Taking the Niumian Gully landslide–debris-flow geohazard chain as an example, we analyze the disaster mechanism of the landslide–debris-flow geohazard chain and its evolution process through field investigation as a reference for disaster prevention and risk reduction in areas with strong earthquakes by analyzing the accumulative sliding amount and the critical rainfall for debris flow formed by loose deposits. Due to the 8.0 Ms earthquake in Wenchuan, the cumulative sliding of the slope reached 230.51 m, much greater than the critical sliding in the Longmen Mountain earthquake area. Permanent damage to the slope occurred, resulting in a landslide, which provided the material source for the occurrence of debris flows. When the study area experienced concentrated rainfall (e.g., exceeding 10.31 mm/h or 54.67 mm/d), loose deposits in the basin began to form a debris flow, causing a landslide–debris-flow geohazard chain. During the evolution process of the geohazard chain, the following stages were observed: pre-earthquake gestation, landslide starting during a strong earthquake, landslide blocking a channel and forming a dammed lake, bursting of the dammed lake flood–debris-flow, sliding of loose deposits, and reciprocating loose-deposit sliding and debris flows. Thus, the formation of the Niumian Valley geohazard chain can be attributed to the combined result of strong earthquake activities and rainfall. In addition, under the action of rainfall, the occurrence of the debris flow and unstable sliding of loose deposits also caused the reciprocating occurrence of debris flows, loose-deposit sliding, and flood-induced debris flows in the study area.

In order to improve the effectiveness of coal mine gas control and enhance the level of coal mine safety production, the application of a microseismic monitoring system and hydraulic fracturing technology in coal mines was studied. Applying hydraulic fracturing technology to coal mine gas treatment, firstly, the geological structure and gas concentration in the mining area are detected using the radio tunnel perspective method and infrared differential absorption method. Then, the relevant parameters of hydraulic fracturing are determined, and finally, hydraulic fracturing technology is implemented. Microseismic monitoring technology is used to monitor the cracks formed during hydraulic fracturing construction and evaluate the fracturing effect. The instantaneous energy envelope is obtained from the microseismic data of each detection channel after stacking and Hilbert transform static correction. A microseismic in-phase inversion positioning objective function based on travel time residuals is constructed, and under the constraints of polarization analysis, the optimal solution is obtained through search iteration to complete microseismic in-phase inversion positioning. Experimental results have shown that after applying this method to coal mine gas control, the gas concentration decreases below the execution standard, achieving good control effects. Under microseismic monitoring in coal mines, the hydraulic fracturing effect can be effectively and reasonably evaluated, and the safety production level of coal mines can be improved.

In recent years, debris flow disasters have occurred frequently along the highway, causing river blockages and road interruptions, which seriously threaten the safety of people's lives and property. Highway G318 is an important throat project linking Sichuan and Tibet; at the same time, it is an important channel for the economic development of Sichuan and Tibet and the transportation of national defense materials. Taking the Linzhi–Lhasa Section of Highway G318 as an example, this study analyses the distribution law and characteristics of coupling factors of debris flows in the study area (under its topographical, hydrometeorological, geological, and structural conditions) using remote sensing interpretation, field surveys, and mathematical statistics. The research shows that: (1) The types and quantity of debris flows in the region show statistical laws under the factors of the slope, slope aspect, drainage area, and gradient of the gully. The vegetation coverage in the upper reaches of the Nyang River valley gradually decreases, and the average debris flow disaster density is 0.529/km, which is the most densely distributed area of debris flow. (2) The distribution density of regional debris flows in narrow valleys is greater than that in wide valleys, and those in the Nyang River basin are greater than those in the Lhasa River basin. (3) By comparing the tectonic geological map and the debris flow distribution map, it was found that the debris flow distribution is controlled by faults, and 71% of the debris flow basins have faults. (4) There is a significant positive correlation between the gradient of the material source area and the gradient of the debris flow gully, as well as a close positive correlation between the rainfall and the fault density, and a close negative correlation between the average gradient and the drainage area. Due to the unique topography and geomorphology of different regions, a difference in meteorology and hydrology occurred. This further affected the topography, geomorphology, and distribution of debris flow disasters. Based on the study of the distribution law of regional debris flow and geological environmental factors, this study provides strong support for regional debris flow prevention and related research.

With the continuous increase in global climate change and human activities, the risk of sudden debris flow disasters is becoming increasingly severe. In order to effectively evaluate and zone the potential hazards of debris flows, this paper proposes a method for zoning the potential sudden hazards of debris flows based on deep neural networks. According to hazard identification, ten risk indicators of potential sudden debris flows are determined. The risk indicators of a potential sudden debris flow in each region were used as the input factors of a deep trust network (DBN) composed of a back propagation (BP) neural network and a restricted Boltzmann machine (RBM). The DBN is pre-trained using the contrast divergence method to obtain the optimal value of the parameter set of the DBN model, and a BP network is set at the last layer of the DBN for fine-tuning to make the network optimal. Using the DBN model with the best parameters, the risk probability of debris flows corresponding to each region is taken as an output. The risk grade is divided, the risk degree of potential sudden debris flow in each region is analyzed, and the potential sudden debris flow risk in each region is divided individually. The results show that this method can effectively complete the risk zoning of sudden debris flow. Moreover, the cumulative contribution of the indicators selected by this method is significant, and the correlation of indicators is not significant, which can play a role in the risk assessment of potential sudden debris flow. This study not only provides new ideas and methods for risk assessment of sudden debris flow disasters, but also fills a gap in the field of geological hazard susceptibility mapping.

Based on an improved genetic algorithm and debris flow disaster monitoring network, this study examines the monitoring and early warning method of debris flow expansion behavior, divides the risk of debris flow disaster, and provides a scientific basis for emergency rescue and post-disaster recovery. The function of the debris flow disaster monitoring network of the spreading behavior disaster chain is constructed. According to the causal reasoning of debris flow disaster monitoring information, the influence factors of debris flow, such as rainfall intensity and duration, are selected as the inputs of the Bayesian network, and the probability of a debris flow disaster is obtained. The probability is compared with the historical data threshold to complete the monitoring and early warning of debris flow spreading behavior. Innovatively, by introducing niche technology to improve traditional genetic algorithms by learning Bayesian networks, the optimization efficiency and convergence speed of genetic algorithms are improved, and the robustness of debris flow monitoring and warning is enhanced. The experimental results show that this method divides debris flow disasters into the following five categories based on their danger: low-risk area, medium-risk area, high-risk area, higher-risk area, and Very high-risk area. It accurately monitors the expansion of debris flows and completes early warning. The disaster management department can develop emergency rescue and post-disaster recovery strategies based on early warning results, thus providing a scientific basis for debris flow disasters. The improved genetic algorithm has a higher learning efficiency, a higher accuracy, a faster convergence speed, and higher advantages in learning time and accuracy of the Bayesian network structure.