayesian optimization
topic TBM tunnel
crown convergence prediction
machine learning
model explanation
bayesian optimization
url https://www.frontiersin.org/articles/10.3389/feart.2025.1608468/full
work_keys_str_mv AT wanruihu interpretablemachinelearningapproachfortbmtunnelcrownconvergencepredictionwithbayesianoptimization
AT kaiwu interpretablemachinelearningapproachfortbmtunnelcrownconvergencepredictionwithbayesianoptimization
AT kaiwu interpretablemachinelearningapproachfortbmtunnelcrownconvergencepredictionwithbayesianoptimization
AT hengliu interpretablemachinelearningapproachfortbmtunnelcrownconvergencepredictionwithbayesianoptimization
AT weibangluo interpretablemachinelearningapproachfortbmtunnelcrownconvergencepredictionwithbayesianoptimization
AT xingxingli interpretablemachinelearningapproachfortbmtunnelcrownconvergencepredictionwithbayesianoptimization
AT pengguan interpretablemachinelearningapproachfortbmtunnelcrownconvergencepredictionwithbayesianoptimization