Recently, heavy rainfall events have been inducing devastating geo-disasters, floods, sediments and debris flows in different regions around Japan, causing severe damage to lives and properties. According to the Intergovernmental Panel on Climate Change (IPCC), the frequency and intensity of localized torrential rainfall events are expected to increase. This study initially highlights the increasing geo-disaster-inducing forces in relation to the deterioration of the social infrastructure and the decline in the labor forces in Japan. Furthermore, several geo-disasters within Kyushu Island, Japan, which seem to occur repeatedly, were analyzed considering the prevailed conditions and the adopted mitigation and prevention protocols. Consequently, the necessity for developing innovative systems and techniques that integrate the academic disciplines in collaboration with the residents and the government was evidently asserted. Moreover, the recent progress in establishing comprehensive geo-hazard vulnerability assessment methods and techniques that consider the regional characteristics, mainly Kyushu and Hokkaido islands, was introduced.

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.

Through this paper, a sampling methodology and a novel full automatic system adopting the continuous pressurization method which is capable of determining the Soil Water Characteristics Curve (SWCC) for both remoulded and undisturbed samples in a very short time were developed. The proposed system was validated by comparing the SWCCs of standard testing soils obtained using the developed system to the SWCCs obtained using a conventional method. Remoulded and undisturbed natural soil samples were tested, where the degree of disturbance influence on the obtained SWCC was discussed. In addition, the undisturbed samples containing moulds material influence on the obtained SWCC was investigated. It was found that remoulded samples do not properly represent the in-situ conditions with significant error that should be carefully considered when conducting analysis and proposing countermeasures against unsaturated soils related Geo-disasters. In addition, the material which the containing mould is made from has minor influence on the obtained SWCC which can be neglected. Finally, it can be concluded that the developed undisturbed soil water characteristics curve obtaining system is direct, rapid, reliable and simple. In addition, the proposed undisturbed sampling and testing methodology can be used to accurately evaluate the spatial variations of the SWCC regardless the heterogeneity of the soil profile.