Search

To reduce the disasters caused by slope instability, this paper proposes a new machine learning (ML) model for slope stability prediction. This improved SVR model uses support vector machine regression (SVR) as the basic prediction tool and the grid search method with 5-fold cross-validation to optimize the hyperparameters to improve the prediction performance. Six features, namely, unit weight, cohesion, friction angle, slope angle, slope height, and pore pressure ratio, were taken as the input of the model, and the factor of safety was taken as the model output. Four statistical indicators, namely, the coefficient of determination (R2), mean absolute percentage error (MAPE), mean absolute error (MAE), and root mean squared error (RMSE), were introduced to assess the generalization performance of the model. Finally, the feature importance score of the features was clarified by calculating the importance of the six features and visualizing them. The results show that the model can well describe the nonlinear relationship between features and the factor of safety. The R2, MAPE, MAE, and RMSE of the testing dataset were 0.901, 7.41%, 0.082, and 0.133, respectively. Compared with other ML models, the improved SVR model had a better effect. The most sensitive feature was unit weight. [ABSTRACT FROM AUTHOR]

Traditional slope stability analysis methods are time-consuming, complex, and cannot provide fast stability estimates when facing a large amount of slope cases. In this case, artificial neural networks (ANN) provide a better alternative. Based on the ANN, the particle swarm optimization (PSO) algorithm, and the principal component analysis (PCA) method, a novel PCA-PANN model is proposed. Then, a dataset of 307 slope cases covering a wide range of slope geometries and mechanical properties of geomaterial is developed. The hybrid machine learning model trained with the dataset is applied to the factor of safety (FoS) prediction of the actual slope, and three evaluation indicators are introduced to measure the prediction performance of the model. Finally, the sensitivity analysis of input parameters is carried out, and the slope protection strategy for different sensitive factors is proposed. The results show that this new model can quickly obtain the FoS and stable state of the slope without complex calculation, only by providing the relevant characteristic parameters. The correlation coefficient of the PCA-PANN model for slope stability analysis reaches more than 0.97. The sensitivity degree of influencing factors from large to small is slope angle, cohesion, pore pressure ratio, slope height, unit weight, and friction angle. [ABSTRACT FROM AUTHOR]

Landslides cause significant economic losses and casualties worldwide. However, robust prediction remains challenging due to the complexity of geological factors contributing to slope stability. Advanced correlation analysis methods can improve prediction capabilities. This study aimed to develop a novel landslide prediction approach that combines numerical modeling and correlation analysis (Spearman rho and Kendall tau) to improve displacement-based failure prediction. Simulations generate multi-location displacement data sets on soil and rock slopes under incremental stability reductions. Targeted monitoring points profile local displacement responses. Statistical analyses, including mean/variance and Spearman/Kendall correlations, quantified displacement-stability relationships. For the homogeneous soil slope, monitoring point 2 of the middle section of the slope showed a mean horizontal displacement of 17.65 mm and a mean vertical displacement of 9.72 mm under stability reduction. Spearman's rho correlation coefficients ranged from 0.31 to 0.76, while Kendall's tau values ranged from 0.29 to 0.64, indicating variable displacement–stability relationships. The joint rock slope model had strong positive total displacement correlations (Spearman's and Kendall's correlation ranges of +1.0 and −1.0) at most points. Horizontal and vertical displacements reached mean maxima of 44.13 mm and 22.17 mm, respectively, at the unstable point 2 of the center section of the slope. The advanced correlation analysis techniques provided superior identification of parameters affecting slope stability compared to standard methods. The generated predictive model dramatically improves landslide prediction capability, allowing preventive measures to be taken to mitigate future losses through this new approach. [ABSTRACT FROM AUTHOR]

Intermittent joints are widely found in slopes and the rock section (locking section) in intermittent joints is an important structure that prevents joints from interconnecting and maintains slope stability, but the exact shape of the locking section is not yet known. In this paper, based on the finite difference method (FDM), k-means algorithm, and alpha shape algorithm, a method is proposed to calculate the shape of locking sections and to quantitatively analyze the controlling effect of locking sections and non-locking sections areas on the stability of slopes. In addition, for slopes with high accuracy in the shape of the locking section, the original mesh in the FDM is reconstructed and a network of discrete points is arranged at the locking section at customised intervals and the maximum principal stresses at each discrete point are calculated by the inverse transformation method of the isoparametric elements. This method greatly reduces the influence of grid size on the shape of the locking section. Finally, eight working conditions were designed to investigate the effect of the position of the weak interlayer on the shape and area of the locking section. The results show that the shape of the locking section does not change much as the angle of the line connecting the end points of the weak interlayer increases, and the shape basically remains elliptical, while the area of the locking section changes by increasing and then decreasing. [ABSTRACT FROM AUTHOR]

The soft interlayer and rock structure play a significant role in controlling the deformation of the bedding slope, and it is necessary to consider the phenomenon of the sudden change of local response in these key parts under rainfall conditions, and then to clarify the mechanism of rainfall infiltration and damage mechanism of such slopes. In this paper, a large red-layered flat-dipping bedding landslide was selected as the research object, and numerical calculations based on the Van Genuchten model for saturated–unsaturated flow were performed in order to investigate the hydrological response and distribution patterns of water within the slope during rainfall. Moreover, stability analysis was performed based on the seepage field results and secondary development of FLAC3D, and the landslide evolution process was simulated and reproduced using the constitutive model of double-variables and the strength reduction method (SRM). The results showed that the effects of heavy rainfall on the water distribution and stability of the highway slope are significant, while the effects on the natural slope are not significant. There are three phases of the slope destabilization: flexure and uplift state, deformation exacerbation state and shear failure state. The slope destabilization mechanism is a typical "sliding-bending-shearing" type. The results of the study can provide a theoretical basis for the study of the seepage, stability analysis and destabilization mechanism of bedding slopes. [ABSTRACT FROM AUTHOR]

As the strength parameters of rock mass degrade differently during slope instability, different factors should be considered in the strength reduction method. Previous nonlinear reduction methods were essentially implemented based on the Mohr–Coulomb criterion, which was reported not to reflect the nonlinear performance of rock mass. To address this deficiency, in this study, the Hoek–Brown criterion was combined with a nonlinear reduction technique for slope stability evaluation. Firstly, based on the classical definition of safety factors, the relationships that should be satisfied by each parameter of the critical slope were derived. The critical curve of the slope regarding the Hoek–Brown constant mb and the uniaxial compressive strength of rock mass σcmass was then obtained. On the assumption that the slope parameter deterioration conforms to the shortest path theory, the reduction ratio of σcmass to mb was determined. The more objective k-means algorithm was employed to automatically search the potential sliding surface, on which the slope safety factor was calculated as the ratio of sliding resistance to sliding force. Finally, the slopes in published literature were adopted for verification, and the calculated safety factors were compared with those by other methods, which showed better efficacy. [ABSTRACT FROM AUTHOR]

Researches on the energy evolution of the key blocks is helpful to reveal the failure process of locked-segment type slope, whose stability is governed by the locked segment along the potential slip surface. In order to study the failure mechanism of the locked segment in the process of slope progressive failure due to strength attenuation, a series of stability analysis on the numerical models of locked-segment type slope were implemented to record the relationship curve between energy and strength reduction coefficient. Then, according to the variation law and characteristic of energy evolution, the failure process of the locked segment was divided into four stages: elastic stage, initial damage stage, extensive damage stage and failure stage. And the reduction coefficient corresponding to the peak of the energy evolution curve was employed to achieve landslide warning. In addition, the method to determine the safety factor of locked-segment type slope was given, and its reliability was verified by comparing with other traditional methods. Finally, the formula for calculating the initial sliding velocity was presented based on the residual strain energy which is defined as the elastic strain energy of the locked segment when the slope is unstable. [ABSTRACT FROM AUTHOR]

The locked section is a kind of geological structure that is commonly found in natural slopes. The instability criterion of the slope with a locked section structure is not yet studied. In accordance with the mechanical properties of this type of slope, the rock mass is divided into several rock blocks along its joint distribution, and the upper limit method of plastic limit analysis is introduced. By combining the principle of virtual work and the characteristics of the slope, a virtual speed is assigned to the slope and the locked section. In addition, the maximum elastic strain energy that can be accumulated in the locked section is calculated to derive its deformation rate and internal energy dissipation power. The virtual velocity, internal energy dissipation power, and gravity work power of the locked section and the rock slope are solved simultaneously in accordance with the Mohr–Coulomb correlation flow law. Finally, the formula for calculating the safety factor of this type of slope under shear failure mode is derived. A slope in Xikou, Sichuan, China, is taken as an example to verify the proposed model. [ABSTRACT FROM AUTHOR]

From the perspective of the mechanical mechanism of slope failure, cohesion c usually plays a different role with friction φ in sliding resistance, which indicates the distinct weights of their reduction factors Fsc and Fsφ to the overall safety factor of slope Fs in the double strength reduction method (DSRM). This study primarily introduced the equivalent influence angle of slope θe, for which c and φ share identical contributions to the safety factor, and investigated its influencing factors, which turns out that θe shows an increasing trend with an increase of slope weight H or slope height γ, but the increasing rate is decreasing. Subsequently, an equivalent influence angle chart was plotted as an effective and advantageous approach to locate the specific value of θe for a given slope. On this basis, the shortest reduction path method was utilized to calculate Fsc and Fsφ, and the stability contributions of c and φ were quantified by the different weight coefficients of Fsc and Fsφ to Fs. The specific weight coefficient could be solved by the correlation between slope angle θ and corresponding θe, thereby developing a new definition of Fs. Ultimately, a modified double strength reduction method was achieved, which was compared with other DSRMs and verified by existing slope examples. [ABSTRACT FROM AUTHOR]

Slope stability analysis is a multi-scale problem. Typically, owing to the distinctions of slope scales (e.g., slope height or slope angle) in practical engineering, the stability calculation results of slopes with various scales from numerical methods inevitably exhibit different computational precision levels in the case of identical computational grids, and therefore the stability results of different slopes cannot be compared. To achieve equal accuracy stability analysis for multi-scale slopes, this study establishes numerical models of slopes with various scales as well as different grid shapes and sizes to conduct stability analysis. The results show the following: (a) a positive correlation relationship exists between the safety factor of the slope and the scaling factor, which is defined as the ratio of the grid size to the slope height; (b) the definition of the refined safety factor is given, representing the safety factor that corresponds to the infinitesimal grid size and eliminating the computational error of slope stability analysis caused by grid size or shape; (c) on this basis, embarking on the composite influence of multiple scales of slope on stability analysis, the study proposes a simplified treatment method suitable for evaluating the refined safety factor of the multi-scale slopes, which is verified as valid and feasible by some examples. [ABSTRACT FROM AUTHOR]

The selection of appropriate monitoring methods is necessary to realize the early warning of slope stability. In this study, a new monitoring method was proposed on the basis of bolt stress variation with reduction factors. Numerical simulation was conducted to construct a rock slope model with joint, and the monitoring bolt was placed at the joint. The relationship between bolt axial force and slope stability was investigated. Moreover, the position and inclination of the bolt were investigated thoroughly. A comprehensive comparison was conducted using an existing displacement monitoring method. Results show that (1) a single peak distribution of the bolt axial force occurs along the length, and the peak appears at the location of the joint and bolt intersection with bolt axial force saltation, which is considered the optimal axial force monitoring position. (2) Regardless of the bolt inclination, the axial force saltation constantly exists, and the internal slope stress can be monitored, except when the angle is 90°. (3) The bolt position does not influence the monitoring effects provided that the bolt penetrates the joint. (4) The axial force saltation of the bolt is earlier than the displacement saltation of the slope; this phenomenon can achieve remarkable monitoring effects appropriately for slope stability early warning. [ABSTRACT FROM AUTHOR]

Rainfall infiltration is an important factor that leads to slope instability. In this study, a numerical model for slope is built to investigate the effects of rainfall intensity and its pattern on slope stability. Results show that rainfall intensity and its pattern significantly influence slope stability due the following instances: (1) the safety factor of slope initially decreases and then stabilizes during rainfall, which is defined as the effective rainfall days; moreover, when the rainfall intensity is less than the saturated permeability coefficient of soil, the effective rainfall days decreases with the increase of rainfall intensity. (2) Under the same rainfall intensity, the ultimate safety factor of sand slope when the effective rainfall days is reached is greater than that of the clay slope. (3) When the rainfall intensity is less than the saturated permeability coefficient of soil with the same total precipitation, a longer rainfall duration indicates a larger slope safety factor; conversely, when the rainfall intensity is greater than the saturated permeability coefficient of soil, a longer rainfall duration indicates a smaller slope safety factor. [ABSTRACT FROM AUTHOR]

The effect of rainfall on the slope may continue and the most unstable state may occur after the rainfall has stopped. This phenomenon can be described as the delay phenomenon. This paper reports on the models and influencing factors of the delay phenomenon using numerical methods. Two representative models of landslides occurring after rainfall were set up to illustrate the mechanisms of the delay phenomenon. Parametric studies were made to quantify the impact of soil types, the depth of initial water table, anisotropic conductivity, rainfall intensity and rainfall pattern on the delay phenomenon. The results indicated that slope soils with slightly smaller water-entry value and slower permeation rate of rainwater have a higher probability of generating the delay phenomenon. The most noticeable delay phenomenon was observed when the anisotropy ratioky/kx = 0.5 and the saturated hydraulic conductivity of soil have similar value with rainfall intensity. Besides, the delay phenomena were the most likely to occur when rainfall intensity peak was near to the time when rainfall stopped. [ABSTRACT FROM AUTHOR]

Rainfall infiltration is the main factor that causes slope instability. To study the effect of hydraulic parameters on the final saturation line and stability of slopes, a numerical slope model is established with a saturated-unsaturated seepage analysis method. Analysis results show the following, (1) When parameter a increases, the effective rainfall duration decreases linearly, and the ultimate safety factor increases gradually; when parameter m increases, the effective rainfall duration increases linearly, and the ultimate safety factor decreases linearly; when parameter n increases, both the effective rainfall duration and the ultimate safety factor decrease first and then remain stable. (2) When the saturated permeability coefficient decreases, the effective rainfall duration presents a crescent trend, and the ultimate safety factor decreases first and then remains the same after rainfall intensity exceeds the saturated permeability coefficient of soil. (3) When rainfall intensity is less than the saturated permeability coefficient of soil, the location of the final saturation line rises as the saturated permeability coefficient decreases and is thus independent of parameters a, m, and n. [ABSTRACT FROM AUTHOR]

Previous studies in the field of slope stability mostly concentrate on the calculation of the safety factor, while critical slip line recognition and extraction are rarely noticed. Since the popular strength reduction method can only provide an approximate slip region, an automatic recognition and rapid extraction method for the slip line of a slope was proposed. Its core lies in the separation of slip mass and stable mass, which was realized by the modified k-medoid clustering algorithm according to the horizontal displacement difference of nodes, and the boundary was regarded as the critical slip line of the slope. In particular, for slopes requiring high slip line accuracy, it is recommended that discrete point networks can be arranged at custom intervals in the slip region, and the horizontal displacement of each point is calculated by the inverse transformation method of isoparametric elements. On this basis, a more accurate slip line is identified and extracted by the modified k-medoid clustering algorithm. This method reduces the influence of grid size and avoids the subjectivity of defining the slip line artificially. Ultimately, based on the published slope cases, the slip lines extracted by the proposed method were compared with those obtained by previous methods, which verifies its validity and reflects the advantages. [ABSTRACT FROM AUTHOR]