Collapses, landslides, and debris flows are the main geological hazards faced by mankind, which bring heavy losses of life and property to people every year. The purpose of this paper is to establish a method for determining the optimal weighting scheme for multiple geological hazard susceptibility mapping. The information gain ratio (IGR) method was used to analyze the predictive ability of the conditioning factors. The support vector machine (SVM) algorithm was used to evaluate the susceptibility to collapse, landslide, and debris flow of the study area. The receiver operating characteristic curves (ROC) and classification statistics of geological hazard samples were applied to evaluate the performance of the models. The analytic hierarchy process (AHP) and frequency ratio (FR) method were combined to determine the optimal weighting scheme for collapse, landslide, and debris flow. All the conditioning factors have shown a certain predictive ability, making the models of collapse, landslide, and debris flow achieve very good performance. The multiple geological hazard susceptibility maps with the weights of 0.297, 0.539, and 0.164 for collapse, landslide, and debris flow was optimal for this study area with high-precision classification of all the geological hazard samples. The conclusions of this paper could provide meaningful references for risk migration and land use in the study area.

Debris flow susceptibility mapping (DFSM), which has proven to be one of the most effective tools for risk management, faces a variety of problems. To realize the rational use of debris flow sample resources and improve the modeling efficiency, a unified model based on transfer learning was established for cross-regional DFSM. First, samples with 10 features collected from two debris flow-prone areas were separately used to perform factor prediction ability analysis (FPAA) based on the information gain ratio (IGR) method and then develop traditional machine learning models based on random forests (RF). Secondly, two feature matrices representing different areas were projected into a common latent feature space to obtain two new feature matrices. Then, the samples with new features were used together for FPAA and developing a unified machine learning model. Finally, the performance of the models was obtained and compared based on the area under curves (AUC) and some statistical results. All the conditioning factors played different roles in debris flow prediction in the two study areas, based on which two traditional models and a unified model were established. The unified model based on feature transferring realized efficient cross-regional modeling, solved the unconvincing problem of limited sample modeling, and enabled more accurate identification of some debris flow samples.

Secondary compression studies can provide insights for evaluating the engineering potential and environmental impact of soil. The objective of this research was to investigate the effect of bound water content on the secondary compression of marine silty clay. To this end, a novel method was established based on thermogravimetric analysis (TGA) to determine the contents and limits of strongly bound water and weakly bound water for three typical marine silty clays including Tianjin mucky silty clay (TJ), Qingdao mucky silty clay (QD), and Weihai silty clay (WH). A total of 17 groups of uniaxial confined compression tests were performed for reconstituted samples at different absolute water contents under the condition of multistage loading to investigate their secondary compression characteristics. The results show that the initial dehydration temperature of strongly bound water (T_s) corresponds to the peak of the derivative thermogravimetry (DTG) curve. The values of T_s for TJ, QD and WH are 112.35 °C, 109.67 °C and 118.46 °C, respectively. The initial dehydration temperatures of weakly bound water (T_w) for TJ, QD and WH are 55.26 °C, 52.56 °C and 56.56 °C, respectively. The secondary compression coefficient C_α changes little before the strongly bound water limit and increases dramatically as weakly bound water content increases at the same vertical stress. A piecewise linear model and a quadratic polynomial model are established for calculating the average secondary compression coefficient from bound water content. Weakly bound water is the determining factor controlling secondary compression. Increasing the bound water content weakens the connection force and friction force among the particles and the viscosity of weakly bound water. The results will guide decisions on long-term settlement assessment and facilitate understanding of the secondary compression mechanism of marine silty clays affected by bound water.