Accurate landslide susceptibility maps are relevant for stakeholders to take effective measures and perform land use planning. The present research aims at using three data-driven approaches to generate landslide susceptibility map for the middle Yellow River catchment (northwest China) and comparing their performances, including the weighted information value (WIV), where the IV model was integrated with analytic hierarchy process (AHP), the support vector machine (SVM) and the random forest (RF) models. A landslide inventory map including 684 historical landslides was generated first by visual interpretation of remote sensing images combined with a field survey. A total of 14 thematic layers were applied to serve as the landslides influencing factors. The Pearson correlation coefficient analyzed the correlation among these factors, and the C5.0 decision tree algorithm determined the factor importance. The results demonstrated the correlation between every two factors were all less than 0.5. Three factors (including distance to road, distance to river, and slope) were the most important contributions to the landslide occurrences in the region, whereas five factors (including NDWI, plan curvature, profile curvature, surface roughness, and aspect) had minor importance. All the models predict that most of the historical landslides are identified in moderate and high susceptibility areas. For the prediction percentage of landslides in high susceptibility areas, both SVM and RF models exceed 70%. The RF model represented the best performance, with high susceptibility zones accounting for 21.9% and landslide numbers accounting for 90.5%. The comparison among the receiver operating characteristic curves indicated that the accuracy was higher in the RF model than in the other two models: the area under the curve (AUC) for the RF was 0.904, whereas that for the WIV and the SVM were 0.845 and 0.847, respectively. Hence, the RF was proven suitable for assessing the landslide susceptibility in the region. Current results can provide valuable references for future studies and landslide risk mitigation strategies.
In this study, an open-cut approach using steel-sheet piles and jet grouting piles for waterproofing was proposed to resolve the problem that ordinary pipe-jacking equipment cannot cross areas with existing anchor cables in soft stratum. The case history of a pipe-jacking project of a sewage treatment plant in the Jinan East Railway Station area was investigated. The mechanical properties of steel-sheet piles, horizontal displacement of piles, and ground surface settlement in the anchor-cable crossing area were investigated based on in situ observations. Numerical investigations were performed using the finite element method (FEM). The effects of existing anchor cables on the mechanical behaviors of retaining structures, deformation variation of the ground, and stability of the excavation were studied. The results indicate that the composite supporting structures of steel-sheet piles and jet grouting piles have a positive effect on waterproofing and deformation control in areas with existing anchor cables. When the steel-sheet pile touched the anchor cable during pile jacking, the compressive stress at the pile cap increased rapidly until it reached 62.8 MPa (the maximum pressure provided by the pile-pressing machine), which is twice the pressure under ordinary conditions. The maximum horizontal displacement of the retaining pile, δv, increased linearly with the excavation depth He. Existing anchor structures behind the excavation can restrain the deformation of the ground and retain the structure to a certain extent. The δv value of the pile with existing anchor structures behind is 6.5 mm or approximately 0.01% of the He value, which is 70% of that of the retaining pile without existing anchor structures. “Groove type” ground surface settlements are found on both sides of the excavation. The maximum ground settlements δh are 0.29% He and 0.05% He, respectively. The plastic zone at both sides of the excavation bottom extends to the ground surface with an angle of about 45°. When an excavation fails, the plastic zone range in the ground with existing anchor cables is significantly larger than it is in the ground without anchor cables. The key contribution of this research is to provide an effective and low-budget treatment for pipe-jacking crossing through an anchor-cable group region. The findings from this study also provide industry practitioners with a comprehensive guide regarding the specific applications and mechanical performance of the crossing excavation for obstacle treatment.
Landslide susceptibility assessment is an important support for disaster identification and risk management. This study aims to analyze the application ability of machine learning hybrid models in different evaluation units. Three typical machine learning models, including random forest forest by penalizing attributes (FPA) and rotation forest were merged by random subspace algorithm. Twelve evaluation factors, including elevation, slope angle, slope aspect, roughness, rainfall, lithology, distance to rivers, distance to roads, normalized difference vegetation index, topographic wetness index, plan curvature, and profile curvature, were extracted from 155 landslides in Yaozhou District, Tongchuan City, China. Six landslide susceptibility maps were generated based on the slope units divided by curvature and 30 m resolution grid units. Multiple performance metrics showed that the RS-RF model based on slope units has excellent spatial prediction ability. At the same time, the method of slope unit division based on curvature is proved to be more suitable for the typical Loess tableland regions, which provides basis for the selection of evaluation units in landslide susceptibility assessment.
Urbanization leads to changes in land use, and the expansion of impervious surfaces leads to an increase in flood vulnerability. Predicting and analyzing these landscape pattern changes are important in the early stages of urban planning. In practice, the threshold for obtaining comprehensive and detailed hydrological and meteorological data is high, which makes it difficult for landscape and urban planners to quickly evaluate urban floods. To compensate for these trends, we took Nanjing, China, as the study site and discussed the leading flood vulnerability landscape patterns based on quantitative assessments. We introduced catastrophe theory to integrate three indicators and seven subfactors for flood vulnerability assessment: exposure, including precipitation; sensitivity, including elevation, slope, soil and drainage density; and adaptability, including land use and forest coverage. Then, we calculated the landscape pattern metrics (shape index, fractal dimension index, related circumscribing circle, contiguity index and landscape division index) at the class level. Finally, we divided the city into four subregions, established regression models for the subregions and the whole city, and deduced the leading flood vulnerability landscape patterns in each region and the whole city. We found that the leading landscape patterns varied among different regions. According to the research results, the landscape pattern indexes identified in this paper can be interpreted intuitively, which can provide a reference for modifying the planning layout of regional green infrastructure, optimizing the vulnerability of urban floods, and providing a basis for further improving Nanjing urban planning and alleviating the urban flood vulnerability. The methods proposed herein also will benefit land use and green infrastructure management in other regions lacking meteorological and hydrological data.