Jet grouted piles are widely used to reduce post-construction settlement of soft clay roadbeds. Nevertheless, it is easy to cause ground heave due to the jet grouted pile. According to the analytical method and numerical method, a sensitivity analysis of the factors affecting ground heave caused by a single jet grouted pile was performed. It is found that the influence of each parameter on ground heave is in the following order: grout pump pressure > embankment load > soil type (including the cohesion, friction angle, and Young’s modulus) > pile diameter > pile length. Considering the effect of the pump pressure on the ground heave is more significant, based on the analytical method of ground heave caused by a single jet grouted pile combined with the solution of small-deflection bending of a circular thin plate, the calculation method for the suggested limit grout pressure for construction under different embankment heights was established. Suggested values of theoretical grout pump pressure were given to prevent ground heave from harming the pavement of operating highways. This study provides some theoretical basis for the subsequent research on the jet grouted pile.

Predicting soil deformation is critical for the success of building construction projects. The traditional methods used for this task, which rely on theoretical calculations and numerical simulations, require detailed information on soil characteristics and geological conditions. These essential details are often challenging to obtain in practical engineering, thereby limiting the accuracy of these methods in building construction contexts. Deep learning (DL) provides a direct approach for modeling soil deformation without having a detailed understanding of the soil properties and geological conditions. However, the existing DL algorithms mainly focus on modeling deformation directly. With advancements in monitoring technology, integrating diverse monitoring data has become crucial for accurately predicting deformation, a need often overlooked in current practices. This paper introduces a monitoring data fusion (MDF) model aimed at enhancing the utilization efficiency of diverse monitoring data. Validated against real-world engineering scenarios, this model significantly outperforms traditional single-feature and multi-feature long short-term memory (LSTM) models. It achieves a mean absolute percentage error (MAPE) of approximately 2.12%, representing reductions of 30% and 63%, and a root mean square error (RMSE) of around 12.5 mm, with reductions of 36% and 77%. Additionally, the DL interpretability method, Shapley additive explanations (SHAP), is utilized to elucidate how various model features contribute to generating predictions.

A series of vertical loading tests on stone columns based on transparent soil were conducted to investigate the failure modes and bearing characteristics of stone columns in layered soils. The influences of different layer thicknesses, different layer distributions, and different aggregate gradations on the bearing capacity of stone columns were examined. Based on the experimental results, a bearing capacity calculation method is proposed for stone columns subjected to bulging failures in lower soft soils. This new calculation method incorporates the self-weight of both the column and the surrounding soil. Verification through an engineering case study shows that, compared with the existing calculation methods, the outcomes derived from the proposed approach exhibit superior agreement with field measurements.