Investigation of Transfer Learning for Tunnel Support Design

Abstract

The potential of machine learning (ML) tools for enhancing geotechnical analysis has been recognized by several researchers. However, obtaining a sufficiently large digital dataset is a major technical challenge. This paper investigates the use of transfer learning, a powerful ML technique, used for overcoming dataset size limitations. The study examines two scenarios where transfer learning is applied to tunnel support analysis. The first scenario investigates transferring knowledge between a ground formation that has been well-studied to a new formation with very limited data. The second scenario is intended to investigate whether transferring knowledge is possible from a dataset that relies on simplified tunnel support analysis to a more complex and realistic analysis. The technical process for transfer learning involves training an Artificial Neural Network (ANN) on a large dataset and adding an extra layer to the model. The added layer is then trained on smaller datasets to fine-tune the model. The study demonstrates the effectiveness of transfer learning for both scenarios. On this basis, it is argued that, with further development and refinement, transfer learning could become a valuable tool for ML-related geotechnical applications.

Coupling Geotechnical Numerical Analysis with Machine Learning for Observational Method Projects

“…Tao et al [15] used a particle swarm optimization algorithm to increase the accuracy of a tunnel deformation analysis. Mitelman and Urlainis [16] used numerical data to demonstrate that learning can be transferred from different but similar data sets.…”

A Comprehensive Approach to Earthquake-Resilient Infrastructure: Integrating Maintenance with Seismic Fragility Curves

“…For instance, integrating machine-learning techniques such as artificial neural networks (ANNs) could assist in analyzing large empirical datasets and identifying key correlations, and coupling ML predictions with numerical analysis provides a means for the virtual validation of deterioration models [48,49]. Transferlearning methods may also help overcome limitations posed by small sample sizes [50]. Dabiri et al [51] developed ML-based models using decision trees, ANNs, and other techniques to predict the dispersion and median PGA parameters of building fragility curves.…”

Machine-Learning-Based Deformation Prediction Method for Deep Foundation-Pit Enclosure Structure

“…In addition, some studies demonstrate the growing interest in applying machine-learning techniques to geotechnical engineering, with a focus on prediction, classification, optimization, and risk assessment in various geotechnical applications [15]. Mitelman [16,17] uses transfer learning to overcome dataset size limitations in geotechnical analysis and combines data-value analysis with machine learning to enhance the decision-making process in observational method projects. Syed [16] used the open-source AutoML framework to construct different ML models for predicting the maximum ground settlement during the construction of soil pressure balance shield tunnels.…”

“…Mitelman [16,17] uses transfer learning to overcome dataset size limitations in geotechnical analysis and combines data-value analysis with machine learning to enhance the decision-making process in observational method projects. Syed [16] used the open-source AutoML framework to construct different ML models for predicting the maximum ground settlement during the construction of soil pressure balance shield tunnels.…”