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.

At the initial phases of tunnel design, information on rock properties is often limited. In such instances, the engineering classification of the rock is recommended as a primary assessment of its geotechnical condition. This paper reviews different rock mass classification methods in the tunnel industry. First, some important considerations for the classification of rock are discussed, such as rock quality designation (RQD), uniaxial compressive strength (UCS) and groundwater condition. Traditional rock classification methods are then assessed, including the rock structure rating (RSR), rock mass rating (RMR), rock mass index (RMI), geological strength index (GSI) and tunnelling quality index (Q system). As RMR and the Q system are two commonly used methods, the relationships between them are summarized and explored. Subsequently, we introduce the detailed application of artificial intelligence (AI) method on rock classification. The advantages and limitations of traditional methods and artificial intelligence (AI) methods are indicated, and their application scopes are clarified. Finally, we provide suggestions for the selection of rock classification methods and prospect the possible future research trends.

Particle segregation is a widespread phenomenon in nature. Vertical vibration systems have been a focal point in studying particle segregation, providing valuable insights into the mechanisms and patterns that influence this process. However, despite extensive research on the mechanisms and patterns of particle separation, the consequences, particularly the mechanical properties of samples resulting from particle segregation, remain less understood. This study aims to investigate the segregation process of a binary mixture under vertical vibration and examine the consequences through monotonic and cyclic triaxial drained tests. The results reveal that large and small particles segregate nearly simultaneously, with more thorough separation observed for large particles. The segregation index, D _s , effectively describes this evolution process, offering a quantitative metric for both mixing and segregation. Granular temperature analysis unveils three distinct states during segregation: solid-like, fluid-like, and solid–liquid transitional phase, corresponding to varying activity levels of particle segregation. Drained triaxial shear tests demonstrate the sensitivity of stress–strain relationships to the degree of segregation. Interestingly, ultimate strength is found to be essentially unrelated to the degree of segregation. When the segregation index approaches zero, signifying particles approaching a uniform distribution, the granular system reaches a harmonic state. This state exhibits optimal mechanical performance characterised by maximum peak stress, friction angle, and the highest elastic modulus. These findings underscore the potential impact of segregation on the mechanical response of granular mixtures and emphasise the necessity of a comprehensive understanding of particle segregation in soil mechanics.

In landslide risk management, it is important to estimate the run-out distance of landslides (or debris flows) such that the consequences can be estimated. This research presents an innovative array of dimensionless equations that effectively estimate run-out distances, supported by both experimental data and numerical simulations. We employ the coupled Eulerian–Lagrangian (CEL) method to confront the challenges presented in large deformations during landslides. The soil is modelled using the Mohr–Coulomb model, and the failure of cohesionless soil slopes (e.g., sand slopes) is studied. The simulation results are used to study the characteristics of flows and run-out distances. We suggest a normalized run-out and introduce new scaling relationships for it under different conditions such as different plane angles and material properties. The granular flows under different scales can be compared directly with this new scaling law. The new relationships are validated by both experimental and numerical data. Our analysis reveals that the normalized run-out distance in debris flows is contingent on the initial geometry, plane angle, and material properties. An increase in debris volume and plane angle can contribute to an increase in the normalized run-out distance, while a rise in friction angles causes a decrease. In the case of landslides, the normalized run-out distance depends on material properties and the slope angle. An increase in slope angle leads to a corresponding increase in the normalized run-out distance.