Explore the vast range of titles available.

Conventional supervised and unsupervised machine learning models used for landslide susceptibility prediction (LSP) have many drawbacks, such as an insufficient number of recorded landslide samples, and the subjective and random selection of non-landslide samples. To overcome these drawbacks, a semi-supervised multiple-layer perceptron (SSMLP) is innovatively proposed with several processes: (1) an initial landslide susceptibility map (LSM) is produced using the multiple-layer perceptron (MLP) based on the original recorded landslide samples and related environmental factors; (2) the initial LSM is respectively classified into five areas with very high, high, moderate, low and very low susceptible levels; (3) some reasonable grid units from the areas with very high susceptible level are selected as new landslide samples to expand the original landslide samples; (4) reasonable non-landslide samples are selected from the areas with very low susceptible level; and (5) the expanded landslide samples, reasonable selected non-landslide samples and related environmental factors are put into the MLP once again to predict the final LSM. The Xunwu County of Jiangxi Province in China is selected as the study area. Conventional supervised machine learning (i.e. MLP) and unsupervised machine learning (i.e. K-means clustering model) are selected for comparisons. The comparative results indicate that the SSMLP model has a considerably higher LSP performance than the MLP and K-means clustering in Xunwu County. The SSMLP model successfully addresses the drawbacks existed in the conventional machine learning for LSP.

Existing studies relating to landslide susceptibility prediction (LSP) either do not pay enough attentions to the continuously updated landslide inventories or use batch learning methods for LSP, resulting in the insufficient use of the entire landslide inventory. To overcome this problem, the Incremental Learning theory combined with a Bayesian Network (ILBN) model is constructed for LSP. Wencheng County of China is taken as the study area, a landslide inventory from 1985 to 2019 and 10 conditioning factors are mapped and analyzed. Then, the LSP results of the ILBN model are compared with the batch learning-based multilayer perceptron (BL-MLP) and support vector machine (BL-SVM) models. Results show that the LSP accuracies of ILBN_0 (ILBN modeling of initial landslide inventory), ILBN_1 (the first Incremental Learning model), and ILBN_2 (the second Incremental Learning model) increase gradually with the AUC value of 0.807, 0.813, and 0.835, respectively. The LSM produced by the ILBN model is more consistent with the law of landslides distribution in the study area. The mean values of ILBN_0, ILBN_1, and ILBN_2 are 0.307, 0.287, and 0.245, and the standard deviations are 0.278, 0.281, and 0.308, respectively. Meanwhile, the characteristics of LSIs in Wencheng County are in line with the actual landslides distribution with the main controlling factors of lithology, elevation, and normalized difference building indexes determined by the weighted mean method. Furthermore, the LSP results of ILBN model are superior to those of the BL-MLP and BL-SVM models. It is concluded that the ILBN model can better address the long-term, continuous LSP using the new added landslide inventory.

The flux-driven displacement of a wetting fluid by a non-wetting fluid in two-dimensional channels with flat parallel plates and sinusoidal surfaces is investigated via a multi-relaxation time multi-component lattice Boltzmann method. The co-current flow and the capillary filling problems are used for the validation of the numerical method. The results have shown that the present method is effective in simulating the viscous and capillary forces during the displacement process. For flat parallel plates, the effect of wettability on the development of fingering flow and the relationship between the developed finger width ratio and the capillary number are investigated. The results are compared to the previous research. The fingering flow is enhanced with a strongly wetting condition and the finger width ratio decreases as the capillary number is raised. For periodic sinusoidal channels, discontinuous interfaces appear due to the roughness of channel walls. The residual behavior of the wetting displaced fluid is enhanced with the wetting condition, as a strongly wetting condition would lead to a slower contact line motion. Finally, a quantitative study of the combined effect of roughness and wettability on the residual saturation is made.

Many nonlinear models have been proposed to forecast groundwater level. However, the evidence of chaos in groundwater levels in landslide has not been explored. In addition, linear correlation analyses are used to determine the input and output variables for the nonlinear models. Linear correlation analyses are unable to capture the nonlinear relationships between the input and output variables. This paper proposes to use chaos theory to select the input and output variables for nonlinear models. The nonlinear model is constructed based on support vector machine (SVM). The parameters of SVM are obtained by particle swarm optimization (PSO). The proposed PSO-SVM model based on chaos theory (chaotic PSO-SVM) is applied to predict the daily groundwater levels in Huayuan landslide and the weekly, monthly groundwater levels in Baijiabao landslide in the Three Gorges Reservoir Area in China. The results show that there are chaos characteristics in the groundwater levels. The linear correlation analysis based PSO-SVM (linear PSO-SVM) and chaos theory-based back-propagation neural network (chaotic BPNN) are also applied for the purpose of comparison. The results show that the chaotic PSO-SVM model has higher prediction accuracy than the linear PSO-SVM and chaotic BPNN models for the test data considered.

The parameter m i is an important rock property parameter required for use of the Hoek–Brown failure criterion. The conventional method for determining m i is to fit a series of triaxial compression test data. In the absence of laboratory test data, guideline charts have been provided by Hoek to estimate the m i value. In the conventional Hoek–Brown failure criterion, the m i value is a constant for a given rock. It is observed that using a constant m i may not fit the triaxial compression test data well for some rocks. In this paper, a negative exponent empirical model is proposed to express m i as a function of confinement, and this exercise leads us to a new empirical failure criterion for intact rocks. Triaxial compression test data of various rocks are used to fit parameters of this model. It is seen that the new empirical failure criterion fits the test data better than the conventional Hoek–Brown failure criterion for intact rocks. The conventional Hoek–Brown criterion fits the test data well in the high-confinement region but fails to match data well in the low-confinement and tension regions. In particular, it overestimates the uniaxial compressive strength (UCS) and the uniaxial tensile strength of rocks. On the other hand, curves fitted by the proposed empirical failure criterion match test data very well, and the estimated UCS and tensile strength agree well with test data.

This paper numerically investigates the fluid flow behavior through single fractures with directional shear dislocations. Synthetic fractures are generated with directional shear dislocations, and the lattice Boltzmann method is used to simulate the fracture flow. With an ignorance of tortuosity effect, a notable overestimation of hydraulic conductivity is observed when the simplified local cubic law is used. During the closure process, the decreasing rate of conductivity is found to be highly related to the roughness of fractures. The conductivity of smoother fractures decreases faster than that of rougher fractures. By conducting simulations on fractures with a constant shear displacement, the effective conductivity is found to vary with the shear directions. The results show that the conductivity of rougher fractures is less sensitive to the shear directions than that of smoother fractures. As fracture surfaces come into contact, a sharp decrease in effective conductivity is observed and the decreasing trend flattens as the contact ratio continues to increase. A new model is proposed based on the bottleneck model to predict the conductivity of sheared fractures. By integrating the tortuosity and channeling effects into the original model, the proposed new model shows a better performance in predicting the conductivity, especially for fractures with rougher surfaces.

The impact of blast vibrations on cement-grouted rock is an unresolved challenge in construction projects where blasting is conducted near the grouted areas. This study investigates the blast vibration resistance of cement-grouted rock using both theoretical and experimental approaches. An analytical model is first presented based on structural characteristics and mechanical properties to describe the stress wave propagation in cement-grouted rock mass and to investigate the failure modes at its bonding interfaces. A model to calculate the safe vibration velocity (SVV) is then proposed to study the effects of the incident angle, in-situ stress, and bonding strength on cement-grouted rock. Next, an experiment was conducted to analyse the blast vibration resistance of cement-grouted rock and to validate the SVV model. Finally, several recommendations regarding safe blast vibration velocities for grouted areas were provided. The results indicate that cement-grouted rock has a high blast vibration resistance, which can be improved by increasing the incident angle, in-situ stress, or bonding strength. A normally incident wave was identified as the most dangerous for cement-grouted rock; thus, the SVV is the minimal in that case. For 3, 7, and 28-day-old cement-grouted rock, the SVV is suggested to be 6, 9, and 13 cm/s, respectively.

A new type of vortex drop shaft without ventilation holes is proposed to resolve the problems associated with insufficient aeration, negative pressure (Unless otherwise specified, the pressure in this text is gauge pressure and time-averaged pressure) on the shaft wall and cavitation erosion. The height of the intake tunnel is adjusted to facilitate aeration and convert the water in the intake tunnel to a non-pressurized flow. The hydraulic characteristics, including the velocity (Unless otherwise specified, the velocity in this text is time-averaged velocity), pressure and aeration concentration, are investigated through model experiment and numerical simulation. The results revealed that the RNG k-ε turbulence model can effectively simulate the flow characteristics of the vortex drop shaft. By changing the inflow conditions, water flowed into the vertical shaft through the intake tunnel with a large amount of air to form a stable mixing cavity. Frictional shearing along the vertical shaft wall and the collisions of rotating water molecules caused the turbulence of the flow to increase; the aeration concentration was sufficient, and the energy dissipation effect was excellent. The cavitation number indicated that the possibility of cavitation erosion was small. The results of this study provide a reference for the analysis of similar spillways.

The discontinuous deformation analysis (DDA) is a numerical method for modeling discontinuous deformation behaviour of jointed rocks. In this paper, two basic problems are discussed related to kinetic energy dissipation and the convergence criterion for the DDA method when it is applied to geotechnical engineering. In view of the fact that the deformation and progressive failure can be treated as a quasi-static process with low kinetic energy dissipation rates, this paper introduces a viscous damping component to absorb discrete blocks’ kinetic energy, establishes the global equations of motion of the discrete block system that take damping effects into account, investigates the energy dissipation mechanism when solving a static or quasi-static problem, and defines the convergence criteria of displacement, kinetic energy and unbalanced force for DDA solutions when the system arrives at a stable state.

During deep rock mass excavation with the method of drill and blast, accompanying the secession of rock fragments and the formation of a new free surface, in situ stress on this boundary is suddenly released within several milliseconds, which is termed the transient release of in situ stress. In this process, enormous strain energy around the excavation face is instantly released in the form of kinetic energy and it inevitably induces microseismic events in surrounding rock masses. Thus, blasting excavation-induced microseismic vibrations in high-stress rock masses are attributed to the combined action of explosion and the transient release of in situ stress. The intensity of stress release-induced microseisms, which depends mainly on the magnitude of the in situ stress and the dimension of the excavation face, is comparable to that of explosion-induced vibrations. With the methods of time–energy density analysis, amplitude spectrum analysis, and finite impulse response (FIR) digital filter, microseismic vibrations induced by the transient release of in situ stress were identified and separated from recorded microseismic signals during a blast of deep rock masses in the Pubugou Hydropower Station. The results show that the low-frequency component in the microseismic records results mainly from the transient release of in situ stress, while the high-frequency component originates primarily from explosion. In addition, a numerical simulation was conducted to demonstrate the occurrence of microseismic events by the transient release of in situ stress, and the results seem to have confirmed fairly well the separated vibrations from microseismic records.