Coupling Geotechnical Numerical Analysis with Machine Learning for Observational Method Projects

Amichai Mitelman, Beverly Yang, Alon Urlainis, Davide Elmo

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

In observational method projects in geotechnical engineering, the final geotechnical design is decided upon during actual construction, depending on the observed behavior of the ground. Hence, engineers must be prepared to make crucial decisions promptly, with few available guidelines. In this paper, we propose coupling numerical analysis with machine learning (ML) algorithms for enhancing the decision process in observational method projects. The proposed methodology consists of two main computational steps: (1) data generation, where multiple numerical models are automatically generated according to the anticipated range of input parameters, and (2) data analysis, where input parameters and model results are analyzed with ML models. Using the case study of the Semel tunnel in Tel Aviv, Israel, we demonstrate how this computational process can contribute to the success of observational method projects through (1) the computation of feature importance, which can assist with better identifying the key features that drive failure prior to project execution, (2) providing insights regarding the monitoring plan, as correlative relationships between various results can be tested, and (3) instantaneous predictions during construction.

Original languageEnglish
Article number196
JournalGeosciences (Switzerland)
Volume13
Issue number7
DOIs
StatePublished - Jul 2023

Keywords

  • geotechnical analysis
  • machine learning
  • numerical modeling
  • observational method
  • tunnel

Fingerprint

Dive into the research topics of 'Coupling Geotechnical Numerical Analysis with Machine Learning for Observational Method Projects'. Together they form a unique fingerprint.

Cite this