Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 29, 2026SensorsOpen Access

Deformation Prediction of Metro Deep Excavations Using CEEMDAN-IWT Denoising and BO-XGBoost

View Full Paper
Ask AI
Bookmark
Share

Authors

JZJing ZhaoLCLonghui ChenHYHongyin Yang

Discussion

Loading...

Member takes

Overview

Randomized trial evaluates deformation prediction for metro excavations, suggesting improved monitoring accuracy.

Key Points

  • This study aims to enhance the accuracy of surface settlement predictions during deep excavation projects using advanced denoising methods and machine learning.
  • Developed a joint denoising strategy using CEEMDAN, sample entropy, and improved wavelet threshold.
  • Implemented a Bayesian optimization-based extreme gradient boosting (BO-XGBoost) model for prediction.
  • Conducted experiments on data from a Wuhan metro deep excavation project to test the effectiveness of the methods.
  • The CEEMDAN-IWT method improved signal-to-noise ratio (SNR) by up to 4.09%.
  • Achieved a root mean square error (RMSE) of 0.09 mm with a mean absolute percentage error (MAPE) of 3.54% using the BO-XGBoost model.
  • Outperformed several baseline models including BP, LSTM, and standard XGBoost.

Cite This Study

Zhao et al. (2026) studied this question.

synapsesocial.com/papers/6a69a26dc8da07d9defa5d75https://doi.org/10.3390/s26154741
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A CEEMDAN–SVR–PSO-LSTM Hybrid Model for Construction-Induced Displacement Prediction of Metro Deep Excavations2026
  2. 2Hybrid Deep Learning Model for Accurate Settlement Forecasting of Metro Tracks under Canal Diversion Engineering2026
  3. 3Prediction model of land surface settlement deformation based on improved LSTM method: CEEMDAN-ICA-AM-LSTM (CIAL) prediction model2024 · 10 citations
  4. 4A Multi-Objective Prediction XGBoost Model for Predicting Ground Settlement, Station Settlement, and Pit Deformation Induced by Ultra-Deep Foundation Construction2024 · 7 citations
  5. 5Diaphragm-Wall Settlement Prediction and Relative Anomaly Screening for Deep Excavations Using Multi-Model Comparison and Intelligent Optimization2026