Tunnel Boring Machines (TBMs) have become prevalent in tunnel construction due to their high efficiency and reliability. The proliferation of data obtained from site investigations and data acquisition systems provides an opportunity for the application of machine learning (ML) techniques. ML algorithms have been successfully applied in TBM tunnelling because they are particularly effective in capturing complex, non-linear relationships. This study focuses on commonly used ML techniques for TBM tunnelling, with a particular emphasis on data processing, algorithms, optimisation techniques, and evaluation metrics. The primary concerns in TBM applications are discussed, including predicting TBM performance, predicting surface settlement, and time series forecasting. This study reviews the current progress, identifies the challenges, and suggests future developments in the field of intelligent TBM tunnelling construction. This aims to contribute to the ongoing efforts in research and industry toward improving the safety, sustainability, and cost-effectiveness of underground excavation projects.

In traditional slope stability analysis, it is assumed that some “average” or appropriately “conservative” properties operate over the entire region of interest. This kind of deterministic conservative analysis often results in higher costs, and thus, a stochastic analysis considering uncertainty and spatial variability was developed to reduce costs. In the past few decades, machine learning has been greatly developed and extensively used in stochastic slope stability analysis, particularly used as surrogate models to improve computational efficiency. To better summarize the current application of machine learning and future research, this paper reviews 159 studies of supervised learning published in the past 20 years. The achievements of machine learning methods are summarized from two aspects—safety factor prediction and slope stability classification. Four potential research challenges and suggestions are also given.

Data-driven intelligent surrogate models gain popularity recently. Particularly in Monte-Carlo-style stochastic analysis, the influencing factors are considered as inputs, the quantities of interest are considered as outputs, and cheaper-to-evaluate surrogates models are built from a small amount of sample data and are used for the full Monte-Carlo analysis. This paper presents a framework with three innovations: (1) we build surrogate models for a particular problem that covers any possible material properties or boundary conditions commonly encountered in practice, so the models are ready to use, and do not require new data or training anymore. (2) The inputs and outputs to the problem are both spatially variable. Even after discretization, the input and output sizes are in the order of tens of thousands, which is challenging for traditional machine-learning algorithms. We take the footing failure mechanism as an example. Two types of neural networks are examined, fully connected networks and deep neural networks with complicated non-sequential structures (a modified U-Net). (3) This study is also the first attempt to use U-Nets as surrogate models for geotechnical problems. Results show that fully connected networks can fit well simple problems with a small input and output size, but fail for complex problems. Deep neural networks that account for the data structure give better results.

Rainfall-induced landslides represent a severe hazard around the world due to their sudden occurrence, as well as their widespread influence and runout distance. Considering the spatial variability of soil, stochastic analysis is often conducted to give a probability description of the runout. However, rainfall-induced landslides are complex and time-consuming for brute-force Monte Carlo analyses. Therefore, new methods are required to improve the efficiency of stochastic analysis. This paper presents a framework to investigate the influence and runout distance of rainfall-induced landslides with a two-step simulation approach. The complete process, from the initialization of instability to the post-failure flow, is simulated. The rainfall infiltration process and initialization of instability are first solved with a coupled hydro-mechanical finite element model. The post-failure flow is simulated using the coupled Eulerian–Lagrangian method, wherein the soil can flow freely in fixed Eulerian meshes. An equivalent-strength method is used to connect two steps by considering the effective stress of unsaturated soil. A rigorous method has been developed to accurately quantify the influence and runout distance via Eulerian analyses. Several simulations have been produced, using three-dimensional analyses to study the shapes of slopes and using stochastic analysis to consider uncertainty and the spatial variability of soils. It was found that a two-dimensional analysis assuming plain strain is generally conservative and safe in design, but care must be taken to interpret 2D results when the slope is convex in the longitudinal direction. The uncertainty and spatial variability of soils can lead to the statistic of influence and runout distance. The framework of using machine-learning models as surrogate models is effective in stochastic analysis of this problem and can greatly reduce computational effort.