A hybrid machine learning model for landslide-oriented risk assessment of long-distance pipelines.

Preparation of pipeline risk zoning is essential for pipeline construction and safe operation. Landslides are one of the main sources of risk to the safe operations of oil and gas pipelines in mountainous areas. This work aims to propose a quantitative assessment model of landslide-induced long-distance pipeline risk by analyzing historical landslide hazard data along oil and gas pipelines. Using the Changshou-Fuling-Wulong-Nanchuan (CN) gas pipeline dataset, two independent assessments were carried out: landslide susceptibility assessment and pipeline vulnerability assessment. Firstly, the study combined the recursive feature elimination and particle swarm optimization-AdaBoost method (RFE-PSO-AdaBoost) to develop a landslide susceptibility mapping model. The RFE method was used to select the conditioning factors, while PSO was used to tune the hyper-parameters. Secondly, considering the angular relationship between the pipelines and landslides, and the segmentation of the pipelines using the fuzzy clustering (FC), the CRITIC method (FC-CRITIC) was combined to develop a pipeline vulnerability assessment model. Accordingly, a pipeline risk map was obtained based on pipeline vulnerability and landslide susceptibility assessment. The study results show that almost 35.3% of the slope units were in extremely high susceptibility zones, 6.68% of the pipelines were in extremely high vulnerability areas, the southern and eastern pipelines segmented in the study area were located in high risk areas and coincided well with the distribution of landslides. The proposed hybrid machine learning model for landslide-oriented risk assessment of long-distance pipelines can provide a scientific and reasonable risk classification for new planning or in service pipelines to avoid landslide-oriented risk and ensure their safe operation in mountainous areas.

Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model.

The spatial heterogeneity of landslide influencing factors is the main reason for the poor generalizability of the susceptibility evaluation model. This study aimed to construct a comprehensive explanatory framework for landslide susceptibility evaluation models based on the SHAP (SHapley Additive explanation)-XGBoost (eXtreme Gradient Boosting) algorithm, analyze the regional characteristics and spatial heterogeneity of landslide influencing factors, and discuss the heterogeneity of the generalizability of the models under different landscapes. Firstly, we selected different regions in typical mountainous hilly region and constructed a geospatial database containing 12 landslide influencing factors such as elevation, annual average rainfall, slope, lithology, and NDVI through field surveys, satellite images, and a literature review. Subsequently, the landslide susceptibility evaluation model was constructed based on the XGBoost algorithm and spatial database, and the prediction results of the landslide susceptibility evaluation model were explained based on regional topography, geology, and hydrology using the SHAP algorithm. Finally, the model was generalized and applied to regions with both similar and very different topography, geology, meteorology, and vegetation, to explore the spatial heterogeneity of the generalizability of the model. The following conclusions were drawn: the spatial distribution of landslides is heterogeneous and complex, and the contribution of each influencing factor on the occurrence of landslides has obvious regional characteristics and spatial heterogeneity. The generalizability of the landslide susceptibility evaluation model is spatially heterogeneous and has better generalizability to regions with similar regional characteristics. Further explanation of the XGBoost landslide susceptibility evaluation model using the SHAP method allows quantitative analysis of the differences in how much various factors contribute to disasters due to spatial heterogeneity, from the perspective of global and local evaluation units. In summary, the integrated explanatory framework based on the SHAP-XGBoost model can quantify the contribution of influencing factors on landslide occurrence at both global and local levels, which is conducive to the construction and improvement of the influencing factor system of landslide susceptibility in different regions. It can also provide a reference for predicting potential landslide hazard-prone areas and for Explainable Artificial Intelligence (XAI) research.

Study on Machine Learning Models for Building Resilience Evaluation in Mountainous Area: A Case Study of Banan District, Chongqing, China.

'Resilience' is a new concept in the research and application of urban construction. From the perspective of building adaptability in a mountainous environment and maintaining safety performance over time, this paper innovatively proposes machine learning methods for evaluating the resilience of buildings in a mountainous area. Firstly, after considering the comprehensive effects of geographical and geological conditions, meteorological and hydrological factors, environmental factors and building factors, the database of building resilience evaluation models in a mountainous area is constructed. Then, machine learning methods such as random forest and support vector machine are used to complete model training and optimization. Finally, the test data are substituted into models, and the models' effects are verified by the confusion matrix. The results show the following: (1) Twelve dominant impact factors are screened. (2) Through the screening of dominant factors, the models are comprehensively optimized. (3) The accuracy of the optimization models based on random forest and support vector machine are both 97.4%, and the F1 scores are greater than 94.4%. Resilience has important implications for risk prevention and the control of buildings in a mountainous environment.

Comparison of Random Forest Model and Frequency Ratio Model for Landslide Susceptibility Mapping (LSM) in Yunyang County (Chongqing, China).

To compare the random forest (RF) model and the frequency ratio (FR) model for landslide susceptibility mapping (LSM), this research selected Yunyang Country as the study area for its frequent natural disasters; especially landslides. A landslide inventory was built by historical records; satellite images; and extensive field surveys. Subsequently; a geospatial database was established based on 987 historical landslides in the study area. Then; all the landslides were randomly divided into two datasets: 70% of them were used as the training dataset and 30% as the test dataset. Furthermore; under five primary conditioning factors (i.e., topography factors; geological factors; environmental factors; human engineering activities; and triggering factors), 22 secondary conditioning factors were selected to form an evaluation factor library for analyzing the landslide susceptibility. On this basis; the RF model training and the FR model mathematical analysis were performed; and the established models were used for the landslide susceptibility simulation in the entire area of Yunyang County. Next; based on the analysis results; the susceptibility maps were divided into five classes: very low; low; medium; high; and very high. In addition; the importance of conditioning factors was ranked and the influence of landslides was explored by using the RF model. The area under the curve (AUC) value of receiver operating characteristic (ROC) curve; precision; accuracy; and recall ratio were used to analyze the predictive ability of the above two LSM models. The results indicated a difference in the performances between the two models. The RF model (AUC = 0.988) performed better than the FR model (AUC = 0.716). Moreover; compared with the FR model; the RF model showed a higher coincidence degree between the areas in the high and the very low susceptibility classes; on the one hand; and the geographical spatial distribution of historical landslides; on the other hand. Therefore; it was concluded that the RF model was more suitable for landslide susceptibility evaluation in Yunyang County; because of its significant model performance; reliability; and stability. The outcome also provided a theoretical basis for application of machine learning techniques (e.g., RF) in landslide prevention; mitigation; and urban planning; so as to deliver an adequate response to the increasing demand for effective and low-cost tools in landslide susceptibility assessments.

Effects of seepage and weak interlayer on the failure modes of surrounding rock: model tests and numerical analysis.

The presence of weak interlayers and groundwater are common adverse geological conditions in tunnels. To investigate the modes of failure of rock masses surrounding tunnels owing to weak interlayers and groundwater, model tests and numerical simulations were conducted in this study based on two cases, and a model that considers only the weak interlayer was conducted for comparison. Based on the tests, differences between two models in terms of rock pressure, displacement, cracks and strain were analysed. The results reveal that the presence of groundwater has a significant effect on the space-time distribution of stress, displacement and cracks in the surrounding rock. Furthermore, based on the numerical model, the seepage field was analysed in terms of pore water pressure, permeability and the seepage process to understand the joint action of groundwater and weak interlayer on the failure mechanism of tunnels. The results show that the groundwater and interlayer complement each other to induce the failure mode of the surrounding rock. The water accelerates slip in the interlayer and the development of cracks. Conversely, low strength, muddy weak interlayers serve as the channels of water flow, resulting in deformations and cracks at different locations and different failure modes.