Search

Groundwater plays an essential role in stabilizing underground structures. However, hydrostatic uplift forces from groundwater can create safety hazards. This paper obtained the groundwater buoyancy reduction coefficients of 36 types of clays through model tests and conducted a finite element simulation to obtain the buoyancy reduction coefficients of additional clays with varying soil properties. Machine learning methods, including extreme gradient boosting (XGBoost) and random forest (RF) algorithms, were used to analyze and identify the soil parameters that have a significant impact on the reduction of groundwater buoyancy. It was found that the permeability coefficient and saturation are the primary factors that influence the reduction of groundwater buoyancy. Additionally, the prediction models developed by XGBoost and RF were compared, and their accuracy was evaluated. These research findings can serve as a reference for designing underground structures that can withstand the potential risk of buoyancy in clay.

Groundwater level change stands a momentous role in affecting the geotechnical construction stability and safety of underground structures. Global warming and active underground construction cause conspicuous changes in the groundwater level, which further leaves an impact on the underground structures’ serviceability. To reveal the interaction between underground structure and soil under groundwater level change in the sand layer, model tests of circular transportation tunnel and rectangular utility tunnel were carried out. With the self-designed experimental equipment and innovative experimental methods, the changes in tunnel stress, bending moment, buoyancy, and vertical displacement of the rise and drawdown of the groundwater level in the sand layer were studied. The results revealed the developments of concentrated structural forces during the rising and falling process of the groundwater water level, indicating critical locations that should be strengthened. Meanwhile, both tunnels showed the same movement trend: settling first, floating afterwards and settling at last. And it is concluded that no reduction is required when calculating buoyancy in sands using measured pore pressure. Conclusions can provide a notable reference for future related research and engineering designs.