Developing hybrid XGBoost model integrated with entropy weight and Bayesian optimization for predicting tunnel squeezing intensity

Xiaojie Geng, Shunchuan Wu (), Yanjie Zhang, Junlong Sun, Haiyong Cheng (), Zhongxin Zhang and Shijiang Pu
Additional contact information
Xiaojie Geng: Kunming University of Science and Technology
Shunchuan Wu: Kunming University of Science and Technology
Yanjie Zhang: Yunnan Dianzhong Water Diversion Engineering Co., Ltd.
Junlong Sun: Kunming University of Science and Technology
Haiyong Cheng: Kunming University of Science and Technology
Zhongxin Zhang: Kunming University of Science and Technology
Shijiang Pu: Kunming University of Science and Technology

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, 2023, vol. 119, issue 1, No 29, 771 pages

Abstract: Abstract Tunnel squeezing, a significant deformation issue intimately tied to creep, poses a substantial threat to the safety and efficiency of tunnel construction. In this study, we employ a combination of the Bayesian Optimization (BO) algorithm and the Entropy Weight Method (EWM) to enhance the Extreme Gradient Boosting (XGBoost) model. This optimized model aims to predict tunnel squeezing intensity accurately, utilizing a dataset derived from 139 tunnel case histories. To extract the information encapsulated in the prediction indices, the EWM is initially used to pre-process the sample data, mitigating the impact of large differences in the input parameters’ values across various dimensions. Concurrently, the BO algorithm is applied to optimize the crucial hyperparameters of the XGBoost model, thereby effectively enhancing its performance. As part of this study, the Strength–Stress Ratio (SSR), Rock Mass Quality Index in the BQ system ([BQ]), Tunnel Diameter (D), and Support Stiffness (K) are selected as inputs for the tunnel squeezing estimation model. Within the study’s context, the prediction accuracy (Acc) and kappa coefficient (k) of the EWM-BO-XGBoost, XGBoost, BO-XGBoost, Evidence Theory (ET), Random Forest (RF), Support Vector Machine (SVM), and Decision Tree (DT) models are computed and compared. The results demonstrate that the Acc (91.7%) and k (0.89) of the EWM-BO-XGBoost model are the highest, attesting to its reliability and superiority over other alternatives. Furthermore, the analysis of the prediction indices’ feature importance reveals that the SSR contributes the most to the squeezing intensity, followed by the D and [BQ], while the K has the least effect on the squeezing intensity. This study can serve as a reference for predicting tunnel squeezing deformation and provide a research foundation for intelligent tunneling operations.

Keywords: Tunnel squeezing; Prediction model; Extreme gradient boosting (XGBoost); Entropy; Bayesian optimization (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s11069-023-06137-0 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:nathaz:v:119:y:2023:i:1:d:10.1007_s11069-023-06137-0

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11069

DOI: 10.1007/s11069-023-06137-0

Access Statistics for this article

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards is currently edited by Thomas Glade, Tad S. Murty and Vladimír Schenk

More articles in Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards from Springer, International Society for the Prevention and Mitigation of Natural Hazards
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().