The shear strength of compacted bentonite is crucial for preventing tilting and damage of the waste canisters in deep geological repositories (DGRs). The shear strength evolution along the confined wetting path also needs to be investigated, given the long saturation time of the bentonite buffer. This study conducted direct shear tests on densely compacted Gaomiaozi bentonite after suction control under confined conditions to determine its peak shear strength and strength parameters. Furthermore, the shear strength evolution along the confined wetting path was modeled on the basis of the effective stress principle. The results show that, for a given dry density, the peak shear strength at a given vertical pressure and the strength parameters exhibit an overall decrease along the confined wetting path. Moreover, the peak shear strength of the specimen that underwent confined wetting was considerably lower than that of the as-compacted specimen with the same total suction, indicating that the suction value and microstructure codetermine the peak shear strength of compacted Gaomiaozi bentonite. For this reason, the peak shear strength in the as-compacted state and the dual-porosity water retention curves established along the confined wetting path were used to model the shear strength evolution along the confined wetting path. The substitution equation for the effective stress parameter chi was selected on the basis of the experimental evidence. Finally, the model parameters were calibrated from the shear strength evolution at a given vertical pressure, and they reasonably reproduced the shear strength evolution under other vertical pressures. These findings can be helpful for the design and safe operation of DGRs under extreme geological conditions.

In ocean engineering, polymer layer is often adopted as waterproof materials, and the mechanical behaviour of marine sand-polymer layer interfaces has significant influence on the engineering safety. In the research, based on the bespoke large temperature-controlled interface shear equipment, direct shear experiments were performed on the interfaces between polymer layer and marine sand with the particle size ranging from 1 mm to 2 mm (S1 marine sand) and from 2 mm to 4 mm (S2 marine sand) in the temperature range of-5 degrees C-80 degrees C. The test outcomes manifest that, both the change rules of interface peak shear strength and its sensitivity to normal stress variation are temperature dependent; The variation rules of the interface peak shear strength in elevated temperature are different in diverse normal stress. By adopting the experimental outcomes, machine learning models were established to predict the interface shear stress under the effects of temperature and soil particle, with higher estimating precision and efficiency. The research findings are beneficial for the correct design of marine engineering facilities related to marine sand-polymer layer interfaces.

In the design of offshore engineering foundations, a critical consideration involves determining the peak shear strength of marine soft clay sediment. To enhance the accuracy of estimating this value, a database containing 729 direct shear tests on marine soft clay sediment was established. Employing a machine learning approach, the Particle Swarm Optimization algorithm (PSO) was integrated with the Adaptive Boosting Algorithm (ADA) and Back Propagation Artificial Neural Network (BPANN). This novel methodology represents the initial effort to employ such a model for predicting the peak shear strength of the soil. To validate the proposed approach, four conventional machine learning algorithms were also developed as references, including PSO-optimized BPANN, Support Vector Machine (SVM), BPANN, and ADA-BPANN. The study results show that the PSO-BPANN model, which has undergone optimization via Particle Swarm Optimization (PSO), has prediction accuracy and efficiency in determining the peak shear performance of marine soft clay sediments that surpass that offered by traditional machine learning models. Additionally, a sensitivity analysis conducted with this innovative model highlights the notable impact of factors such as normal stress, initial soil density, the number of drying-wetting cycles, and average soil particle size on the peak shear strength of this type of sediment, while the impact of initial soil moisture content and temperature is comparatively minor. Finally, an analytical formula derived from the novel algorithm allows for precise estimation of the peak shear strength of marine soft clay sediment, catering to individuals lacking a background in machine learning.