A set of small-scale physical modeling of a single pile under lateral loads was performed in a loose sand environment. Digital images were captured during the lateral loading of the pile from the side and from the top of the model simultaneously. The particle image velocimetry (PIV) method was applied, and the deformations of the soil around the pile and the soil strains were obtained from these tests. The soil displacement pattern near the surface around the piles was studied, and the effect of the pile length on the soil deformation pattern was investigated. The effect of pile stiffness and width on soil deformation patterns was also studied. For the study of soil deformation patterns around rigid piles, three tests with rigid piles were undertaken, and strain distribution in the soil was obtained. Based on PIV analysis, a three-dimensional strain wedge with the shape of a circular cone was formulated. The equation of the strain wedge was derived, and with the stress-strain limit equilibrium ana...

The index mechanical properties, strength, and stiffness parameters of rock materials (i.e., uniaxial compressive strength, c, ϕ, E, and G) are critical factors in the proper geotechnical design of rock structures. Direct procedures such as field surveys, sampling, and testing are used to estimate these properties, and are time-consuming and costly. Indirect methods have gained popularity in recent years due to their time-saving and highly accurate results, which are comparable to those obtained through direct approaches. This study presents a procedure for establishing a deep learning-based predictive model (DNN) for obtaining the geomechanical characteristics of marlstone samples that have been recovered from the South Pars region of southwest Iran. The model was implemented on a dataset resulting from the execution of numerous geotechnical tests and the evaluation of the geotechnical parameters of a total of 120 samples. The applied model was verified by using benchmark learning classifiers (e.g., Support Vector Machine, Logistic Regression, Gaussian Naïve Bayes, Multilayer Perceptron, Bernoulli Naïve Bayes, and Decision Tree), Loss Function, MAE, MSE, RMSE, and R-square. According to the results, the proposed DNN-based model led to the highest accuracy (0.95), precision (0.97), and the lowest error rate (MAE = 0.13, MSE = 0.11, and RMSE = 0.17). Moreover, in terms of R², the model was able to accurately predict the geotechnical indices (0.933 for UCS, 0.925 for E, 0.941 for G, 0.954 for c, and 0.921 for φ).

This study presents a novel empirical classification system for stability analysis of rock slopes in weak rock based on their geotechnical and geological properties. For this purpose, consideration is given to the marly rock slopes, which include three main groups of weak rock (lime marlstone, marlstone, and marly limestone). The 40 different slopes located in the South Pars special zone (Assalouyeh), southwest of Iran, are targeted in classification. To prepare comprehensive graphical stability charts for weak rocks, extensive field surveys, sampling, geotechnical laboratory tests, and ground measurements are conducted in slope sites. Using the findings of the study, empirical stability charts for slopes composed of weak materials were developed. The charts are associated with geotechnical indexes, geo-units’ weathering impact, and in-situ stress conditions. Using these graphical charts assists in investigating the stability condition of rock slopes and estimating the geotechnical characteristics of clay-based weak rocks such as marlstones.