Search

Introduction: This work employs a coupled evaluation model that integrates deterministic coefficients with the Analytic Hierarchy Process to conduct a comprehensive assessment of geological disaster susceptibility in Shenzhen Town, Ninghai County. Methods: Cascading geological disasters induced by typhoons and rainfall in the southeast coastal area of China are a major concern and cause huge losses of life and property every year. To effectively prevent and mitigate such disasters, it is necessary to evaluate the susceptibility of geological disasters. Taking geological disasters in Shenzhen Town, Ninghai County as the research object, eight influencing factors in terms of topographic and geomorphological conditions, engineering geological conditions, and human activities were selected based on the geographic information platform (GIS) in this work. The coupling model of the certainty factor model and analytic hierarchy process method was used to evaluate the susceptibility of geological hazards in the study area. Results: The evaluation results illustrate that the coupling model can accurately and objectively assess the susceptibility of geological hazards in this region, with a high evaluation accuracy of 80.8%. The susceptibility is greatly affected by slope, stratigraphic lithology, and human activities. The areas with extraordinarily high and high susceptibility were identified in the northwestern part of the study, where the ignimbrite is exposed in the steep topography. Discussion: The research method provides a reference for evaluating the susceptibility of geological hazards in the southeastern coastal region of China, and the evaluation results can provide recommendations for decision-making on disaster prevention and mitigation in this region. [ABSTRACT FROM AUTHOR]

Compared with large-scale geological disasters such as landslides and earthquakes, small-scale urban geological disasters such as collapses and ground fissures are often overlooked. However, the socioeconomic impacts of these small-scale events can often exceed those of larger disasters in major cities. Although the use of machine learning for susceptibility assessment is a well-established aspect of large-scale geological disaster prevention, insufficient disaster samples and resultant dataset imbalances have hindered its application to small-scale urban geological disasters. To address this issue, we propose a comprehensive process that involves defining disaster risk areas to expand disaster sample points, optimizing the extraction method for training and test sets to balance the dataset, and selecting models with high generalization capabilities to enhance prediction accuracy. By focusing on all urban road collapse incidents from 2015 to 2023 in Binjiang District, Hangzhou’s most economically developed areas, we demonstrated the reliability of this process. Furthermore, to support urban policymakers, we employed the SHAP model to demystify the predictive process and assess the impact of factors, providing reliable analytical results. Our approach provides a replicable and comprehensive solution for susceptibility assessments of cities impacted by small-scale geological disasters using machine learning and subsequent analyses. [ABSTRACT FROM AUTHOR]

Landslides are pervasive geological hazards that pose significant risks to human life, property, and the environment. Understanding landslide susceptibility is crucial for predicting and mitigating these disasters. This article advocates for a comprehensive review by systematically compiling and analyzing 146 relevant studies up to 2024. It assesses current progress and limitations and offers guidance for future research. This paper provides a comprehensive overview of the diverse challenges encountered by machine learning models in landslide susceptibility assessment, encompassing aspects such as model selection, the formulation of evaluation index systems, model interpretability, and spatial heterogeneity. The construction of an evaluation index system, which serves as the foundational data for the model, profoundly influences its accuracy. This study extensively investigates the selection of evaluation factors and the identification of positive and negative samples, proposing valuable methodologies. Furthermore, this paper briefly deliberates and compares classical machine learning models, offering valuable insights for model selection. Additionally, it delves into discussions concerning model interpretability and spatial heterogeneity issues. These research findings promise to enhance the precision of landslide susceptibility assessments and furnish effective strategies for risk management. [ABSTRACT FROM AUTHOR]

To address the subjectivity of traditional factor attribute grading methods and the weak predictive capabilities of single-model classifications, this study focused on Yulong County; the Contribution Degree Clustering Method (CDCM) utilizes the Certainty Factor (CF) as the contribution index to partition continuous factor attribute intervals. Additionally, the Sparrow Search Optimization Algorithm (SSA) is employed for hyperparameter tuning. The CF is incorporated into Support Vector Machine (SVM), Back Propagation Neural Network (BPNN), and Random Forest (RF) models to form the CF-SSA-SVM, CF-SSA-BPNN, and CF-SSA-RF coupling models, respectively. These basic coupling models are further integrated using the Stacking algorithm to create the CF-SSA-Stacking integrated coupling model for constructing a landslide susceptibility assessment system. The results indicate that the CF-SSA-Stacking integrated coupling model achieves the highest accuracy, F1 score, Kappa coefficient, and AUC value, with values of 0.89375, 0.89172, 0.787500, and 0.9522, respectively. These metrics are significantly superior to those of the three basic coupling models, demonstrating better generalization capability and reliability. This suggests that the model can identify more historical landslide occurrences using fewer grid areas classified as extremely-high- or high-susceptibility zones. It is suitable as an effective regional landslide susceptibility assessment method for practical disaster prevention and mitigation applications. Further studies could explore the model's performance across varying geological settings or with different datasets, providing a roadmap for future research and development in landslide susceptibility assessment. [ABSTRACT FROM AUTHOR]

Copyright of Geology & Resources is the property of Geology & Resources Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The holistic risk assessment model defines vulnerabilities that may vary depending on the type of hazard in the urban settlement. This model aims to identify the priority issues that need improving across the entire city and the spatial distribution of these issues. The paper describes the physical risk assessment phase of the model. The model emphasizes evaluating natural events such as earthquakes, floods, landslides, and climatic events together. The pairwise comparison method through the literature review has defined the criteria and weights selected for the model, and the susceptibility, vulnerability, and risk mapping are made using a weighted sum model through geographic information systems. Risk size is assigned a numeric value from 1 to 5, with 1 being the lowest. In conclusion, the paper provides physical risk distribution mapping of Kırklareli Central district, the study area, based on each hazard type. The paper also defines the multi-hazard risk, combining maps with the weighted sum. Accordingly, the paper has demonstrated that approximately 80% of the central district settlement is a medium-risk area, and 2.85% is a high-risk area. [ABSTRACT FROM AUTHOR]

Karst collapse is one of the main geological disasters in the northern hilly area of Guangzhou City, posing practical threats to public safety and affecting harmonious living conditions, thereby constraining local rural revitalization and development. This study analyzes the formation conditions of karst collapses in the northern hilly area of Guangzhou, including karst development degree, conditions of overlying soil layers, and hydrodynamic conditions of groundwater. Based on this analysis, six evaluation factors—karst development degree, soil layer thickness, soil layer structure, annual variation range of groundwater level, extent of fracture influence, and density of collapse points—are selected. The weight of each factor is determined by analytic hierarchy process (AHP), and a comprehensive index method is employed to establish the susceptibility assessment model for karst collapses in the northern hilly area of Guangzhou City. The results show that the areas of high, moderate, and low susceptibility to karst collapses in this region are 4.77, 14.24 , 21.71 km2, respectively. Karst subsidence occurrences are predominantly distributed in high vulnerability areas (94.29%) and moderate vulnerability areas (5.71%), validating the rationality of vulnerability zoning assessment. The research findings provide a basis for geological disaster early warning and prevention zoning for local karst collapse, and also provide geological support for promoting rural revitalization and development.

Most data-driven landslide-susceptibility assessment models heavily rely on statistical analyses based on geological and environmental similarity principles. These models often struggle to establish connections with landslide destruction processes and mechanisms effectively. In response to this challenge, this study introduces a hybrid approach that combines the transient rainfall infiltration, regional slope-stability physics–based model (TRIGRS) and the random forest (RF) model. Initially, to calculate the safety coefficients of the study area, the TRIGRS model was employed, and appropriate non-landslide samples were selected based on these coefficients. Subsequently, to enable learning and fitting of the nonlinear relationships between sample points and geological environmental factors, historical landslide data and safety coefficient-filtered non-landslide point data were input into the RF model, ultimately generating landslide probability values that represent the magnitude of landslide occurrences. The coupled model demonstrated excellent predictive performance using the landslides induced by the 2019 "Lekima" typhoon in Yongjia, Zhejiang Province, as a case study. The results indicated that the evaluation effect of the TRIGRS and RF coupled model was satisfactory, achieving an accuracy (ACC) rate of 77.6% and an area under the curve (AUC) of 0.873. Furthermore, the ACC and AUC of the TRIGRS and RF coupled model increased by 8.22% and 9.20%, respectively, compared with those of the traditional buffering sampling method. Therefore, the TRIGRS and RF coupled model better evaluates regional landslide susceptibility than the traditional buffering sampling method. [ABSTRACT FROM AUTHOR]

With the advancement of urbanization, frequent geological disasters not only restrict the development of town in mountain areas, but also may cause major casualties and property losses. Consequently, the suspension of geological disasters is of great significance to predict and prevent regional geological disasters. In order to improve the accuracy and rationality of geological hazard susceptibility modeling, 11 key factors of geological hazards, such as topographic features, lithology, distance from fault and NDVI (normalized difference vegetation index), were selected by digital elevation model grid data, and the geological hazard susceptibility model of landslide and collapse in Macheng City was built by using information, information value-logistic regression coupling analysis, finally the comprehensive geological hazard susceptibility assessment model was extracted by the maximum value of grid. The ROC (receiver operating characteristic ) curve and rationality verification of the results of the single model and the coupling model show that the information value-logistic regression coupling model is more effective and more accurate than the traditional information value model, and the susceptibility of geological disasters in mountain areas can be evaluated more accurately by the coupling model. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Journal of Geological Hazard & Control is the property of China Institute of Geological Environmental Monitoring (CIGEM) Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Fushun, located in Northeast China, is prone to debris flow disasters due to its complex topographical and geological conditions. In 2013, large-scale debris flow disasters triggered by a rainstorm broke out, causing hundreds of casualties and serious economic losses. Therefore, it is significant to evaluate the susceptibility and hazard of debris flows in Fushun. Instead of adopting grid units, this research adopts the hydrological response units as the evaluation units and conducts debris flow susceptibility assessment for Fushun area with analytical hierarchical process. By combining the susceptibility with two different precipitation data, hazard assessment is further conducted. Comparison between the two hazard maps is conducted to explore the influence of precipitation on debris flow hazard assessment. Under different precipitation conditions, the debris flow hazard of the same area changes. Statistics on the accuracy of the susceptibility and hazard assessment results is conducted and further compared with the local existing debris flow disaster records, demonstrating that the evaluation results are generally in good consistency with the actual situation in Fushun. [ABSTRACT FROM AUTHOR]

Strong earthquakes can frequently trigger a large number of co-seismic landslides. Obtaining an accurate susceptibility map of co-seismic landslides is crucial for post-disaster rescue and reconstruction efforts. In this study, the pre-seismic average annual surface deformation rate of the study area was obtained using Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) technology. Furthermore, the landslide hazards prior to the earthquake in multiple locations within the study area were analyzed. Subsequently, the deformation data was combined with 11 evaluation factors, including the distance to the fault and the Peak Ground Acceleration (PGA), to model the susceptibility of landslides. We constructed four models to evaluate the susceptibility of landslides in the study area: the Bayesian optimization random forest (BO-RF) model, the random forest model (RF), the logistic regression model (LR), and the support vector machine model (SVM). The BO-RF model outperformed the other models, achieving an AUC value of 0.984, an accuracy of 0.952, a precision of 0.953, a recall of 0.952, and an F1 score of 0.953. Furthermore, incorporating pre-seismic deformation features in the evaluation of co-seismic landslide susceptibility can effectively improve the reliability of model predictions, as compared to the evaluation model results without incorporating deformation factors. The obtained research results provide valuable data support for the rescue and management of disaster-stricken areas.

The improvement of landslide susceptibility assessment is a long-standing problem in hazard mitigation work, wherein previous studies have proposed various training models. However, the ratio of positive to negative samples and the selection of non-landslide samples have been shown to significantly influence results. These research directions have traditionally been focal points, while datasets are often overlooked, serving merely as auxiliary tools to support the validation process. Hence, this study proposes an approach to enhance datasets through the introduction of the side-sampling method. This technique focuses on individual research cells, conducting feature sampling training on fixed regions of length M, thereby enabling more precise identification of geographical clustering characteristics. Using evaluation metrics such as accuracy, precision, recall, F1 score, and ROC curve, this study conducts a comparative analysis between the side-sampling method and traditional sampling methods, using three distinct railway lines in China as the study areas. Results show substantial improvements beyond several exceptions: accuracy (+7.68%), precision (+7.19%), recall (+13.48%), F1 score (+9.92%), and ROC (+6.22%). The results demonstrate a significant overall improvement in the performance of the trained models based on the side-sampling method, providing a positive insight into mitigating landslide hazards along railways from the dataset perspective.

The Karakoram Highway (KKH) is a major road traffic route connecting China to South Asia and the Middle East via Pakistan. Geological hazards occur often in the study area due to the influence of complex geological features, active glaciers, and a changing climate, causing major disruptions to traffic operations. As a result, a geological hazard susceptibility map was created in this study to aid in the prevention and control of highway slope disasters. Through field investigation and map interpretation, 102 geohazards, including landslides, debris flows, and collapses, were observed along the route. The logistic regression method was utilized to generate a predictive model for the susceptibility map considering topography, faults, peak ground acceleration, geology, land cover, rainfall, and drainages. The results imply that the model performs well in terms of prediction. The AUC (area under the receiver operating characteristics (ROC) curve) value is 90.6%. The risk associated with the highway was assessed using the susceptibility map. Some sections of the highway are in high-risk zones, where disasters are more perilous and endanger people and automobiles. This effort will support geohazard protection, management, and safe operation of road traffic.

Reservoir impoundment is the main factor inducing reservoir landslides, it is essential to obtain the dynamic landslide susceptibility by considering hydraulic factors. In this paper, we proposed the use of the original and revised logistic regression models (machine learning methods) to analyze the landslide susceptibility after the second stage of reservoir impoundment. Data of active unstable slopes before the first stage of reservoir impoundment were used to train the models. The results indicated that the two models both performed well with high accuracy. The revised logistic regression model performed better than the original logistic regression model in two aspects. Firstly, TPR and AUC of the revised model is 0.771 and 0.906 which is obviously higher than the original model of 0.743 and 0.896. Secondly, the revised model can predict the unstable slopes after reservoir impoundment which the original model can’t predict. The former could be used to obtain the dynamic landslide susceptibility in reservoir areas after different stages of reservoir impoundment and predict the potential reactivated unstable slopes more precisely due to hydraulic factors.

IntroductionThis work employs a coupled evaluation model that integrates deterministic coefficients with the Analytic Hierarchy Process to conduct a comprehensive assessment of geological disaster susceptibility in Shenzhen Town, Ninghai County.MethodsCascading geological disasters induced by typhoons and rainfall in the southeast coastal area of China are a major concern and cause huge losses of life and property every year. To effectively prevent and mitigate such disasters, it is necessary to evaluate the susceptibility of geological disasters. Taking geological disasters in Shenzhen Town, Ninghai County as the research object, eight influencing factors in terms of topographic and geomorphological conditions, engineering geological conditions, and human activities were selected based on the geographic information platform (GIS) in this work. The coupling model of the certainty factor model and analytic hierarchy process method was used to evaluate the susceptibility of geological hazards in the study area.ResultsThe evaluation results illustrate that the coupling model can accurately and objectively assess the susceptibility of geological hazards in this region, with a high evaluation accuracy of 80.8%. The susceptibility is greatly affected by slope, stratigraphic lithology, and human activities. The areas with extraordinarily high and high susceptibility were identified in the northwestern part of the study, where the ignimbrite is exposed in the steep topography.DiscussionThe research method provides a reference for evaluating the susceptibility of geological hazards in the southeastern coastal region of China, and the evaluation results can provide recommendations for decision-making on disaster prevention and mitigation in this region.

Global warming is causing glaciers to retreat and glacial lakes to expand in the Himalayas, which amplifies the risk of glacial lake outburst debris flows (GLODFs) and poses a significant threat to downstream lives and infrastructures. However, the complex interplay between GLODF occurrences and associated indicators, coupled with the lack of a comprehensive susceptibility indicator system that considers the entire GLODF process, presents a substantial challenge in assessing GLODF susceptibility in the Himalayas. This study proposes a process-driven GLODF susceptibility assessment indicator system responding to climate change that considers the complete process of GLODF formation, incorporating relevant parameters about upstream, themselves, and downstream of glacial lakes. Furthermore, to mitigate subjective factors associated with traditional evaluation methods, we developed three novel hybrid machine-learning models by integrating classic machine-learning algorithms with the whale optimization algorithm (WOA) to delineate the distribution of GLODF susceptibility in the Himalayas. All the hybrid models effectively predicted the GLODFs occurrence, with the WOA-SVC model demonstrating the highest prediction accuracy. Approximately 34% of the catchments exhibit high and very high susceptibility levels, primarily concentrated along the north and south sides of the Himalayan ridge, particularly in the eastern and central Himalayas. Indicators capturing the physical formation process of hazards, such as topographic potential (highest relative importance value of 40%), can precisely identify GLODF. A total of 128 catchments pose potential transboundary threats, with 24 classified as having a very high susceptibility level and 25 as having a high susceptibility level. Notably, the border region between China and Nepal is a prominent hotspot for transboundary threats of GLODF. These findings can provide valuable clues for disaster prevention, mitigation, and cross-border coordination in the Himalayas.

Precisely assessing the vulnerability of landslides is essential for effective risk assessment. The findings from such assessments will undoubtedly be in high demand, providing a solid scientific foundation for a range of critical initiatives aimed at disaster prevention and control. In the research, authors set the ancient core district of Sichuan Moxi Ancient Town as the research object; they conduct and give the final result of the geological survey. Fault influences are commonly utilized as key markers for delineating strata in the field of stratigraphy, and the slope distance, slope angle, slope aspect, elevation, terrain undulation, plane curvature, profile curvature, mean curvature, relative elevation, land use type, surface roughness, water influence, distance of the catchment, cumulative water volume, and the Normalized Vegetation Index (NDVI) are used along roads to calculate annual rainfall. With the purpose of the establishment of the evaluation system, there are 17 factors selected in total. Through the landslide-susceptibility assessment by the coupled models of DNN-I-SVM and DNN-I-LR nine factors had been selected; it was found that the Area Under the Curve (AUC) value of the Receiver Operating Characteristic Curve (ROC) was high, and the accuracy of the model is relatively high. The coupler, DNN-I-LR, gives 0.875 of an evaluation accuracy of AUC, higher than DNN-I-SVM, which yielded 0.860. It is necessary to note that, in this region, compared to the DNN-I-SVM model, the DNN-I-LR coupling model has better fitting and prediction abilities. [ABSTRACT FROM AUTHOR]

Targeting at the problems of fuzzy evaluation system and neglect of triggering factors such as rainfall in the susceptibility and hazard assessment of debris flows, a study was conducted in the Fushun City based on analysis of the development and distribution patterns of debris flow disasters, the analytic hierarchy process method was utilized to assess the susceptibility and disasters of debris flow, using hydrological response units as evaluation units. The assessment accuracy is evaluated by incorporating existing debris flow disaster points. The results show that among the 42 existing debris flow disaster points, 36 are located in the high and extremely high susceptibility areas (accounting for 85. 71%), and 33 are located in the high and extremely high hazard areas (accounting for 78. 57%). This indicates that the susceptibility and hazard assessment results are reliable and consistent with the current development situation of debris flow disasters in Fushun City. [ABSTRACT FROM AUTHOR]

Wave-induced seabed liquefaction significantly jeopardizes the stability of marine structures and the safety of human life. Susceptibility assessment is key to enabling spatial predictions and establishing a solid foundation for effective risk analysis and management. However, the current research encounters various challenges, involving an incomplete evaluation system, poor applicability of methods, and insufficient databases. These issues collectively hinder the accuracy of susceptibility assessments, undermining their utility in engineering projects. To address these challenges, a susceptibility assessment method with the safety factor was developed as the key assessment parameter, allowing for a comprehensive susceptibility assessment across the silt-dominated nearshore environment using Empirical Bayesian Kriging (EBK). The safety factor is determined by combining the cyclic stress ratio (CSR) and the cyclic resistance ratio (CRR), which characterize wave loadings and sediment properties in the study area, respectively. This method was applied in the Chengdao region of the Yellow River Estuary, China, a typical silt-dominated nearshore environment where wave-induced liquefaction events have been reported as being responsible for multiple oil platform and pipeline accidents. By collecting the regional wave and seabed sediment data from cores spanning from 1998 to 2017, the safety factors were calculated, and a zonal map depicting the susceptibility assessment of wave-induced seabed liquefaction was created. This study can serve as a valuable reference for the construction and maintenance of marine engineering in liquefaction-prone areas. [ABSTRACT FROM AUTHOR]

Exploring the interplay between the spatial and temporal distribution of geological hazards and the complex hazard-prone environment provides valuable insights for effective management of geological hazards. We analyzed the spatial and temporal distribution characteristics of historical geological hazards in Hunan Province from 2015 to 2022 using standard deviation ellipse, mean nearest neighbor, and kernel density estimation. We also employed three machine learning models to evaluate the susceptibility of geological hazards. Our research reveals that the frequency trends of landslide, debris flow, and collapse over time exhibit highly similar characteristics, and their high-density areas in spatial distribution significantly overlap. Spatial correlation analysis and kernel density estimation show that geological hazards tend to aggregate in certain areas. Central Hunan and its surrounding regions are high-density areas for geological hazards, with the most severe surface collapses occurring in the Loudi area. Geological hazards are more likely to occur at the intersection of various administrative regions, and landslides, in particular, manifest as multi-point distributions, forming a belt around cities—especially in the Hengyang area, surrounded by ridges and mountains. The locus of gravity shift for geological hazards is complex, yet the distance is small, and it primarily concentrates in and around Loudi. Lithology is the most crucial factor affecting geological hazards, followed by elevation and the topographic relief index. The extreme gradient boosting model achieved an AUC value of 0.786, outperforming the random forest and support vector machine models. The susceptibility assessment aligns closely with the kernel density estimation results. This study provides a solid foundation for understanding the spatiotemporal evolution and susceptibility of geological hazards on a local scale, thereby aiding in hazard risk prevention and control. [ABSTRACT FROM AUTHOR]

Study region: Prahova river basin located in the central-southern region of Romania. Study focus: This study aims to assess the susceptibility to flooding by using state-of-the-art machine learning and optimization procedures. To achieve this goal, we employed ten flood-related variables as independent variables in our machine learning models. These variables include slope angle, convergence index, distance from the river, elevation, plan curvature, hydrological soil group, lithology, topographic wetness index, rainfall, and land use. We used 158 flood locations as dependent variables in the training of four hybrid models: Deep Learning Neural Network-Statistical Index (DLNN-SI), Particle Swarm Optimization-Deep Learning Neural Network-Statistical Index (PSO-DLNN-SI), Support Vector Machine-Statistical Index (SVM-SI), and Particle Swarm Optimization-Support Vector Machine-Statistical Index (PSO-SVM-SI). Utilizing the Statistical Index method, we calculated coefficients for each flood predictor class or category. New hydrological insights for the region: The PSO-DLNN-SI model demonstrated the best performance, achieving an AUC-ROC curve of 0.952. It's worth noting that the application of the PSO algorithm significantly enhanced the model's performance. Additionally, it's crucial to highlight that approximately 25 % of the study region exhibits a high to very high susceptibility to flood events. Taking into account the very precise results of the models applied in the present study, we can state that from a hydrological point of view, the current research contributes to a better understanding of the intensity with which floods can affect the different areas of the Prahova river basin.

This paper addresses the issue of uncertainty in the grading of geological hazard susceptibility evaluation factors and introduces the adaptive expansion factor fuzzy coverage grading method (AIFFC) to optimize the grading of geological hazard susceptibility evaluation factors. Taking Xiangxiang City, Hunan Province as the research area, nine evaluation factors, including slope, slope direction, elevation and average annual rainfall, normalized difference vegetation index for land use, roads, faults, lithology, were extracted. The AIFFC method and the natural breakpoint method were used to grade continuous factors. These graded factors were then incorporated into a weighted information model and random forest model to obtain a susceptibility zoning map for the study area. The superiority of the AIFFC classification method was tested through the comparison of single-factor grading results, disaster product ratio analysis,and ROC curve comparison of susceptibility zoning results. Based on AIFFC, the hazard accumulation ratio of the random forest model and the weighted information entropy model in the high susceptibility areas increased by 56.3% and 74.6%, respectively, while in the low susceptibility areas, it decreased by 48% and 58.1%, respectively. The AUC values increased by 7.6% and 2.7%, respectively. The AIFFC classification method is used to optimize the evaluation factor classification of geological disaster susceptibility, which significantly improves the rationality of the evaluation of geological disaster susceptibility.

Landslides are pervasive geological hazards that pose significant risks to human life, property, and the environment. Understanding landslide susceptibility is crucial for predicting and mitigating these disasters. This article advocates for a comprehensive review by systematically compiling and analyzing 146 relevant studies up to 2024. It assesses current progress and limitations and offers guidance for future research. This paper provides a comprehensive overview of the diverse challenges encountered by machine learning models in landslide susceptibility assessment, encompassing aspects such as model selection, the formulation of evaluation index systems, model interpretability, and spatial heterogeneity. The construction of an evaluation index system, which serves as the foundational data for the model, profoundly influences its accuracy. This study extensively investigates the selection of evaluation factors and the identification of positive and negative samples, proposing valuable methodologies. Furthermore, this paper briefly deliberates and compares classical machine learning models, offering valuable insights for model selection. Additionally, it delves into discussions concerning model interpretability and spatial heterogeneity issues. These research findings promise to enhance the precision of landslide susceptibility assessments and furnish effective strategies for risk management.

The Mediterranean coasts are known for their tourist attractiveness due to its richness in fishing resources and beach resorts as well as landscapes at the level of different ecosystems (forests, rocky and sandy beaches). The construction of the Mediterranean coastal road (RN16), which aims to enhance the tourist value of these resources and to improve access to this coastal region, has triggered an almost radical modification in the development process of this area, where the risks are increasing because of the multiplication of the challenges and the hazards due to the instability of its slopes. These events are mainly the result of marine erosion, the involvement of geological, geomorphological, climatic factors and also anthropic parameters with a strong littoralization. The study area is characterized by active tectonics translated by the presence of faulting sets affecting the rock mass. The aim of this study is to assess the characteristics of the rock mass and its stability and to anticipate landslide occurrence frequency with a particular size in a specified region with a certain rock mass quality as well. The methodology followed in this work consists of the elaboration of a complete inventory of landslides, the fracturation analysis and the rock mass engineering conducted to evaluate the stability of the slopes and the statistical analysis of the landslide size distribution. The combination of these two approaches has allowed us to assess qualitatively and quantitatively the landslide hazard on coastal rocky fractured areas. [ABSTRACT FROM AUTHOR]

Gully erosion can usually cause the serious environmental damage and economic losses. Susceptibility assessment and spatial distribution of gully erosion can provide a strong references for the targeted measures, decision-making on environmental protection, geologic disaster prevention, water resource management, and infrastructure planning. It is of great significance to better understand and manage the gully system, and then reduce potential risks and losses. The regional environment can be improved to maintain the regional food production in sustainable economic development. Much effort has focused on the prediction models of soil erosion over the past few decades. The amount of erosion on slopes has been predicted from both empirical statistical and physical genesis models. However, few models have been developed to predict the development of erosion gullies. Gully erosion is more complicated than slope erosion. Furthermore, the modeling has only focused on the shallow gully erosion. Only a few studies have been conducted on the topographic, critical and empirical model of gully morphologic features, the gully erosion prediction, and the landscape evolution. It is still lacking on general extrapolation of these models, even the susceptibility of gully erosion. Multiple factors can also be considered, such as the topography, geomorphology, soil, climate, vegetation and anthropogenic factors. A comprehensive and quantitative analysis of the influencing factors can be expected with the remote sensing satellites, resource and environmental surveys. A large amount of gully-erosion data has been accumulated to statistically modeling in this field. The susceptibility assessment of gully erosion aims to calculate the importance of the influencing factors on the occurrence of gully erosion and the prediction performance between different algorithms. It is still lacking on the innovative and promotional research in this field. In this review, the flow of research in this direction was systematically introduced to summarize the strengths and weaknesses of the statistical models under various classifications. The advance in this direction was proposed to compare the commonalities and differences in the application conditions from three aspects: the process of gully erosion, the data construction, and the application of statistical model. At the same time, future research needs to realize the application of transfer learning and time series models in the susceptibility assessment on gully erosion. The deep learning and physical mechanisms can be integrated to clarify the erosion gully development, in order to improve and strengthen the cross-disciplinary application of statistical models in soil erosion. The finding can lay the theoretical and technical foundation for regional development planning. [ABSTRACT FROM AUTHOR]

Xinyang City of Henan Province, located on the north-south boundary of both geography and climate of China, is prone to geological disasters. The assessment of geohazard susceptibility is of great guiding significance for disaster prevention and reduction. Based on the data analysis, 7 indexes including slope gradient, aspect, terrain curvature, distance to water system, distance to faults, nighttime light index and vegetation index are selected and the CF-LR model is used to assess the geohazard susceptibility in Xinyang City. The results show that the geohazard susceptibility in the area can be divided into four categories: extremely high-risk area (accounting for 11.39% of the total area), high-risk area (19.51%), medium-risk area (14.20%) and low-risk area (54.90%). The results are verified to meet the requirements of rationality and accuracy, indicating that the CF-LR model can objectively and accurately assess the geohazard susceptibility in Xinyang City. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Journal of Geological Hazard & Control is the property of China Institute of Geological Environmental Monitoring (CIGEM) Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the conventional process of geological hazard assessment, issues such as subjectivity in selecting susceptibility factor weights, randomness, and fuzziness in factor grading are prevalent. The application of a single assessment model can only provide qualitative evaluation of geological hazard susceptibility, lacking quantitative analysis. To overcome these challenges, this study employs an enhanced integrated algorithm (XGBoost) and cloud model. Among 189 disaster potential points in Chaoyang City, twelve susceptibility factors including slope, meteorological conditions, vegetation coverage and elevation were selected. The XGBoost classification algorithm was used to determine susceptibility factor weights. The results showed that the algorithm classification achieved high performance with fitting accuracy of 96.5%. On this basis, the cloud model was employed to transform the fuzzy factor grading into a quantitative problem, establishing a susceptibility evaluation index system for geological hazards in Chaoyang City, thereby assessing their susceptibility. To validate the evaluation index system, the Dadongshan landslide in Chaoyang City was selected as the assessment unit. Results indicate a high susceptibility level for this evaluation unit, consistent with actual conditions. The methodology proposed in this study is promising and can offers reference for evaluating geological hazard susceptibility.

In response to the issues of inconsistent factor selection and limited training samples in debris flow factor-based evaluation methods, this study proposed a prototypical network-based approach for assessing the susceptibility of valley debris flow disasters. The method involves organizing the training data through meta-learning and calculating the prototype center for each valley type, serving as a representative of that category. Subsequently, the distance between the features of unknown samples and the prototype center of each class is computed to determine the probability of their classification. Based on the category probabilities, the debris flow susceptibility index of the valley is calculated to obtain the evaluation grade for debris flow susceptibility. The model was applied to evaluate the valleys in Nujiang Prefecture, and its results were compared with historical disaster data, yielding a classification accuracy rate of 67.39%. The evaluation levels provided by the model align well with the severity of debris flow disasters in historical events. Compared to traditional methods such as field surveys and factor evaluation, the method proposed in this paper allows for the rapid identification and evaluation of debris flow disaster areas using remote sensing imagery, presenting new insights for research on early warning and prediction of debris flow disasters.

To address the subjectivity of traditional factor attribute grading methods and the weak predictive capabilities of single-model classifications, this study focused on Yulong County; the Contribution Degree Clustering Method (CDCM) utilizes the Certainty Factor (CF) as the contribution index to partition continuous factor attribute intervals. Additionally, the Sparrow Search Optimization Algorithm (SSA) is employed for hyperparameter tuning. The CF is incorporated into Support Vector Machine (SVM), Back Propagation Neural Network (BPNN), and Random Forest (RF) models to form the CF-SSA-SVM, CF-SSA-BPNN, and CF-SSA-RF coupling models, respectively. These basic coupling models are further integrated using the Stacking algorithm to create the CF-SSA-Stacking integrated coupling model for constructing a landslide susceptibility assessment system. The results indicate that the CF-SSA-Stacking integrated coupling model achieves the highest accuracy, F1 score, Kappa coefficient, and AUC value, with values of 0.89375, 0.89172, 0.787500, and 0.9522, respectively. These metrics are significantly superior to those of the three basic coupling models, demonstrating better generalization capability and reliability. This suggests that the model can identify more historical landslide occurrences using fewer grid areas classified as extremely-high- or high-susceptibility zones. It is suitable as an effective regional landslide susceptibility assessment method for practical disaster prevention and mitigation applications. Further studies could explore the model’s performance across varying geological settings or with different datasets, providing a roadmap for future research and development in landslide susceptibility assessment.

The geological and environmental background conditions of the Qingjiang River Basin are highly complex, particularly with frequent geological disasters along the Qingjiang reservoir bank. Previous susceptibility assessment for geological disasters was mostly focused on administrative areas and seldom specialized evaluations for the reservoir bank zone. Furthermore, there is still room for improvement in the evaluation index system, as well as in the pertinence and reliability of the evaluation method. To address these shortcomings, a more suitable susceptibility evaluation index system was constructed to obtain accurate and applicable susceptibility zoning results. The Yuxiakou to Ziqiu section of the Qingjiang River Basin was chosen as the research area, with the wading slope body on both sides of the river selected as the research object and the slope unit chosen as the evaluation unit. A susceptibility evaluation system composed of ten indicators, including slope, aspect, elevation range, slope type, NDVI, TWI, slope structure type, engineering geological rock formation, accumulation thickness, and valley evolution, was constructed.The logistic regression and random forest methods were used to construct the evaluation model based on the normalized certain factors, and different susceptibility zoning results were obtained. According to the evaluation results, the high-prone areas were mainly distributed in the middle to lower water wading areas of the left bank from the east of Yuxiakou to the east of Ziqiu, along the main stream of the Qingjiang River. The logistic regression model showed better applicability in the reservoir-bank section with complex topography and landforms. The research revealed that the accumulation thickness and valley evolution indicators were effective in representing the unique geological background conditions of the Qingjiang reservoir bank. The logistic regression model was able to learn the developmental law of disasters and has a reliable susceptibility prediction ability.

Himachal Pradesh (HP), one of the 11 states of the Indian Himalayan Region, has a prolonged history of landslides and related mass-movement activities. In recent years, landslide incidences have increased significantly in the state due to changing climatic patterns and enhanced anthropogenic interventions. Therefore, to understand the spatial distribution of landslide-prone zones, regional-scale landslide susceptibility mapping for the entire state has been carried out using two bivariate methods, i.e. weight of evidence and information value. The results depict that 25-30% of the total area of the state is confined in the high to very high landslide susceptible (LS) zones. These are dominantly confined to three regions: Kinnaur, Lahaul, Chamba and upper Kangra. It is also ascertained that a higher percentage of high and very high LS zones are located at an elevation of 2000-4000 m and on the slopes facing south with an inclination -40°. Moderate and low to very low LS zones comprise ~27% and ~43-48% of the total area respectively, and are confined to the Outer and Lesser Himalaya. These maps were validated using the success rate curve and prediction rate curve, indicating that both models have more or less similar efficiency and accuracy. [ABSTRACT FROM AUTHOR]

As selection of landslide-causing indicators and training samples in landslide susceptibility assessment are the key factors in determining a model's accuracy, the purpose of this research is to improve the accuracy of the landslide susceptibility assessment model by streamlining landslide-causing indicators and expanding training samples. To this end, rough set (RS) theory and genetic reduction method are adopted to reduce the initial 15 landslide-related indicators to 8 indicators highly correlated to landslide occurrence. Then, to tackle the problem of insufficient training samples, a semi-supervised classification method is employed to train the model classifier using labeled data and unlabeled data as mixed samples. Upon these, the landslide susceptibility assessment model of RS-SSVM is set up, with landslide susceptibility grades divided into high, medium, low, and non-prone zones in Qinzhou. Finally, the area under curve (AUC) values are used to compare and validate performances for different models. Analysis and comparison of the results denotes that the RS-SSVM method performed well as indicated by the AUC values of training datasets and verification datasets being 0.9308 and 0.9116. Meanwhile, the AUC values of RS-SSVM and SSVM are 0.9116 and 0.8522, respectively. This indicates that selecting more landslide-causing indicators does not necessarily bring better accuracy; instead, only the key impact indicators should be selected. Furthermore, overlay statistical analysis using historical landslide inventory data and assessment results shows that 71.27% of the historical landslides sites are in the high susceptibility areas accounting for 2.96% of the total area of the study area, which agrees well with the distribution features of historical landslides. Therefore, the proposed RS-SSVM method can improve the spatial cognition of the complex landslide systems aside from being applied to landslide susceptibility assessment in other places with similar regional geo-environmental conditions. [ABSTRACT FROM AUTHOR]

Copyright of Remote Sensing for Natural Resources is the property of Remote Sensing for Natural Resources Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the conventional process of geological hazard assessment, issues such as subjectivity in selecting susceptibility factor weights, randomness, and fuzziness in factor grading are prevalent. The application of a single assessment model can only provide qualitative evaluation of geological hazard susceptibility, lacking quantitative analysis. To overcome these challenges, this study employs an enhanced integrated algorithm (XGBoost) and cloud model. Among 189 disaster potential points in Chaoyang City, twelve susceptibility factors including slope, meteorological conditions, vegetation coverage and elevation were selected. The XGBoost classification algorithm was used to determine susceptibility factor weights. The results showed that the algorithm classification achieved high performance with fitting accuracy of 96.5%. On this basis, the cloud model was employed to transform the fuzzy factor grading into a quantitative problem, establishing a susceptibility evaluation index system for geological hazards in Chaoyang City, thereby assessing their susceptibility. To validate the evaluation index system, the Dadongshan landslide in Chaoyang City was selected as the assessment unit. Results indicate a high susceptibility level for this evaluation unit, consistent with actual conditions. The methodology proposed in this study is promising and can offers reference for evaluating geological hazard susceptibility. [ABSTRACT FROM AUTHOR]

Foreseeing the failure of important unstable volumes is a major concern in the Alps, especially due to the presence of people and infrastructures in the valleys. The use of monitoring and remote sensing techniques is aimed at detecting potential instabilities and the combination of several techniques permits the cross-validation of the detected movements. Supplemented with field mapping and structural analysis, it is possible to define possible scenarios of rupture in terms of volume, mechanisms of failure and susceptibility. A combined observation strategy was applied to the study of major instability located in the Ticinese Alps (Switzerland), Cima del Simano, where the monitoring started in 2006 with the measurement of opened cracks with extensometers. Since 2021, the monitoring has been completed by LiDAR, satellite and GB-InSAR observations and structural analysis. Here, slow but constant movements of about 7 mm/yr were detected along with rockfall activities near the Simano summit. Eight failure scenarios of various sizes ranging from 2.3 × 105 m3 to 51 × 106 m3, various mechanisms (toppling, planar, wedge and circular sliding) and various occurrence probabilities were defined based on the topography and the monitoring results and by applying a Slope Local Base Level (SLBL) algorithm. Weather acquisition campaigns by means of thermologgers were also conducted to suggest possible causes that lead to the observed movements and to suggest the evolution of the instabilities with actual and future climate changes. [ABSTRACT FROM AUTHOR]

Combined with visible light remote sensing technology and InSAR technology, this study employed the fundamental principles of the frequency ratio model, information content model, and analytic hierarchy process to assess the susceptibility of the study area. Nine susceptibility assessment factors such as elevation, slope, aspect, water system, vegetation coverage, geological structure, stratum lithology, rainfall, and human activities were selected, and the factor correlation degree was calculated by using the relative area density value of the landslide. The frequency ratio model and information content model were selected to carry out landslide susceptibility zoning, and the accuracy of the two models was verified by the ROC curve and density method. The results indicate that the information content model performed relatively well. Therefore, the information model, combined with the analytic hierarchy process and fuzzy superposition method using the landslide point density map, was chosen to evaluate landslide susceptibility. The study area was divided into five levels of landslide hazard, ranging from low to high, using the natural discontinuity point method. The results show that the area of each hazard zoning is 197.48, 455.72, 408.21, 152.66, and 16.22 km2 from low to high, and the proportion of landslides in the corresponding area is 0.17%, 1.60%, 3.88%, 8.41%, and 16.65%, respectively. It can be seen that with the increase in the hazard level, the proportion of landslides also increases significantly, which verifies the accuracy of the hazard results. Additionally, four representative landslides in the study area were selected for analysis to understand their characteristics and underlying mechanisms. The results revealed that these landslides were notably influenced by the density of the Jinsha River and the surrounding roads. The susceptibility assessment outcomes for geological disasters align well with the current situation of landslide occurrences in the Tuoding river section, demonstrating high accuracy. This study provides a scientific foundation for effective prevention and control measures against local landslide disasters. [ABSTRACT FROM AUTHOR]

The Mw 7.5 Palu earthquake that occurred on 28 September 2018 (UTC 10:02) on Sulawesi Island, Indonesia, triggered approximately 15,600 landslides, causing about 4000 fatalities and widespread destruction. The primary objective of this study is to perform landslide susceptibility mapping (LSM) associated with this event and assess the performance of the most widely used machine learning algorithms of logistic regression (LR) and random forest (RF). Eight controlling factors were considered, including elevation, hillslope gradient, aspect, relief, distance to rivers, peak ground velocity (PGV), peak ground acceleration (PGA), and lithology. To evaluate model uncertainty, training samples were randomly selected and used to establish the models 20 times, resulting in 20 susceptibility maps for different models. The quality of the landslide susceptibility maps was evaluated using several metrics, including the mean landslide susceptibility index (LSI), modelling uncertainty, and predictive accuracy. The results demonstrate that both models effectively capture the actual distribution of landslides, with areas exhibiting high LSI predominantly concentrated on both sides of the seismogenic fault. The RF model exhibits less sensitivity to changes in training samples, whereas the LR model displays significant variation in LSI with sample changes. Overall, both models demonstrate satisfactory performance; however, the RF model exhibits superior predictive capability compared to the LR model. [ABSTRACT FROM AUTHOR]

The development and utilization of land in the main urban area have significantly impacted the stability of the regional geological environment through various means, such as increased load and subway construction, primarily manifested as rock and soil mass deformation leading to geological hazards. Therefore, it is worth exploring how to reduce the occurrence of karst ground subsidence (KGS) through reasonable land development and control measures in the main urban areas with large-scale developments of buried karst formations. This study focuses on the main urban area of Wuhan City. An evaluation model for KGS was constructed using the analytic hierarchy process (AHP) and comprehensive index evaluation method by analyzing the geological conditions that affect KGS. The susceptibility zoning of KGS was obtained with GIS spatial analysis technology. The results show that the susceptible areas can be divided into extreme, high, medium, and weak susceptibility, accounting for 4.93%, 15.30%, 33.21%, and 46.56%, respectively, which are consistent with the distribution density of past KSGs. Furthermore, by selecting the subway construction as a human activity type, it indirectly discusses the influence of land development intensity on KGS. The results show that past KSGs are mainly concentrated in areas with high engineering construction density and significant land development intensity. Based on the above, strategies for regional land development and prevention and control of KGSs are proposed. [ABSTRACT FROM AUTHOR]

Copyright of Geology & Resources is the property of Geology & Resources Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Geological Hazard & Control is the property of China Institute of Geological Environmental Monitoring (CIGEM) Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To study the susceptibility of debris flow in Kangding City, the study area was divided into 421 watershed units. Spatial analysis tools in ArcGIS software and SPSS software were used to analyze the internal superposition of evaluation indicators and the correlation between evaluation indicators and debris flows disasters. By screening out the evaluation factors with a high degree of overlap and poor correlation, eight evaluation factors were selected for debris flow susceptibility assessment. These included watershed unit area, melton rate, form factor ratio, collapse and landslides density of catchment, average fractional vegetation cover of catchment, road density of catchment, average stream power index of catchment, and average rainfall during the multi-year flood season. The susceptibility of debris flow was quantitatively evaluated by combining the information value model and the entropy method. The weights of the evaluation indicators were quantitatively determined by the entropy method, and the evaluation factor weighted information quantity value was calculated. Based on this, the debris flow susceptibility in Kangding City was divided into four grades: extremely high, high, medium and low. The results of debris flow susceptibility assessment were tested using the frequency ratio model and the Receiver-Operating Characteristic (ROC) curve, with an AUC curve of 0.842, indicating high accuracy of the evaluation model.

In the mapping and assessment of mountain hazard susceptibility using machine learning models, the selection of model parameters plays a critical role in the accuracy of predicting models. In this study, we present a novel approach for developing a prediction model based on random forest (RF) by incorporating ensembles of hyperparameter optimization. The performance of the RF model is enhanced by employing a Bayesian optimization (Bayes) method and a genetic algorithm (GA) and verified in the Wudu section of the Bailong River basin, China, which is a typical hazard-prone, mountainous area. We identified fourteen influential factors based on field measurements to describe the “avalanche–landslide–debris flow” hazard chains in the study area. We constructed training (80%) and validation (20%) datasets for 378 hazard sites. The performance of the models was assessed using standard statistical metrics, including recall, confusion matrix, accuracy, F1, precision, and area under the operating characteristic curve (AUC), based on a multicollinearity analysis and Relief-F two-step evaluation. The results indicate that all three models, i.e., RF, GA-RF, and Bayes-RF, achieved good performance (AUC: 0.89~0.92). The Bayes-RF model outperformed the other two models (AUC = 0.92). Therefore, this model is highly accurate and robust for mountain hazard susceptibility assessment and is useful for the study area as well as other regions. Additionally, stakeholders can use the susceptibility map produced to guide mountain hazard prevention and control measures in the region.

When using machine learning models for landslide susceptibility evaluation, the non-landslide sample points are usually selected randomly outside the landslide influence area, leading to a certain error. To improve the accuracy of landslide susceptibility evaluation, this paper couples the self-organizing map (SOM) neural network, information (I) model, and support vector machine (SVM) model, and proposes a SOM-I-SVM model-based method of landslide susceptibility evaluation, comparing with K-means clustering to verify the reliability of this model. The Maojian District of the city of Shiyan is taken as an example, and seven factors of the distance from water system, slope, rainfall, distance from structure, relative height difference, distance from road, stratigraphic lithology are selected by correlation and importance analyses of environmental factors to establish a landslide susceptibility evaluation system. Based on these, the graded information values of each factor are calculated and used as input variables for landslide susceptibility evaluation. The SOM neural network and K-means clustering are used to select non-landslide samples, and the sample data set is substituted into the I-SVM model to predict landslide susceptibility. The prediction accuracies of the four models, SVM, I-SVM, KMeans-I-SVM and SOM-I-SVM, are compared, and the area under the ROC curve (AUC values) are 0.82, 0.88, 0.90 and 0.91, indicating that the SOM-I-SVM model can effectively improve the accuracy of landslide susceptibility prediction.

Precisely assessing the vulnerability of landslides is essential for effective risk assessment. The findings from such assessments will undoubtedly be in high demand, providing a solid scientific foundation for a range of critical initiatives aimed at disaster prevention and control. In the research, authors set the ancient core district of Sichuan Moxi Ancient Town as the research object; they conduct and give the final result of the geological survey. Fault influences are commonly utilized as key markers for delineating strata in the field of stratigraphy, and the slope distance, slope angle, slope aspect, elevation, terrain undulation, plane curvature, profile curvature, mean curvature, relative elevation, land use type, surface roughness, water influence, distance of the catchment, cumulative water volume, and the Normalized Vegetation Index (NDVI) are used along roads to calculate annual rainfall. With the purpose of the establishment of the evaluation system, there are 17 factors selected in total. Through the landslide-susceptibility assessment by the coupled models of DNN-I-SVM and DNN-I-LR nine factors had been selected; it was found that the Area Under the Curve (AUC) value of the Receiver Operating Characteristic Curve (ROC) was high, and the accuracy of the model is relatively high. The coupler, DNN-I-LR, gives 0.875 of an evaluation accuracy of AUC, higher than DNN-I-SVM, which yielded 0.860. It is necessary to note that, in this region, compared to the DNN-I-SVM model, the DNN-I-LR coupling model has better fitting and prediction abilities.

Wave-induced seabed liquefaction significantly jeopardizes the stability of marine structures and the safety of human life. Susceptibility assessment is key to enabling spatial predictions and establishing a solid foundation for effective risk analysis and management. However, the current research encounters various challenges, involving an incomplete evaluation system, poor applicability of methods, and insufficient databases. These issues collectively hinder the accuracy of susceptibility assessments, undermining their utility in engineering projects. To address these challenges, a susceptibility assessment method with the safety factor was developed as the key assessment parameter, allowing for a comprehensive susceptibility assessment across the silt-dominated nearshore environment using Empirical Bayesian Kriging (EBK). The safety factor is determined by combining the cyclic stress ratio (CSR) and the cyclic resistance ratio (CRR), which characterize wave loadings and sediment properties in the study area, respectively. This method was applied in the Chengdao region of the Yellow River Estuary, China, a typical silt-dominated nearshore environment where wave-induced liquefaction events have been reported as being responsible for multiple oil platform and pipeline accidents. By collecting the regional wave and seabed sediment data from cores spanning from 1998 to 2017, the safety factors were calculated, and a zonal map depicting the susceptibility assessment of wave-induced seabed liquefaction was created. This study can serve as a valuable reference for the construction and maintenance of marine engineering in liquefaction-prone areas.