Tunnelling and Underground Space Technology · 2024 · 16 citations · 23 references
EngineeringCivil EngineeringGeological EngineeringEngineering GeologyMachine LearningTunnel EngineeringRock ClassificationTunnel DesignTunnel GeologyTunnelingUnderground Excavation MethodsComputational ReproducibilityMethod ReproducibilityModel Performance AnalysisModel Performance EvaluationPredictive Model PerformanceReproducibility StudiesRock Type ClassificationTunnels
• Predicting ten rock types from MWD-data before tunnelling using ML on tabular data. • Comparison of models for near similar- with major groups of rock types. • Comparison of performance in geologic transition zones with regular zones. • Comparison of performance using all or only dependent MWD-parameters. • An ML process emphasising result reproducibility and trustworthiness. Despite the increasing global usage of Measure While Drilling (MWD) data in tunnel projects, the application of machine learning (ML) techniques for real-time rock type prediction still needs to be explored. This paper introduces a novel ML approach to predict rock types in advance of the tunnel face using MWD data. Drawing on a diverse dataset of 4986 samples from 15 Norwegian tunnels, this study employed a pipeline including the LightGBM machine learning algorithm to forecast rock types 3–6 m ahead of excavation, achieving a balanced accuracy of 0.96 for six primary rock types using all 48 MWD-features. A more challenging label configuration with ten classes of near similar rock types, aimed to test the outer boundaries of model performance, achieved a score of 0.87. Performance in geologic transition zones is compared to regular zones. Notably, this capability facilitates proactive logistics for excavated rock material reuse and rock engineering strategies. Data leakage and reproducibility challenges in ML-based research are addressed in a step-by-step approach, and comparisons are drawn between digital and conventional scientific experimentation.
23
Scikit-learn: Machine Learning in Python
Fabián Pedregosa, Gaël Varoquaux, Alexandre Gramfort et al. · arXiv (Cornell University) · 2012 · 63.7K citations · Full text
SMOTE: Synthetic Minority Over-sampling Technique
Nitesh V. Chawla, Kevin W. Bowyer, Lawrence Hall et al. · Journal of Artificial Intelligence Research · 2002 · 31.2K citations · Full text
An introduction to ROC analysis
Tom Fawcett · Pattern Recognition Letters · 2005 · 21.3K citations
LightGBM: A Highly Efficient Gradient Boosting Decision Tree
Guolin Ke, Qi Meng, Thomas Finley et al. · HAL (Le Centre pour la Communication Scientifique Directe) · 2017 · 9.5K citations · Full text