Tunneling-induced settlement prediction using the hybrid feature selection method for feature optimization

Tunneling-induced ground settlement is influenced by a variety of features. In this article, a machine learning model is proposed to predict the ground settlement induced by shield tunneling. A hybrid feature selection method based on the importance degree of variables is first used to select the variables that are most significant to the settlement. Then, from the three perspectives of permutation importance, Sobol’s variance and Shapley additive explanations analysis, the influence of input features to output are quantified and the features are organically combined to construct the subsets for a random forest (RF) model. The monitoring data from a tunnel construction case across the Yellow River is used to evaluate this model. The variable importance measures (VIMs) based RF model with less variables than the original RF model shows a similar performance. Compared to the principal component analysis (PCA) based RF model, VIMs-based RF model shows a better performance while retaining the feature’s physical information, which is critical for future studies that continue to explore the explicit expression of settlement prediction.

• Record URL:
  • https://doi.org/10.1016/j.trgeo.2022.100808
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S2214391222000927
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/22143912
• Supplemental Notes:
  • © 2022 Published by Elsevier Ltd. Abstract reprinted with permission of Elsevier.
• Authors:
  • Cheng, Yang
  • Zhou, Wan-Huan
  • Xu, Tao
• Publication Date: 2022-9

Language

• English

Media Info

• Media Type: Web
• Features: Figures; References; Tables;
• Pagination: 100808
• Serial:
  • Transportation Geotechnics
  • Volume: 36
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 2214-3912
  • Serial URL: http://www.sciencedirect.com/science/journal/22143912

Subject/Index Terms

• TRT Terms: Ground settlement; Machine learning; Predictive models; Shielding (Tunneling)
• Geographic Terms: Yellow River (China)
• Subject Areas: Bridges and other structures; Geotechnology; Highways;

Filing Info

• Accession Number: 01858258
• Record Type: Publication
• Files: TRIS
• Created Date: Sep 20 2022 2:33PM