This paper delves into the critical assessment of predicting sidewall displacement in underground caverns through the application of nine distinct machine learning techniques. The accurate prediction of sidewall displacement is essential for ensuring the structural safety and stability of underground caverns, which are prone to various geological challenges. The dataset utilized in this study comprises a total of 310 data points, each containing 13 relevant parameters extracted from 10 underground cavern projects located in Iran and other regions. To facilitate a comprehensive evaluation, the dataset is evenly divided into training and testing subset. The study employs a diverse array of machine learning models, including recurrent neural network, back-propagation neural network, K-nearest neighbors, normalized and ordinary radial basis function, support vector machine, weight estimation, feed-forward stepwise regression, and fuzzy inference system. These models are leveraged to develop predictive models that can accurately forecast sidewall displacement in underground caverns. The training phase involves utilizing 80% of the dataset (248 data points) to train the models, while the remaining 20% (62 data points) are used for testing and validation purposes. The findings of the study highlight the back-propagation neural network (BPNN) model as the most effective in providing accurate predictions. The BPNN model demonstrates a remarkably high correlation coefficient (R2 = 0.99) and a low error rate (RMSE = 4.27E-05), indicating its superior performance in predicting sidewall displacement in underground caverns. This research contributes valuable insights into the application of machine learning techniques for enhancing the safety and stability of underground structures.

If the pressure exerted on the face of a tunnel excavated by TBM exceeds a threshold, it leads to failure of the soil or rock masses ahead of the tunnel face, which results in heaving the ground surface. In the current research, the upper bound method of limit analysis was employed to calculate the blow-out pressure of tunnels excavated in rock masses obeying the Hoek-Brown nonlinear criterion. The results of the proposed method were compared with three-dimensional finite element models, as well as the available methods in the literature. The results show that when σ_ci, m_i, and GSI increase, the blow-out pressure increases as well. By doubling the tunnel diameter, the blow-out pressure reduces up to 54.6%. Also, by doubling the height of the tunnel cover and the surcharge pressure exerted on the ground surface above the tunnel, the blow-out pressure increased up to 74.9% and 5.4%, respectively. With 35% increase in the unit weight of the rock mass surrounding the tunnel, the blow-out pressure increases in the range of 14.8% to 19.6%. The results of the present study were provided in simple design graphs that can easily be used in practical applications in order to obtain the blow-out pressure.

This paper reports several plane-strain trapdoor tests conducted to investigate the effects of reinforcement on soil arching development under localized surface loading with a loading plate width three times the trapdoor width. An analogical soil composed of aluminum rods with three different diameters was used as the backfill and Kraft paper with two different stiffness values was used as the reinforcement material. Four reinforcement arrangements were investigated: (1) no reinforcement, (2) one low stiffness reinforcement R1, (3) one high stiffness reinforcement R2, and (4) two low stiffness reinforcements R1 with a backfill layer in between. The stiffness of R2 was approximately twice that of R1; therefore, two R1 had approximately the same total stiffness as one R2. Test results indicate that the use of reinforcement minimized soil arching degradation under localized surface loading. Soil arching with reinforcement degraded more at unloading stages as compared to that at loading stages. The use of stiffer reinforcement had the advantages of more effectively minimizing soil arching degradation. As compared to one high stiffness reinforcement layer, two low stiffness reinforcement layers with a backfill layer of certain thickness in between promoted soil arching under localized surface loading. Due to different states of soil arching development with and without reinforcement, an analytical multi-stage soil arching model available in the literature was selected in this study to calculate the average vertical pressures acting on the trapdoor or on the deflected reinforcement section under both the backfill self-weight and localized surface loading.

The primary goal of this study is to evaluate the migration of fine granular materials into overlying layers under cyclic loading using a modified large-scale triaxial system as a physical model test. Samples prepared for the modified large-scale triaxial system comprised a 60 mm thick gravel layer overlying a 120 mm thick subgrade layer, which could be either tailings or railway sand. A quantitative analysis of the migration of fine granular materials was based on the mass percentage and grain size of migrated materials collected in the gravel. In addition, the cyclic characteristics, i.e., accumulated axial strain and excess pore water pressure, were evaluated. As a result, the total migration rate of the railway sand sample was found to be small. However, the total migration rate of the sample containing tailings in the subgrade layer was much higher than that of the railway sand sample. In addition, the migration analysis revealed that finer tailings particles tended to be migrated into the upper gravel layer easier than coarser tailings particles under cyclic loading. This could be involved in significant increases in excess pore water pressure at the last cycles of the physical model test.

Measurement or prediction of compression index (C_c) of soils is essential for assessment of total and differential settlement of structures. It is a well-known fact that this parameter is controlled by several index identifiers of soil including initial void ratio, Atterberg limits, overconsolidation ratio, specific gravity, etc. Many studies in the past proposed relationships for prediction of C_c based on different index properties. Therefore, this study aims to present a comparison of previously proposed equations for estimation of C_c. Data from literature was compiled, and a total of 90 and 623 test results on remolded and undisturbed specimens were used to question the validity of previously proposed equations. Nevertheless, the modeling ability of 7 and 12 equations for estimation of C_c of remolded and undisturbed soils were questioned by use of compiled data. Moreover, new empirical relationships based on initial void ratio and toughness limit for prediction of C_c was proposed by use of nonlinear multivariable regression and evolutionary based regression analyses. The results are promising-the performances of models established are quite acceptable, which are verified by statistical analyses.

Monopile foundations of offshore wind turbines embedded in soft clay are subjected to the long-term cyclic lateral loads induced by winds, currents, and waves, the vibration of monopile leads to the accumulation of pore pressure and cyclic strains in the soil in its vicinity, which poses a threat to the safety operation of monopile. The researchers mainly focused on the hysteretic stress-strain relationship of soft clay and kinds of stiffness degradation models have been adopted, which may consume considerable computing resources and is not applicable for the long-term bearing performance analysis of monopile. In this study, a modified cyclic stiffness degradation model considering the effect of plastic strain and pore pressure change has been proposed and validated by comparing with the triaxial test results. Subsequently, the effects of cyclic load ratio, pile aspect ratio, number of load cycles, and length to embedded depth ratio on the accumulated rotation angle and pore pressure are presented. The results indicate the number of load cycles can significantly affect the accumulated rotation angle of monopile, whereas the accumulated pore pressure distribution along the pile merely changes with pile diameter, embedded length, and the number of load cycles, the stiffness of monopile can be significantly weakened by decreasing the embedded depth ratio L/H of monopile. The stiffness degradation of soil is more significant in the passive earth pressure zone, in which soil liquefaction is likely to occur. Furthermore, the suitability of the "accumulated rotation angle" and "accumulated pore pressure" design criteria for determining the required cyclic load ratio are discussed.

The epicentral region of earthquakes is typically where liquefaction-related damage takes place. To determine the maximum distance, such as maximum epicentral distance (R_e), maximum fault distance (R_f), or maximum hypocentral distance (R_h), at which an earthquake can inflict damage, given its magnitude, this study, using a recently updated global liquefaction database, multiple ML models are built to predict the limiting distances (R_e, R_f, or R_h) required for an earthquake of a given magnitude to cause damage. Four machine learning models LSTM (Long Short-Term Memory), BiLSTM (Bidirectional Long Short-Term Memory), CNN (Convolutional Neural Network), and XGB (Extreme Gradient Boosting) are developed using the Python programming language. All four proposed ML models performed better than empirical models for limiting distance assessment. Among these models, the XGB model outperformed all the models. In order to determine how well the suggested models can predict limiting distances, a number of statistical parameters have been studied. To compare the accuracy of the proposed models, rank analysis, error matrix, and Taylor diagram have been developed. The ML models proposed in this paper are more robust than other current models and may be used to assess the minimal energy of a liquefaction disaster caused by an earthquake or to estimate the maximum distance of a liquefied site provided an earthquake in rapid disaster mapping.

The primary goal was to assess how the addition of cement dust, a byproduct known to be harmful, could be used to stabilize clay. Various percentages of cement dust were added to soil samples, which were then subjected to triaxial testing at different rates of strain using an unconsolidated undrained triaxial machine. Six different rates of strain were applied to analyze the response of the clay under different conditions, resulting in 216 triaxial sample tests. As the percentage of cement dust in the clay samples increased, there was a noticeable increase in the strength properties of the clay, indicating a positive effect of cement dust on the clay's strength characteristics. Higher rates of strain during testing led to increased strength properties of the clay. Varying cement dust content influenced the impact of increasing the rate of strain on the clay's strength properties. Higher cement dust content reduced the sensitivity of the clay to changes in strain rate, indicating that the clay became less responsive to changes in strain rate as cement dust content increased. Potential for Clay Stabilization Cement dust proved the potential to enhance the strength properties of clay, indicating its potential utility in clay stabilization applications. Both higher percentages of cement dust and higher rates of strain were found to increase the clay's strength. It's essential to consider both the percentage of cement dust and the rate of strain when assessing the strength properties of clay in practical applications.