The T-shaped strip footing is a good choice for building foundations because it effectively resists overturning forces and accommodates eccentric loading. The footing's embedded within the soil enhances its capacity to counteract the forces generated by eccentric loading, providing additional stability and support. This study presents a couple of finite element limit analysis (FELA) and regression machine learning models in predicting the bearing capacity of eccentrically loaded T-shaped footings on anisotropic clays. A numerical simulation of T-shaped strip footings in anisotropic clay under eccentric loading is performed using a FELA software, namely OptumG2. At the same time, the regression soft computing models employed four techniques, including the genetic programming (GP), age-layered population structure-genetic algorithm (ALPS-GA), offspring selection genetic algorithm (OSGA), and grammatical evolution (GE) models. The AUS yield criterion is utilized to govern the soil properties, while the footing is modeled as a rigid material. By emphasizing the stability of the surrounding soil, this study neglects the failure of the footing itself since the footing is assumed to be very rigid. Parametric analyses are conducted using a dimensionless approach. The influences of eccentricity (e/B), the insertion length ratio (D/B), the anisotropic strength ratio (re), and the adhesion factor (alpha) on the bearing capacity factor (N) are investigated. The impact of these dimensionless parameters on the shear dissipation of the model to monitor the failure pattern is discussed. The current results are compared with prior solutions, showing consistency. Moreover, predictive regression machine learning techniques (GP, ALPS-GA, OSGA, and GE models) are applied to develop empirical equations for N estimation, with the proposed OSGA model demonstrating superior performance, achieving coefficients of determination (R2) of 0.985 and 0.984 for the training and testing sets, respectively.

The uplift capacity of pipeline systems in geotechnical engineering is influenced by internal loading and external factors, making it a significant consideration in pipeline design problems. Previous research has conducted experimental tests and numerical solutions to investigate the relationship between force and displacement or the resistance of pipelines in numerous soil media. This paper proposes a machine-learning regression technique to predict the uplift capacity of buried pipelines in anisotropic clays with parametric analysis. Specifically, the Multivariate Adaptive Regression Spline (MARS) is employed to establish the relationship between input parameters, namely the depth ratio (H/D), anisotropic strength ratio (re), load inclination (beta), overburden factor (gamma H/Suc), adhesion factor (alpha), and the output uplift resistance (N) obtained from the finite element limit analysis (FELA), utilizing the AUS material model integrated with the OptumG2 commercial program. Furthermore, the sensitivity analysis outcome shows the embedded depth ratio is the most critical parameter, followed by the anisotropic strength ratio, overburden factor, load inclination, and adhesion factor. Additionally, the shear velocity field contours show that when the depth ratio and the load inclination increase, the dissipation of shear changes. Design data visualizations, tables, graph contours, and empirical equations are created and can be utilized to aid in the development of practical designs.