Human Engineering Activities Research Articles

Development and Comparison of InSAR-Based Land Subsidence Prediction Models

Land subsidence caused by human engineering activities is a serious problem worldwide. We selected Qian’an County as the study area to explore the evolution of land subsidence and predict its deformation trend. This study utilized synthetic aperture radar interferometry (InSAR) technology to process 64 Sentinel-1 data covering the area, and high-precision and high-resolution surface deformation data from January 2017 to December 2021 were obtained to analyze the deformation characteristics and evolution of land subsidence. Then, land subsidence was predicted using the intelligence neural network theory, machine learning methods, time-series prediction models, dynamic data processing techniques, and engineering geology of ground subsidence. This study developed three time-series prediction models: a support vector regression (SVR), a Holt Exponential Smoothing (Holt) model, and multi-layer perceptron (MLP) models. A time-series prediction analysis was conducted using the surface deformation data of the subsidence funnel area of Zhouzi Village, Qian’an County. In addition, the advantages and disadvantages of the three models were compared and analyzed. The results show that the three developed time-series data prediction models can effectively capture the time-series-related characteristics of surface deformation in the study area. The SVR and Holt models are suitable for analyzing fewer external interference factors and shorter periods, while the MLP model has high accuracy and universality, making it suitable for predicting both short-term and long-term surface deformation. Ultimately, our results are valuable for further research on land subsidence prediction.

A Small-Scale Landslide in 2023, Leshan, China: Basic Characteristics, Kinematic Process and Cause Analysis

Sudden mountain landslides can pose substantial threats to human lives and property. On 4 June 2023, a landslide occurred in Jinkouhe District, Leshan City, Sichuan Province, resulting in 19 deaths and 5 injuries. This study, drawing on field investigations, geological data, and historical imagery, elucidates the characteristics and causes of the landslide and conducts a reverse analysis of the landslide movement process using Massflow V2.8 numerical simulation software. The results indicate that rainfall and human engineering activities are key factors that triggered this landslide. Numerical simulation shows that the landslide stopped after 60 s of sliding, with a movement distance of approximately 286 m, a maximum sliding speed of 17 m/s, and a maximum accumulation thickness of 7 m, eventually forming a loose landslide debris accumulation of approximately 5.25 × 103 m3. The findings of this study provide significant reference value for research on landslide movement characteristics and disaster prevention and mitigation in mountainous areas.

Landslide risk assessment combining kernel extreme learning machine and information value modeling-A case study of Jiaxian Country of loess plateau, China

Landslide risk mapping can be an effective reference for disaster mitigation and land use planning, but the modelling process involves multidisciplinary knowledge which leads to its complexity. In this study, Jiaxian County in Shaanxi Province on the Loess Plateau of China, served as the study area, primarily characterized by Quaternary loess-covered geomorphology, with an average rainfall of about 400 mm annually. Soil erosion and human engineering activities have contributed to significant slope failures, posing threats to local residents and infrastructure. A reasonable inventory of landslides in the region was established by field survey combined with aerial imagery, allowing for characterization of their development and spatial distribution. Nine thematic maps related to landslide occurring and three vulnerability maps were prepared as influencing factors for landslide risk assessment. Subsequently, landslide susceptibility and hazard were evaluated using a kernel extreme learning machine (KELM) and information value (IV) model, followed by map validation. A decision table was then employed to generate the landslide risk map. The results of landslide hazard mapping showed that the historical landslide events were mainly developed in the central part of the study area, particularly concentrated near the developed river network. Integration of overall risk elements suggested that landslide risks in the study area were generally at a low level. Besides, a total of 0.25 % and 2.05 % of the areas were classified as having very high and high landslide risk levels, respectively, where 65.11 % of inventory landslides occurred. Therefore, the proposed procedure is a valuable tool for assessing landslide risk in Jiaxian Country.

Investigation of planar sliding deformation and analysis of the damage mechanism of a rocky landslide in Yaoping triggered by highway excavation in Hubei, China

During projects to build roads in China's mountainous areas, which are often characterized by the poor stability of rocky slopes, cases of deformation damage occur frequently. Because of the wide distribution of rocky landslides in the smooth layer, the unavoidable perturbation caused by engineering construction and the seriousness of landslide disasters, the destruction of this type of landslide and the research into prevention of the mechanism cannot be ignored. On 6 February 2023, a rock slide occurred in Yaoping village, Hubei Province, China. Using field investigations, Google satellite images, unmanned aerial vehicle photography, indoor testing and numerical simulations, we analysed the geological situation, deformation characteristics, damage process and triggering mechanism. The results show that the Yaoping landslide is a typical downward plane-sliding rock slide induced by the excavation of a highway. When strain softening occurs, the shear strength and friction coefficient of the slip zone soil are significantly reduced. Excavation caused the factor of safety of the slope to decrease substantially, with a maximum decrease rate of 60.7%. Excavation is considered to be the extrinsic factor that triggered the occurrence of the Yaoping landslide, while the reduction of landslide resistance caused by strain softening of the soil in the slip zone is the intrinsic direct factor that led to the occurrence of this type of landslide. The Yaoping landslide has obvious traction landslide characteristics. The landslide from deformation to destruction has four stages: creep at the leading edge of the landslide; traction deformation in the middle and back of the landslide; slip belt softening; and integral sliding. The prevention and control of this type of landslide requires a larger scope and depth of investigation, in order to identify in advance the possible soft surface in the rock layer, to speculate on the possible formation of landslide destruction mode, and to determine the support scheme and scope according to the geological conditions of the slopes on both sides of the highway. The slip zone soil of the Yaoping landslide was used to obtain the strength index of slip zone soil, which provides data support for the overall deformation characterization of the landslide. The results can provide a reference for the risk management and prevention of rock slides caused by human engineering activities during the excavation of roads.

Vulnerability assessment of landslides along the Yunnan section of the Northern Tropic of Cancer based on fuzzy evidence weight model

AbstractFrequent geological disasters pose significant threats to both human lives and property. High-risk landslides, with features such as rapid occurrence, wide distribution, and strong destructiveness, are of particular concern. To investigate the distribution characteristics and threat range of landslides, the Yunnan section of the Northern Tropic of Cancer was selected as the study area. Based on the fuzzy evidence weight model and using a grid size of 1000 m × 1000 m as the study unit, a vulnerability assessment of landslides along the Northern Tropic of Cancer in Yunnan was conducted. This assessment involved constructing a set of 13 evaluation indicator factors from three aspects: geological environment, geographical environment, and human engineering activities. The assessment results were subsequently subjected to precision verification. The results are as follows: (1) The overall vulnerability of landslides in the Yunnan section of the Northern Tropic of Cancer is moderate, covering an area of 25,968.79 km2. This area constitutes the largest proportion, accounting for 46.30% of the entire study area and is primarily distributed in counties such as Yanshan, Funing, and Shuangjiang. The highly vulnerable area covers 15,942.27 km2, representing 28.43% of the total study area. This region is mainly distributed in counties such as Gejiu, Yuanjiang, and Mojiang. (2) The main triggering factors for landslides are twofold: first, large-scale slope instability caused by excavation in human engineering activities, leading to extensive unstable slopes affected by long-term weathering and gravitational effects. Second, soil erosion resulting from land cultivation leads to the collapse and sliding of weathered and fragmented rocks under the influence of heavy rainfall and water erosion. During routine geological disaster patrols, special attention should be given to these factors, with a focus on implementing engineering measures in areas with more fragile geological environments. (3) Precision verification of the assessment results was conducted using both receiver operating characteristic (ROC) curves and Success rate curves. The area under the curve (AUC) values for the success rate curve and ROC curve were 0.85 and 0.74, respectively. The verification results showed high accuracy and feasibility of the evaluation method.

Study on the susceptibility of debris flow disasters in southeast Tibet based on the information content model and random forest model

Linzhi, in southeast of the Tibetan Plateau, has high mountain and gorge terrain. Recently, with rapid changes in climate and fast development of engineering construction in Tibet, the fragile ecological environment in Linzhi has been further damaged, resulting in a sharp increase in debris flow disasters in the region. This poses a serious threat to local social and economic development and safety of lives and property. We divided the study area into multiple watershed units, and explored the reliability of the information content model (ICM), random forest model (RF), and their coupled model (ICM-RF) in the evaluation of debris flow disaster susceptibility. Through remote sensing interpretation, field investigations, and data collection, data on debris flow disasters and evaluation indicators in the study area were obtained. Using multicollinearity analysis, 16 evaluation indicators were selected from 7 major categories including topography, geological conditions, meteorological and hydrological conditions, ecological environment conditions, human engineering activities, seismic activities, and watershed characteristics; a debris flow disaster susceptibility evaluation index system was constructed. Prediction performance of the three models was tested using ROC curves. ICM-RF model had better prediction performance than single models, indicating its superiority for predicting debris flow disaster susceptibility.

GIS-Based assessment of geological hazard susceptibility in Southeastern Tibetan region: An information entropy approach

The terrain and geological conditions in southeastern Tibetan region are complex, especially under the influence of hydraulic and hydroelectric development, and susceptibility to geological hazards has increased. This study focused on three counties in Changdu City. We aimed to assess the susceptibility to geological hazards in this region using Geographic Information System (GIS) technology and information entropy models. Historical geological hazard data from the local area, remote sensing data, and GIS were utilized to develop an information entropy model for landslide geological hazard analysis. Key triggering factors for landslide geological hazards in the southeastern Tibetan region were identified, and a comprehensive dataset was compiled. Information entropy model was applied to consider various influencing factors and calculate their impact on geological hazards, Landslide risk in the area was analyzed and generate a susceptibility map for geological hazards. Our results indicate significant correlations between factors, such as steep terrain, human engineering activities, and land types with landslide occurrences. The established evaluation model can reasonably predict potential geological hazard risk in Nujiang River region and partially reflect the distribution characteristics of geological hazards in the southeastern Tibetan region. This offers a scientific foundation for relevant authorities to formulate disaster prevention and response strategies.

Exploring the geological structure of a large-scale landslide using semi-airborne TEM in the Karst area of southwest China

Abstract The karst strata in the southwestern mountainous areas of China are extensively developed, creating a fragile geological environment. Landslide geological disasters occur frequently in these areas due to high annual rainfall, concentrated time periods, and frequent human engineering activities. Conventional ground geophysical methods face challenges in complex terrains, making it difficult to quickly and reliably obtain underground structures in landslide-prone areas. The semi-airborne transient electromagnetic method (SATEM) combines ground-based transmission and airborne reception of electromagnetic responses. This method, characterized by large emission magnetic moment and rapid data collection in the air, offers advantages in detecting deep geological structures in complex terrain areas. This article presents the application of a newly developed loop source SATEM system, integrated with multi-rotor unmanned aerial vehicles (UAVs), to conduct deep geological structure detection experiments on a large-scale landslide. The inversion results clearly depict the spatial distribution of the Feixianguan Formation and Longtan Formation, as well as vertical fractures developed in the strata due to underground coal mining. The detection test demonstrates the applicability of the SATEM method in detecting underground structures in Karst Plateau special landform areas, providing a new detection approach for similar regions.

Study on the influence of slope shape with numerical calculation models on slope safety during slope excavation.

Under the influence of natural weathering and excavation in human engineering, slopes in nature have various slope shapes. In human engineering activities, the stability of different types of slopes formed by manual excavation must be affected by multiple factors such as geologic setting, lithology and environment. Therefore, to understand the impact of slope shape, geologic setting, and other conditions on slope stability of artificial slopes, calculation models for straight slope, concave slope, and convex slope are constructed based on the three slope shape characteristics. By changing the angles of upward and downward slope angles and analysing the parameters of slope shape, joint spacing, and joint angle, discrete element software is used to calculate the slope safety factor. The calculation results show that the slope shape, joint spacing, and joint inclination affect the safety of slopes. In straight slopes with large joint spacing, the smaller the slope angle, the greater the safety factor. However, in the interval of small joint spacing, the safety coefficient of slopes with slight joint inclination has the opposite variation characteristics. When a<90°, the straight slope has a dominant joint inclination angle that minimises the slope safety factor. In concave slopes, the more concave the slope shape is, the smaller the safety factor is; For concave slopes with small joint spacing, the slope with slight joint inclination has a more significant safety factor; Under the condition of large joint spacing, there is a dominant joint inclination in the joint inclination range of 30° to 70° for concave slopes, which minimises the safety factor of the slope. In convex slopes, the smaller the joint inclination angle of the slope, the smaller the safety factor of the slope, and the smaller the upslope angle of the slope, the greater the safety factor of the slope.

Correction: Zeng et al. Tempo-Spatial Landslide Susceptibility Assessment from the Perspective of Human Engineering Activity. Remote Sens. 2023, 15, 4111

In the original publication [...]

Habitat Quality Assessment and Driving Factor Analysis of Xiangyu in Feng River Basin Based on InVEST Model

Analyzing the evolution of regional habitat quality is an important means to assess the impact of engineering activities on ecosystems. Taking Xiangyu in the Feng River Basin as the study area, the land use change in 1985 and 2022 was analyzed, and the habitat quality and degradation degree were evaluated by using the Integrated Assessment and Tradeoff of Ecosystem Services (InVEST) model. The results showed that from 1985 to 2022, the transfer of land use types in Xiangyu mainly occurred on dry land, bare land, forest land, and industrial land. The area of dry land and bare land converted into industrial land is 10,825.15 m2 and 249,123.09 m2, respectively, and affected by the measures of returning farmland to forest and grassland in Shaanxi Province, the area transferred to forest land reached 371,471.87 m2, mainly from dry land and bare land. The continuous expansion of industrial land led to a significant decline in habitat quality, and the areas with high habitat degradation were concentrated in forest land in a large range, which indicated that forest land was vulnerable to industrial land expansion. Land use change and human engineering activities are the main factors affecting the ecological environment, and limiting the expansion rate of industrial land is the key to protecting the ecological environment.

Risk zonation of submarine geological hazards in the Chengdao area of the Yellow River subaqueous delta

Submarine geological disasters occur frequently in the Chengdao area of the Yellow River subaqueous delta, which seriously threaten the safe operation of marine engineering in the region. Therefore, it is of great significance to carry out risk zonation for this region. The current study presents a detailed assessment of risk zones related to submarine geological hazards in this region based on analytical hierarchy process (AHP). The system of assessment index for risk zonation was established with four aspects of hydrodynamic condition, engineering geological environment, disaster geological conditions and human engineering activities. Eight geological hazard evaluation factors were selected and the distribution characteristics of each evaluation factor were discussed in detail by combining qualitative analysis and quantitative calculation. The risk level of submarine geological hazards in the Chengdao area are divided into four types: low risk, relatively low risk, relatively high risk, and high risk. The results show that the areas with a high geological hazard risk in this region are mainly distributed in the areas with water depths of 9–12 m, where the hydrodynamic effect is strong, with many human engineering activities, and seriously suffered from geologic hazards. The study results can provide scientific basis for engineering construction and hazard prevention in the Chengdao area.

Response Characteristics and Water Inflow Prediction of Complex Groundwater Systems under High-Intensity Coal Seam Mining Conditions

With the gradual improvement in coal mining efficiency, the disturbance of groundwater systems caused by high-intensity mining also increases, leading to challenges in maintaining mine safety and protecting water resources in mining areas. How to accurately describe the dynamic changes in the groundwater system under mining and quantitatively predict mine water inflow are currently major problems to be addressed. Based on a full analysis of the response characteristics of a groundwater system to the extraction disturbance, this paper presents a new method to establish a mine hydrogeological conceptual model that can accurately represent the water inrush process. The unstructured-grid package of MODFLOW is used to accurately characterize the formation structure and finally make accurate water inflow predictions. Taking the Caojiatan coal mine in Shaanxi Province, China, as an example, a numerical model of unstructured water inflow is established, and the changes in the water inflow source and intensity are quantitatively evaluated. Compared with the traditional water inflow prediction method, the prediction accuracy of the new model is improved by 12–17%, which is achieved by detailing the response of the complex groundwater system under high-intensity mining conditions. The method presented in this paper has great significance and applicatory value for obtaining a comprehensive understanding of the disturbance characteristics of human underground engineering activities (e.g., coal mining) on groundwater systems, as well as accurately predicting water inflow.

Landslide susceptibility assessment in Western Henan Province based on a comparison of conventional and ensemble machine learning

Landslide is a serious natural disaster next only to earthquake and flood, which will cause a great threat to people’s lives and property safety. The traditional research of landslide disaster based on experience driving or statistical model and its assessment results are subjective , difficult to quantify, and no pertinence. As a new research method for landslide susceptibility assessment, machine learning can greatly improve the landslide susceptibility model’s accuracy by constructing statistical models. Taking Western Henan for example, the study selected 16 landslide influencing factors such as topography, geological environment, hydrological conditions, and human activities. And 11 landslide factors with the most significant influence on the landslide were selected by the recursive feature elimination (RFE) method. There are five machine learning methods (Support Vector Machines (SVM), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Linear Discriminant Analysis (LDA)) were used to construct the spatial distribution model of landslide susceptibility. The models were evaluated by the receiver operating characteristic curve and statistical index. After analysis and comparison, the XGBoost model (AUC 0.8759) performed the best and was suitable for dealing with regression problems. The model had a high adaptability to landslide data. According to the landslide susceptibility map of the five models, the overall distribution can be observed. The extremely high and high susceptibility areas are distributed in the Funiu Mountain range in the southwest, the Xiaoshan Mountain range in the west, and the Yellow River basin in the north. These areas have large terrain fluctuations, complicated geological structural environments and frequent human engineering activities. The extremely high and highly prone areas were 12043.3 km² and 3087.45 km², accounting for 47.61% and 12.20% of the total area of the study area, respectively. Our study reflects the distribution of landslide susceptibility in western Henan Province, which provides a scientific basis for regional disaster warning, prediction, and resource protection. The study has important practical significance for subsequent landslide disaster management.

Risk Assessment and Control of Geological Hazards in Towns of Complex Mountainous Areas Based on Remote Sensing and Geological Survey

Mountainous areas have become among the most developed areas of geological hazards due to special geological environmental conditions and intensive human engineering activities. Geological hazards are a main threat to urbanization, rural revitalization, and new rural construction in complex mountainous areas. It is of great strategic significance to conduct large-scale geological hazard investigation and risk assessment in urban areas, control the risk of geological hazards at the source and propose risk control measures. In this paper, we established the technical methods of geologic hazard risk assessment and control in complex mountain towns by taking Longlin Town in the mountainous region of Gansu Longnan, China as the study area, with the Quanjia bay debris flows and Panping Village landslides as the typical pilot investigation and assessment. The methods consist of six stages—risk identification, hazard disaster model investigation, risk analysis, vulnerability assessment, risk evaluation and risk management and control measures and proposals. On this basis, the results of geological hazards with different precipitation frequencies (5%, 2%, 1%) are presented. The results show that 75.23% of the regions remained at low risk levels; 24.38% of the regions increased a risk level with decreasing precipitation frequency, and 0.39% of the regions remained at extremely high risk levels under different precipitation frequency conditions. For the Quanjia bay debris flows and Panping Village landslides case, we discussed the geological hazards risk source control contents, management and control technologies, engineering and non-engineering measures of disaster prevention and control for urban disasters and specific disaster areas. This research can provide technical support and reference for disaster prevention and mitigation, and territorial spatial planning.

Tempo-Spatial Landslide Susceptibility Assessment from the Perspective of Human Engineering Activity

The expansion of mountainous urban areas and road networks can influence the terrain, vegetation, and material characteristics, thereby altering the susceptibility of landslides. Understanding the relationship between human engineering activities and landslide occurrence is of great significance for both landslide prevention and land resource management. In this study, an analysis was conducted on the landslide caused by Typhoon Megi in 2016. A representative mountainous area along the eastern coast of China—characterized by urban development, deforestation, and severe road expansion—was used to analyze the spatial distribution of landslides. For this purpose, high-precision Planet optical remote sensing images were used to obtain the landslide inventory related to the Typhoon Megi event. The main innovative features are as follows: (i) the newly developed patch generating land-use simulation (PLUS) model simulated and analyzed the driving factors of land-use land-cover (LULC) from 2010 to 2060; (ii) the innovative stacking strategy combined three strong ensemble models—Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM)—to calculate the distribution of landslide susceptibility; and (iii) distance from road and LULC maps were used as short-term and long-term dynamic factors to examine the impact of human engineering activities on landslide susceptibility. The results show that the maximum expansion area of built-up land from 2010 to 2020 was 13.433 km2, mainly expanding forest land and cropland land, with areas of 8.28 km2 and 5.99 km2, respectively. The predicted LULC map for 2060 shows a growth of 45.88 km2 in the built-up land, mainly distributed around government residences in areas with relatively flat terrain and frequent socio-economic activities. The factor contribution shows that distance from road has a higher impact than LULC. The Stacking RF-XGB-LGBM model obtained the optimal AUC value of 0.915 in the landslide susceptibility analysis in 2016. Furthermore, future road network and urban expansion have intensified the probability of landslides occurring in urban areas in 2015. To our knowledge, this is the first application of the PLUS and Stacking RF-XGB-LGBM models in landslide susceptibility analysis in international literature. The research results can serve as a foundation for developing land management guidelines to reduce the risk of landslide failures.

Geological Hazard Assessment of Secondary Collapses Due to Volcanic Earthquakes on Changbai Mountain in China

In recent years, the volcanic activity of Changbai Mountain has been accompanied by several earthquakes, and the frequent human engineering activities have led to a gradual increase in the number of collapses in the region, which severely impacts residents’ lives and property safety. In northeastern China, the Changbai Mountain area in the southeastern Jilin Province is a typical mountain environment. This paper selects 12 evaluation indicators to build a hazard assessment system, including slope, aspect, elevation, curvature, lithology, NDVI, land use type, distance from the fault, the river from the road, volcanic earthquake, and annual average precipitation. Using emotional weight (G1 method) and objective weight (WOE-CV method), the hazard due to collapses in the study area is evaluated too. Among them, the transcendence probability of volcanic earthquakes greater than VI degree represents the relationship between Changbai Mountain volcanic earthquakes and the assessment of geological collapse hazard. The results show that high- and very high-hazard areas are mainly distributed in densely populated areas and national and provincial trunk lines, with apparent spatial agglomeration characteristics. The low-hazard area, medium-hazard area, high-hazard area and very high-hazard area accounted for 19.33%, 44.19%, 33.85% and 2.63% of the total area of the study area, respectively. By comparing the previous geological hazard survey reports in the area with the collapse hazard zoning map in this paper, 87.72% of the known collapse hazard areas are distributed within high and very high hazard zones, indicating that the conclusions of the article are more accurate and in line with the actual situation. Results from collapse-related hazards can provide relevant guidance for preventing and controlling geological risks posed by volcanic earthquakes affecting Changbai Mountain.

Landslide Risk Mapping Using the Weight-of-Evidence Method in the Datong Mining Area, Qinghai Province

Qinghai is rich in mineral resources, but frequent and large-scale mineral mining has caused secondary damage to the fragile primary surface and produced a large number of landslide disasters. In complex geological environments such as glacier ablation and frequent tectonic movements, a complete quantitative evaluation method for landslide risk in high-cold mining areas has not yet been formed. In view of this, this article uses the field survey and remote sensing data of the Datong mining area in Qinghai Province in 2012 as the basic data. We comprehensively considered five first-level factors (13 s-level factors) including topography, lithological structure, mining engineering activities, land use, and dynamic deformation as evaluation indicators for landslide susceptibility in mining areas, and used the Topographic Wetness Index (TWI) and the Human Engineering Activity Intensity (HEAI) to quantitatively estimate the hazard of landslide according to the landslide trigger mechanism. The weight-of-evidence approach was used for landslide hazard and risk mapping under different landslide--inducing conditions. The results indicate that the extremely high-hazard areas induced by human engineering activities account for 14% of the total area, and the extremely high-risk areas account for 13% of the total area in the Datong mining area, and the area of the extremely high-risk area is large; the landslide risk assessment mapping model constructed in this study can effectively evaluate the probability of slope instability caused by rainfall and human engineering activities. The effective value of the receiver operating characteristic (ROC) curve of the sensitivity assessment model reaches 0.863, and the evaluation results are consistent with reality; using the weight-of-evidence model for landslide risk assessment is more in line with the actual situation in alpine mining areas, and is more suitable for guiding landslide risk management and disaster prevention and mitigation in mining areas.

Slope Rock and Soil Mass Movement Geological Hazards Susceptibility Evaluation Using Information Quantity, Deterministic Coefficient, and Logistic Regression Models and Their Comparison at Xuanwei, China

In China, the majority of mountainous regions are characterized by complex topography and a delicate, sensitive geological environment. These areas, which exhibit insufficient infrastructure and widespread irrational human engineering activities, are often susceptible to geological hazards such as slope instability and soil mass movements. These geological hazards pose substantial threats to human lives and property, hindering the progress of mountainous areas. Therefore, conducting research on evaluating the vulnerability of slope rock and soil mass movement geological hazards (hereinafter referred to as geological hazards) is of utmost importance for hazard prevention, emergency management, and economic advancement in these regions. This study focuses on Xuanwei City and selects eight factors for evaluation, including elevation, gradient, slope aspect, normalized vegetation index, stratigraphic lithology, distance from faults, distance from rivers, and distance from roads. These factors are chosen based on a comprehensive analysis of the spatial and temporal distribution of geological hazards and hazard incubation conditions. Two paired models, the deterministic coefficient model + logistic regression model (CF+LR) and the information quantity model + logistic regression model (I+LR), were employed to assess the study area quantitatively. The performance of these models was assessed by employing receiver operating characteristic (ROC) curves and calculating the corresponding area under curve (AUC) values. The results indicate that: (1) The AUC values for the coupled CF+LR and I+LR models are 0.799 and 0.772, respectively. These results indicate that both models provide an objective and reliable assessment of the vulnerability to geological hazards, specifically slope rock and soil mass movements, in the study area. (2) Based on the CF+LR model calculations, the geological hazard susceptibility of Xuanwei City can be categorized into four zones: extremely high susceptibility (6.09%), high susceptibility (31.08%), medium susceptibility (32.26%), and low susceptibility (30.57%). (3) The CF+LR model more accurately represents the evaluation results and offers a strong reference value.

Ensemble learning framework for landslide susceptibility mapping: Different basic classifier and ensemble strategy

The application of ensemble learning models has been continuously improved in recent landslide susceptibility research, but most studies have no unified ensemble framework. Moreover, few papers have discussed the applicability of the ensemble learning model in landslide susceptibility mapping at the township level. This study aims at defining a robust ensemble framework that can become the benchmark method for future research dealing with the comparison of different ensemble models. For this purpose, the present work focuses on three different basic classifiers: decision tree (DT), support vector machine (SVM), and multi-layer perceptron neural network model (MLPNN) and two homogeneous ensemble models such as random forest (RF) and extreme gradient boosting (XGBoost). The hierarchical construction of deep ensemble relied on two leading ensemble technologies (i.e., homogeneous/heterogeneous model ensemble and bagging, boosting, stacking ensemble strategy) to provide a more accurate and effective spatial probability of landslide occurrence. The selected study area is Dazhou town, located in the Jurassic red-strata area in the Three Gorges Reservoir Area of China, which is a strategic economic area currently characterized by widespread landslide risk. Based on a long-term field investigation, the inventory counting thirty-three slow-moving landslide polygons was drawn. The results show that the ensemble models do not necessarily perform better; for instance, the Bagging based DT-SVM-MLPNN-XGBoost model performed worse than the single XGBoost model. Amongst the eleven tested models, the Stacking based RF-XGBoost model, which is a homogeneous model based on bagging, boosting, and stacking ensemble, showed the highest capability of predicting the landslide-affected areas. Besides, the factor behaviors of DT, SVM, MLPNN, RF and XGBoost models reflected the characteristics of slow-moving landslides in the Three Gorges reservoir area, wherein unfavorable lithological conditions and intense human engineering activities (i.e., reservoir water level fluctuation, residential area construction, and farmland development) are proven to be the key triggers. The presented approach could be used for landslide spatial occurrence prediction in similar regions and other fields.