The stability of the embankment’s slopes is a critical aspect of geotechnical engineering and it is essential to guarantee the effectiveness of the factor of safety to prevent any potential failures in the slope both during and post-construction. The current study consists of two parts; the first part is the study of the behavior of the geogrid-encased granular columns and their interaction with the soil at the shear surface generated by the slippage of the soil, while the second part is a study of the stability of slopes by changing several factors, including the area replacement ratio (Ar %) of the granular columns, the angle of the embankment slope (β), and different elastic modulus (E_g) of geogrid on the stability of an embankment. About 90 analyses were conducted on a clayey sand embankment over a clayey layer. The area replacement ratios (Ar %) were changed by using different values of the diameter of the column; from 50 to 100 cm. The angle of the embankment slope was changed from 28 to 36 degrees. Furthermore, three different values, 0.12, 2.625, and 6.552 GPa, of modulus of elasticity were used. The results show that increasing the modulus of elasticity of the geogrid increases the normalized shear strength and decreases the lateral displacement in the column. Furthermore, the factor of safety was increased as the stiffness ratio between the geogrid and the materials increased. However, the factor of safety was noted to decrease when the angle of the embankment slope was increased.

The accurate determination of the ratio between design capacity and the measured capacity of piles is crucial for designing safe and cost-effective foundations. However, conventional methods for pile design rely on empirical equations which are unable to consider the complexity of soil-pile interactions due to lack of information about pile conditions and loading history. To overcome this issue, this study proposes a novel hybrid machine learning model named Tree-structured Parzen Estimator based Extreme Gradient Boosting (TPE-XGB) to estimate the effect of various pile and soil-related parameters including pile type, diameter, tip depth allowable pile on the ratio between design capacity from soil investigation and measured capacity from testing. For this purpose, 69 full-scale pile load tests were conducted, and GIS-based mapping was conducted to analyze spatial data. The TPE-XGB model was trained on the experimental data, and the results demonstrated the high efficacy of TPE-XGB model in predicting the output with 95% accuracy and minimal error (RMSE = 0.027). In addition, to interpret the findings of black-box TPE-XGB algorithm, Shapely Additive Analysis (SHAP) and Individual Conditional Expectation (ICE) analysis were used to identify the most important features and to explore the nonlinear relationships between input features and model output respectively. Finally, to facilitate the practical implementation of this study’s findings, a graphical user interface (GUI) was developed, allowing engineers to easily input site-specific parameters and obtain explainable model predictions. This data-driven approach offers a reliable tool for engineers to optimize pile design while ensuring transparency and reliability in decision-making.