Increasing development of infrastructure in Indonesia has driven the need for effective ground improvement methods to accelerate the consolidation of soft soil, which is estimated to occupy around 10% of the country’s land area. A prefabricated vertical drain combined with vacuum preloading is among the most effective methods for this purpose. However, the prefabricated vertical drain creates a smear zone in the surrounding soil area during installation. This study examines the effectiveness of a newly developed mandrel system in reducing the smear zone during prefabricated vertical drain installation. Large-scale consolidation tests at a macro level and microstructure analysis using scanning electron microscopy at a micro level were employed to investigate the effect of soil water content and shear strength. The results show that the water content and shear strength of the soft soil gradually increased in the inner smear zone and transition zone, while both decreased in the radial distance. Furthermore, the soil structure underwent a transformation in which the particle area and pore area became a closed flake structure, and apparent agglomeration occurred. The test results indicate that the newly developed mandrel system can effectively reduce the smear zone. The macro to micro test results demonstrated that the mandrel system is successful in reducing the smear zone effect.

By comparing different settlement forecast methods, eight methods were selected considering the creep of marine soft soils in this case study, including the Hyperbolic Method (HM), Exponential Curve Method (ECM), Pearl Growth Curve Modeling (PGCM), Gompertz Growth Curve Modeling (GGCM), Grey (1, 1) Model (GM), Grey Verhulst Model (GVM), Back Propagation of Artificial Neural Network (BPANN) with Levenberg–Marquardt Algorithm (BPLM), and BPANN with Gradient Descent of Momentum and Adaptive Learning Rate (BPGD). Taking Lingni Seawall soil ground improved with prefabricated vertical drain-assisted staged riprap filling as an example, forecasts of the short-term, medium-term, long-term, and final settlements at different locations of the soft ground were performed with the eight selected methods. The forecasting values were compared with each other and with the monitored data. When relative errors were between 0 and −1%, both the forecasting accuracy and engineering safety were appropriate and reliable. It was concluded that the appropriate forecast methods were different not only due to the time periods during the settlement process, but also the locations of soft ground. Among these methods, only BPGD was appropriate for all the time periods and locations, such as at the edge of the berm, and at the center of the berm and embankment.