Oil and gas pipelines are part of long-distance transportation projects which pass through areas with complex geological conditions and which are prone to geological disasters. Geological disasters significantly affect the safety of pipeline operations. Therefore, it is essential to conduct geological disaster risk assessments in areas along pipelines to ensure efficient pipeline operation, and to provide theoretical support for early warning and forecasting of geological disasters. In this study, the pipeline routes of the Sichuan-Chongqing and Western Hubei management offices of the Sichuan-East Gas Transmission Project were studied. Seven topographic factors—surface elevation, topographic slope, topographic aspect, plane curvature, stratum lithology, rainfall, and vegetation coverage index—were superimposed using the laying method with a total of eight evaluation indicators. The quantitative relationships between the factors and geological disasters were obtained using the geographic information system (GIS) and weight of evidence (WOE). The backpropagation neural network (BP) was optimised using a genetic algorithm (GA) to obtain the weight of each evaluation index. The quantified index was then utilized to identify the geological hazard risk zone along the pipeline. The results showed that the laying method, stratum lithology, and normalised difference vegetation index were the factors influencing hazards.

Drifting snow, the flow of dispersed snow particles near ground level under the action of wind, is a major form of snow damage. When drifting snow occurs on railways, highways, and other transportation lines, it seriously affects their operational safety and results in drifting snow disasters. Drifting snow disasters frequently occur in the high latitudes of northwest China. At present, most scholars are committed to studying the prevention and control measures of drifting snow, but the prerequisite for prevention is to effectively evaluate the susceptibility of drifting snow along railways and highways to identify areas with a high risk of occurrence. Taking the Xinjiang Afukuzhun Railway as an example, this study uses a geographic information system (GIS) combined with on-site monitoring and surveys to establish a drifting snow susceptibility evaluation index system. The drifting snow susceptibility index (DSSI) is calculated through the weight of an evidence (WOE) model, and a genetic algorithm backpropagation (GA-BP) algorithm is used to obtain optimised evaluation index weights to improve the accuracy of model evaluation. The results show that the accuracies of the WOE model, WOE backpropagation (WOE-BP) model, and weight of evidence genetic algorithm backpropagation (WOE-GA-BP) model are 0.747, 0.748, and 0.785, respectively, indicating that the method can be effectively applied to evaluate drifting snow susceptibility.

As an important connecting channel between cities, roads are one of the main elements in urban development infrastructure. The stability evaluation of the roadbed slope runs through the entire life cycle, especially during the operation stage. However, under extreme weather conditions, especially heavy rainfall, the roadbed slope may become unstable, thus endangering operational safety. Therefore, it is necessary to conduct precise dynamic assessments of slope stability. However, due to site limitations, it is often not possible to obtain accurate mechanical parameters of a slope using traditional survey methods when deformation and failure have already occurred. In this study, building upon our existing parameter inversion model, the improved backpropagation genetic algorithm non-dominated sorting genetic algorithm II model (BPGA-NSGA-II), in-depth research was conducted on the selection of key parameters for the model. This study utilized monitoring data to perform an inversion analysis of the real-time mechanical parameters of the slope. Subsequently, the inverted parameters were applied to dynamically assess the stability of the slope. The calculation results demonstrate that the slope safety factor decreased from an initial value of 1.212 to 0.800, which aligns with actual monitoring data. This research provides a scientifically effective method for the dynamic stability assessment of slopes.