The monopiles are always subjected to both vertical loads and lateral loads. However, the designs for the piles under the vertical loads and the lateral loads are carried out separately in practice because the interaction between those two loads is still unclear. A series of model tests are carried out to investigate the influence of the vertical loads on the lateral responses of the monopile in sandy soil. The results show that the presence of the vertical load improves the lateral behaviour of the monopile. The influence of the vertical load on p–y curve around the monopile is also investigated to look for a useful suggestion for the design of monopile. In order to calculate the lateral responses of the monopile based on traditional design method, several equations are proposed to evaluate the degree of improvements.

Predicting the maximum ground subsidence (Smax) in the construction of soil pressure balanced shield tunnel, particularly on soft foundation soils, is essential for safe operation and to minimize the possible risk of damage in urban areas. Although some research has been done, this issue has not been solved because of its complexity and many other influencing factors. Due to the increasing accuracy of machine learning (ML) in predicting surface deformation of shield tunneling and the development of automated machine learning (AutoML) technology. In the study, different ML prediction models were constructed using an open source AutoML framework. The prediction model was trained by the dataset, which contains 14 input parameters and an output (i.e., Smax). Different AutoML frameworks were employed to compare their validities and efficiencies. The performance of the model is estimated by contrasting the prediction accuracy parameters, including root mean square error (RMSE), mean absolute error (MAE) and determinant coefficient (R²).With a coefficient of determination (R²) of 0.808, MAE of 3.7, and RMSE of 5.2 on the testing dataset, the best prediction model i.e., extra tree regressor showed better performance, proving that our model has advantages in predicting Smax. Furthermore, the SHAP analysis reveal that the soil type (ST), torque (To), cover depth (H), groundwater level (GW), and tunneling deviation have a significant effect on Smax compared to other model inputs.

This paper presents a novel type of deep foundation — an anchor foundation with root caissons, which improve the soil–caisson interaction using penetrating roots. A simplified analytical procedure is proposed for calculating responses of the new anchor foundation subjected to combined vertical, horizontal, and moment loadings. Caisson–soil interaction is simulated by a Winkler subgrade reaction model, with an improved Winkler spring constant to consider the reinforcement effect of roots. The method incorporates limiting soil stress to investigate soil nonlinear behavior and a transfer matrix to represent nonhomogeneous soils, with a passive caisson model accounting for group effects. The effectiveness of the present approach is evaluated by comparison with full-scale field load tests and a finite element analysis on a small-scale anchor foundation to give a preliminary design guideline for the Ma’anshan Yangtze River Bridge in China.