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.

Freeze-thaw (FT) alternation can severely affect the properties of fine-grained soils, often leading to the failure of foundation backfill projects, such as open canals and roads in cold regions. To address these problems, a water-soluble anionic polyacrylamide (APAM) was used to improve the properties of fine-grained soils, particularly silty clay. This study aims to analyze the effects of the APAM polymer on the physico-mechanical and microstructural properties of silty clay under both unfrozen and FT cycles. For this purpose, different addition dosages and FT cycle numbers were determined, and then a series of zeta potential, thermal conductivity, permeability, triaxial compression, and scanning electron microscopy (SEM) tests were conducted on the soil samples. Additionally, a unidirectional freezing test was constructed to investigate the coupled thermo-hydro-mechanical processes of APAM-treated soil samples. The results showed that the addition of the APAM polymer significantly enhanced the macroscopic engineering properties and microstructural characteristics of silty clay. This improvement was attributed to the charge neutralization, adsorption bridging effect, and hydrophobic interaction provided by the APAM polymer. However, all the soil samples showed a significant deterioration in their engineering properties during FT cycles, especially after the third FT cycle. It was notable that APAM-treated soil samples were superior to the untreated sample in terms of FT resistance. During the unidirectional freezing process, the pore water migrated from the unfrozen zone towards the freezing front due to the temperature gradient. The treated sample's pore water migration volume was considerably lower than that of the untreated sample, resulting in a 55.25% reduction in total frost heave when the APAM dosage was 0.30%. The findings of this paper may be utilized to mitigate the risk of frost damage to foundation backfill projects in cold regions, as well as to get a better understanding of the stabilization mechanism of the eco-friendly APAM polymer.