Search

This study examined the applicability of factorization machines with quantum annealing (FMQA) to the field of landslide risk assessment for two specific black‐box optimization problems, hyperparameter optimization (HPO) for metamodeling and metamodel‐based simulation optimization (MBSO) targeting granular flow simulation using discrete element method (DEM). These two optimization problems are solved successively: HPO is first performed to determine the hyperparameters of the Gaussian process regression (GPR) metamodel, which is then used as a low‐cost, fast approximate solver of granular flow simulations for MBSO. After conducting a series of granular flow simulations using DEM, a metamodel is created that outputs a risk index of interest, the run‐out distance, from its input parameters by employing GPR with two hyperparameters, length‐scale and signal variance. Subsequently, HPO is performed to obtain the optimal set of hyperparameters by applying FMQA and other optimization methods using another set of hyperparameters determined using the gradient‐ascent method as the reference solution. Finally, using the metamodel created by each optimization method as an approximate solver for DEM simulations, MBSO is performed to find the optimal target output, the maximum run‐out distance, in the space of physical input parameters for risk assessment. A comparison of the performance of FMQA with that of other methods shows that FMQA is competitive in terms of efficiency and stability with state‐of‐the‐art algorithms such as Bayesian optimization. [ABSTRACT FROM AUTHOR]

The assessment of landslide susceptibility often overlooks the influence of forests on shallow landslide mobility, despite its significance. This study delved into the impact of forest presence on shallow landslide mobility during intense rainfall in Mengdong, China. Field investigations were coupled with the analysis of pre- and post-rainfall remote sensing (RS) images to delineate landslides. The ratio of landslide height (H) to travel distance (L) from a digital elevation model (DEM) were used to calculate landslides mobility. Preceding the event, forest coverage was evaluated using the normalized difference vegetation index (NDVI) derived from multiband RS image. The research identified 1531 shallow landslides in the area, revealing a higher concentration of landslides on slopes with elevated NDVI. Results indicated that disparities in soil permeability and cohesion, generating pore water pressure (PWP), triggered clusters of shallow landslides. Shallow landslides exhibit a higher propensity on slopes with elevated NDVI. The dimensions (height and area) of these identified shallow landslides typically exhibit a positive correlation with NDVI, consequently resulting in longer travel distances for landslides occurring on higher NDVI slopes. The average H/L ratio of all identified landslides was about 0.63. H/L generally increases with NDVI and decreases with landslide area. However, due to river channel restrictions, the H/L increases with slope gradient. The findings suggest that the high permeability of areas with tree roots poses a risk to the shallow stability of slopes, yet trees contribute to mitigating landslide mobility. [ABSTRACT FROM AUTHOR]

Several landslide susceptibility (LS) maps at various scales of analysis have been performed with specific zoning purposes and techniques. Supervised machine learning algorithms (ML) have become one of the most diffused techniques for landslide prediction, whose reliability is firmly based on the quality of input data. Site-specific landslide inventories are often more accurate and complete than national or worldwide databases. For these reasons, detailed landslide inventory and predisposing variables must be collected to derive reliable LS products. However, high-quality data are often rare, and risk managers must consider lower-resolution available products with no more than informative purposes. In this work, we compared different ML models to select the most accurate for large-scale LS assessment within the Municipality of Rome. The ExtraTreesClassifier outperformed the others reaching an average F1-score of 0.896. Thereafter, we addressed the reliability of open-source LS maps at different scales of analysis (global to regional) by means of statistical and spatial analysis. The obtained results shed light on the difference in hazard zoning depending on the scale and mapping unit. An approach for low-resolution LS data fusion was attempted, assessing the importance of the adopted criteria, which increased the ability to detect occurred landslides while maintaining precision. [ABSTRACT FROM AUTHOR]

Spatial accurate mapping of land susceptibility to wind erosion is necessary to mitigate its destructive consequences. In this research, for the first time, we developed a novel methodology based on deep learning (DL) and active learning (AL) models, their combination (e.g., recurrent neural network (RNN), RNN-AL, gated recurrent units (GRU), and GRU-AL) and three interpretation techniques (e.g., synergy matrix, SHapley Additive exPlanations (SHAP) decision plot, and accumulated local effects (ALE) plot) to map global land susceptibility to wind erosion. In this respect, 13 variables were explored as controlling factors to wind erosion, and eight of them (e.g., wind speed, topsoil carbon content, topsoil clay content, elevation, topsoil gravel fragment, precipitation, topsoil sand content and soil moisture) were selected as important factors via the Harris Hawk Optimization (HHO) feature selection algorithm. The four models were applied to map land susceptibility to wind erosion, and their performance was assessed by three measures consisting of area under of receiver operating characteristic (AUROC) curve, cumulative gain and Kolmogorov Smirnov (KS) statistic plots. The results revealed that GRU-AL model was considered as the most accurate, revealing that 38.5%, 12.6%, 10.3%, 12.5% and 26.1% of the global lands are grouped at very low, low, moderate, high and very high susceptibility classes to wind erosion hazard, respectively. Interpretation techniques were applied to interpret the contribution and impact of the eight input variables on the model's output. Synergy plot revealed that the soil carbon content exhibited high synergy with DEM and soil moisture on the model's predictions. ALE plot showed that soil carbon content and precipitation had negative feedback on the prediction of land susceptibility to wind erosion. Based on SHAP decision plot, soil moisture and DEM presented the highest contribution on the model's output. Results highlighted new regions at high latitudes (southern Greenland coast, hotspots in Alaska and Siberia), which exhibited high and very high land susceptibility to wind erosion. [ABSTRACT FROM AUTHOR]

In the northwestern Himalayas, including Jammu and Kashmir (J&K), frequent landslides pose significant risks, necessitating proactive zoning to mitigate potential damage through effective land-use planning. Fourteen causative and two triggering factors, such as slope, aspect, curvature, relative relief (RR), terrain ruggedness index (TRI), geomorphon, dissection index (Di), lithology, structural tectonic, drainage density (Dd), stream power index (SPI), topographic wetness index (TWI), land use land cover (LULC), road density (Rd), earthquake density (Ed), and rainfall density (Rd), were selected based on terrain conditions to assess landslide susceptibility. Utilizing frequency ratio (FR) and information value (IV) approaches, a comprehensive landslide susceptibility mapping (LSM) study covered 54,922 km2, incorporating 6669 landslide instances. This dataset was split into 70% (4659 landslides) for modeling and 30% (2010 landslides) for validation. The landslide susceptibility map, classified into five categories (very low, low, moderate, high, and very high), delineates varying proportions of the study area. Using the FR approach, these zones cover 12.9% (7063 km2), 25.7% (14,101 km2), 25.6% (14,049 km2), 24.7% (13,586 km2), and 11.1% (6123 km2) of the area, respectively. Meanwhile, employing the IV approach, the coverage percentages are 5.7% (3119 km2), 11.0% (6063 km2), 20.1% (11,057 km2), 38.9% (21,373 km2), and 24.1% (13,310 km2). Validation using receiver operating characteristic curves revealed high correlations for both FR (AUC: 0.809) and IV (AUC: 0.778) models, indicating their effectiveness. The FR model, characterized by simplicity and higher accuracy, outperformed the IV model, offering valuable insights for local, regional, and governments in land-use planning, disaster prevention, and mitigation efforts. [ABSTRACT FROM AUTHOR]

This paper tests a multivariate statistical model to simulate rainfall dependent susceptibility scenarios of shallow landslides. To this end, extreme rainfall events spanning from 1977 to 2021 in the Orba basin (a study area of 505 km2 located in Piedmont, northern Italy), have been considered. First of all, the role of conditioning and triggering factors on the spatial pattern of shallow landslides in areas with complex geological conditions is analysed by comparing their spatial distribution and their influence within logistic regression models, with results showing that rainfall and specific lithological and geomorphological conditions exert the strongest control on the spatial pattern of landslide. Different rainfall-based scenarios were then modelled using logistic regression models trained on different combinations of past events and evaluated using an ensemble of performance metrics. Models calibrated on multi-events outperform the ones based on a single event, since they are capable of compensating for local misleading effects that can arise from the use of a single rainfall event. The best performing developed model considers all the landslide triggering rainfall scenarios and two non-triggering intense rainfall events, with a score of 0.90 out of 1 on the multi-criteria TOPSIS-based performance index. Finally, a new approach based on misclassification costs is proposed to account for false negatives and false positives in the predicted susceptibility maps. Overall, this approach based on a multi-event calibration and on a misclassification costs analysis shows promise in producing rainfall dependent shallow landslide susceptibility scenarios that could be used for hazard analyses, early warning systems and to assist decision-makers in developing risk mitigation strategies. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) is essential for determining risk regions and guiding mitigation strategies. Machine learning (ML) techniques have been broadly utilized, but the uncertainty and interpretability of these models have not been well-studied. This study conducted a comparative analysis and uncertainty assessment of five ML algorithms--Random Forest (RF), Light Gradient-Boosting Machine (LGB), Extreme Gradient Boosting (XGB), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM)--for LSM in Inje area, South Korea. We optimized these models using Bayesian optimization, a method that refines model performance through probabilistic model-based tuning of hyperparameters. The performance of these algorithms was evaluated using accuracy, Kappa score, and F1 score, with accuracy in detecting landslide-prone locations ranging from 0.916 to 0.947. Among them, the tree-based models (RF, LGB, XGB) showed competitive performance and outperformed the other models. Prediction uncertainty was quantified using bootstrapping and Monte Carlo simulation methods, with the latter providing a more consistent estimate across models. Further, the interpretability of ML predictions was analyzed through sensitivity analysis and SHAP values. We also expanded our investigation to include both the inclusion and exclusion of predictors, providing insights into each significant variable through a comprehensive sensitivity analysis. This paper provides insights into the predictive uncertainty and interpretability of ML algorithms for LSM, contributing to future research in South Korea and beyond. [ABSTRACT FROM AUTHOR]

This document is an editorial from the journal Frontiers in Earth Science titled "Prevention, Mitigation, and Relief of Compound and Chained Natural Hazards." It discusses the increasing frequency of extreme natural disasters due to global climate warming and frequent earthquakes, which pose significant threats to human life and property. The editorial highlights the importance of preventing, mitigating, and relieving compound and chained natural hazards, and the role of technological advancements in addressing these hazards. The document provides an overview of nine published papers that focus on earthquakes, geological hazards, earthquake-triggered landslides, and landslide susceptibility. It concludes by emphasizing the need for continued research on comprehensive natural hazards and disaster chains, beyond earthquakes and geological disasters, such as meteorological events, floods, droughts, wildfires, and tsunamis. [Extracted from the article]

Delineating spatiotemporal variations in landslide susceptibility patterns is crucial for landslide prevention and management. In this study, we present a space–time modeling approach to predict the annual landslide susceptibility of the main island of Taiwan from 2004 to 2018. Specifically, we use a Bayesian version of the binomial generalized additive model, assuming that landslide occurrence follows a Bernoulli distribution. We generate 46,074 slope units to partition the island of Taiwan and divide the time domain into 14 annual units. The binary states of landslide presence and absence are classified by a set of static and dynamic covariates. Our modeling strategy features an initial explanatory model to test for goodness of fit and to interpret the effects of covariates. Then, five cross-validation schemes are tested to provide the full range of the predictive capacity of our model. We summarize the performance of each test through receiver operating characteristic curves and their numerical variation over space and time. Overall, our space–time model achieves satisfactory results, with the mean AUC above 0.8. We believe this type of dynamic prediction is a new direction that eventually moves away from the static view provided by traditional susceptibility models. Meanwhile, we believe that such analyses are only stepping stones for further improvements, the most natural of which are statistical simulations of future scenarios. [ABSTRACT FROM AUTHOR]

Landslides are widespread geomorphological phenomena with complex mechanisms that have caused extensive causalities and property damage worldwide. The scale and frequency of landslides are presently increasing owing to the warming effects of climate change, which further increases the associated safety risks. In this study, the relationship between historical landslides and environmental variables in the Hanjiang River Basin was determined and an optimized model was used to constrain the relative contribution of variables and best spatial response curve. The optimal MaxEnt model was used to predict the current distribution of landslides and influence of future rainfall changes on the landslide susceptibility. The results indicate that environmental variables in the study area statistically correlate with landslide events over the past 20 years. The MaxEnt model evaluation was applied to landslide hazards in the Hanjiang River Basin based on current climate change scenarios. The results indicate that 25.9% of the study area is classified as a high-risk area. The main environmental variables that affect the distribution of landslides include altitude, slope, normalized difference vegetation index, annual precipitation, distance from rivers, and distance from roads, with a cumulative contribution rate of approximately 90%. The annual rainfall in the Hanjiang River Basin will continue to increase under future climate warming scenarios. Increased rainfall will further increase the extent of high- and medium-risk areas in the basin, especially when following the RCP8.5 climate prediction, which is expected to increase the high-risk area by 10.7% by 2070. Furthermore, high landslide risk areas in the basin will migrate to high-altitude areas in the future, which poses new challenges for the prevention and control of landslide risks. This study demonstrates the usefulness of the MaxEnt model as a tool for landslide susceptibility prediction in the Hanjiang River Basin caused by global warming and yields robust prediction results. This approach therefore provides an important reference for river basin management and disaster reduction and prevention. The study on landslide risks also supports the hypothesis that global climate change will further enhance the frequency and intensity of landslide activity throughout the course of the 21st Century. [ABSTRACT FROM AUTHOR]

On 5 September 2022, a Ms 6.8 earthquake struck Luding County, Ganzi Tibetan Autonomous Prefecture, Sichuan Province, China. This seismic event triggered over 16,000 landslides and caused serious casualties and infrastructure damages. The aim of this study is to perform the detailed landslides susceptibility mapping associated with this event based on an updated landslide inventory and logistic regression (LR) modeling. Firstly, we quantitatively assessed the importance of different controlling factors using the Jackknife and single-variable methods for modeling landslide occurrence. Subsequently, four landslide susceptibility assessment models were developed based on the LR model, and we evaluated the accuracy of the landslide susceptibility mappings using Receiver Operating Characteristic (ROC) curves and statistical measures. The results show that ground motion has the greatest influence on landslides in the entire study area, followed by elevation, while distance to rivers and topographic relief have little influence on the distribution of landslides. Compared to the NEE plate, PGA has a greater impact on landslides in the SWW plate. Moreover, the AUC value of the SWW plate significantly decreases for lithological types and aspect, indicating a more pronounced lithological control over landslides in the SWW plate. We attribute this phenomenon primarily to the occurrence of numerous landslides in Permian basalt and tuff in the SWW plate. Otherwise, the susceptibility results based on four models indicate that high-susceptibility areas predicted by different models are distributed along both sides of seismogenic faults and the Dadu Rivers. Landslide data have a significant impact on the model prediction results, and the model prediction accuracy based on the landslide data of the SWW plate is higher. [ABSTRACT FROM AUTHOR]

Landslides are a widely recognized phenomenon, causing huge economic and human losses worldwide. The detection of spatial and temporal landslide deformation, together with the acquisition of precursor information, is crucial for hazard prediction and landslide risk management. Advanced landslide monitoring systems based on remote sensing techniques (RSTs) play a crucial role in risk management and provide important support for early warning systems (EWSs) at local and regional scales. The purpose of this article is to present a review of the current state of knowledge in the development of RSTs used for identifying landslide precursors, as well as detecting, monitoring, and predicting landslides. Almost 200 articles from 2010 to 2024 were analyzed, in which the authors utilized RSTs to detect potential precursors for early warning of hazards. The applications, challenges, and trends of RSTs, largely dependent on the type of landslide, deformation pattern, hazards posed by the landslide, and the size of the area of interest, were also discussed. Although the article indicates some limitations of the RSTs used so far, integrating different techniques and technological developments offers the opportunity to create reliable EWSs and improve existing ones. [ABSTRACT FROM AUTHOR]

The eastern margin of the Tibetan Plateau is one of the regions with the most severe landslide disasters on a global scale. With the intensification of seismic activity around the Tibetan Plateau and the increase in extreme rainfall events, the prevention of landslide disasters in the region is facing serious challenges. This article selects the Bailong River Basin located in this region as the research area, and the historical landslide data obtained from high-precision remote sensing image interpretation combined with field validation are used as the sample library. Using machine learning algorithms and data-driven landslide susceptibility assessment as the methods, 17 commonly used models and 17 important factors affecting the development of landslides are selected to carry out the susceptibility assessment. The results show that the BaggingClassifier model shows advantageous applicability in the region, and the landslide susceptibility distribution map of the Bailong River Basin was generated using this model. The results show that the road and population density are both high in very high and high susceptible areas, indicating that there is still a significant potential landslide risk in the basin. The quantitative evaluation of the main influencing factors emphasizes that distance to a road is the most important factor. However, due to the widespread utilization of ancient landslides by local residents for settlement and agricultural cultivation over hundreds of years, the vast majority of landslides are likely to have occurred prior to human settlement. Therefore, the importance of this factor may be overestimated, and the evaluation of the factors still needs to be dynamically examined in conjunction with the development history of the region. The five factors of NDVI, altitude, faults, average annual rainfall, and rivers have a secondary impact on landslide susceptibility. The research results have important significance for the susceptibility assessment of landslides in the complex environment of human–land interaction and for the construction of landslide disaster monitoring and early warning systems in the Bailong River Basin. [ABSTRACT FROM AUTHOR]

Though strongly linked to landslides, hydropedological characteristics are inadequately investigated in Manafwa catchment. This study investigated hydropedological characteristics at medium landslide sites in Manafwa catchment. The design included 12 infiltration experiments that were conducted at each site. To determine the selected soil physical properties, composite soil samples were extracted from the infiltration sites for soil laboratory analysis. Soil cores were extracted to determine saturated hydraulic conductivity (Ksat) and bulk density. The observed high infiltration rates and rapid Ksat underscore the susceptibility of the studied sites to landslide hazards. Additionally, soil organic matter, clay content, and bulk density further contribute to the understanding of the hydropedological factors influencing landslide occurrences. These findings reveal the need for comprehensive investigations into hydropedological characteristics of other landslide categories to assist in landslide risk assessment and management strategies. [ABSTRACT FROM AUTHOR]

This scientometric analysis significantly advances the understanding of landslide risk assessment and economic losses, focusing on scientometric insights. This study aims at analyzing the global trends and structures of landslide risk and economic loss research from 2002 to 2023 using scientometric techniques such as co-authorship, co-word, co-citation, cluster analysis, and trend topics, among others. Thus, analysis of 92 studies gathered from Scopus and Web of Science databases reveals a continuous growth in environmental, social, and quantitative research topics. Predominant contributions hail mainly from China and Italy. The research identifies critical themes, including risk analysis, vulnerability, fragility, and economic losses. The current identified research combines advanced statistical methods, including logistic regression, with climate change scenarios and susceptibility assessments to reveal intricate connections between climatic shifts, hydrogeological hazards, and their economic and environmental impacts. This study provides researchers and practitioners with a comprehensive understanding of the status quo and research trends of ontology research landslide risk and its economic losses. It also promotes further studies in this domain. [ABSTRACT FROM AUTHOR]

Landslides are a severe geological hazard in northeastern India, particularly in Mizoram's Aizawl district. To assess this hazard, we conducted a landslide susceptibility mapping study using the frequency ratio (FR) and analytical hierarchy process (AHP) methods. Twelve factors, including slope, elevation, aspect, curvature, topographic wetness index, topographic ruggedness index, rainfall erosivity factor, geology, land use land cover, normalized difference vegetation index (NDVI), and distance to road, were considered. The final susceptibility maps were created by combining these factors, each weighted according to its importance. Since no standard classification guidelines existed, we compared different systems like GIS-based geometric interval (GIC), natural breaks (NBC), and quantile interval (QIC) with mean-standard deviation (MSC). The area was divided into five susceptibility zones: very high, high, moderate, low, and very low. We evaluated the accuracy of these systems using success rate curve (SRC) and quality sum ratio (Qs) techniques. SRC results showed similar performance for GIC, NBC, QIC, and MSC classifications. The AHP method also yielded comparable results. After analyzing the AUC under SRC and Qs, we selected the MSC classification system as the optimal approach for landslide susceptibility mapping. Notably, the distance to roads factor had the highest predictive value, highlighting its importance in identifying slope instability for effective management strategies. As landslides pose significant risks in northeastern India, and our study using FR and AHP methods, along with MSC classification, provides valuable insights for mitigating this geological hazard. [ABSTRACT FROM AUTHOR]

Constraining landslide occurrence rates can help to generate landslide hazard models that predict the spatial and temporal occurrence of landslides. However, most landslide inventories do not include any temporal data due to the difficulties of dating landslide deposits. Here we introduce a method for estimating the mean landslide occurrence rate of deep‐seated rotational and translational slides derived solely from high‐resolution (≤3 m) elevation data and globally available estimates of the diffusion coefficient for sediment flux. The method applies a linear diffusion model to the roughest landslide deposits until they reach a representative non‐landslide roughness distribution. This estimates the time for a landslide deposit to be unrecognizable in high‐resolution digital elevation data, which we term the mean lifetime of the landslide. Using the mean lifetime and number of landslides within an area of interest, we can estimate the mean occurrence rate of landslides over that domain. We validate this approach using a comprehensive temporal inventory of landslides in western Oregon created using age‐roughness curves that are calibrated with high‐resolution elevation data and radiocarbon data. We find good agreement between our diffusion method and the existing age‐roughness‐derived estimates, producing mean lifetimes of 4500 and 5200 years (4% difference), respectively. Hazard maps produced using the two methodologies generally agree, with the maximum differences in landslide probability reaching 0.1. Due to the relative abundance of high‐resolution elevation data compared with age‐dated landslides, our method could help constrain landslide occurrence rates in areas previously considered unfeasible. Plain Language Summary: Estimating how often landslides occur over a given area can be helpful in reducing landslide damages in the future. Traditional methods of estimating how often landslides occur require complex methods for estimating landslide ages, which can be time consuming and expensive. As a result, age‐dated landslides are limited to a few locations around the world. Here, we present a method for estimating how often landslides occur using only widely available high‐resolution elevation data. We contrast our method with results using traditional age‐dating techniques and find good agreement. Using our method, we can estimate how often landslides occur in areas where it was previously impractical. Key Points: We present a method for constraining landslide occurrence rates without using traditional age‐dating techniquesThe method applies a diffusion model and only requires elevation data, a landslide inventory, and estimates of the diffusion coefficientEstimates of landslide occurrence rates using age‐dating and the diffusion method show good agreement [ABSTRACT FROM AUTHOR]

The article presents an interview with Verena Winiwarter, Professor of Environmental History at the University of Vienna. She discusses the early history of the European Society for Environmental History (ESEH), including the first ESEH conference in Saint Andrews, Scotland, the establishment of the society's structure, and the creation of its website. Topics include the society's origins, early conferences, and initial digital resources.

The article explores the connection between the Handlová landslide and the forced displacement of Germans from the region after World War Two, examining how past events influenced the disaster. Topics discussed include the impact of the displacement on local land use, the alteration of infrastructure by new settlers, and the subsequent environmental consequences of these changes.

The present work aims to evaluate potential sources of uncertainty associated with rainfall-triggered event-based landslide inventories within the framework of landslide susceptibility assessment. Therefore, this study addresses the following questions: (i) How representative is an event-based landslide inventory map of the total landslide activity and distribution in a study area?; (ii) How reliable is an event-based landslide susceptibility map?; (iii) How appropriate is an event-based landslide inventory map for independently validating a landslide susceptibility map? To address these questions, two independent and contrasting rainfall event-based landslide inventories were used, together with a historical landslide inventory, to assess landslide susceptibility for different types of landslides in a study area located north of Lisbon, Portugal. The results revealed the following findings: (i) contrasting rainfall critical conditions for failure can trigger similar landslide types, although they may vary in size and be spatially constrained by different predisposing conditions, particularly lithology and soil type; (ii) landslide susceptibility models using event-based landslide inventories are not reliable in the study area, regardless of the landslide inventory map used for training and validation; and (iii) complementary sources of uncertainty results from using incomplete historical landslide inventories to assess landslide susceptibility and non-totally independent landslide inventories for modeling validation. The present study enhances the understanding of regional landslide susceptibility patterns based on contrasting rainfall-trigger conditions, providing valuable information to minimize exposure; to design regional landslide early warning systems for specific rainfall-trigger landslide events; and to improve the response and preparedness of civil protection services. [ABSTRACT FROM AUTHOR]

The eastern Himalayan syntaxis region is located on the eastern edge of the Qinghai–Tibet Plateau, and it is one of the regions with the most intense geological tectonic activity in the world. There have been many large-scale landslides in the eastern Himalayan syntaxis region and the distribution of these landslides is of great significance for the inversion of regional tectonic activity strength, major engineering construction and urban–rural planning. However, no researchers have systematically studied all these landslides of this area. In this study, based on Google Earth satellite imagery, landslides were identified using artificial visual interpretation. Then, we analysed 11 landslide-influencing factors were selected, comprising topographic factors (elevation, slope, aspect, curvature), geological environmental factors (strata, distance to faults, distance to water, distance to roads, normalized difference vegetation index), inducing factors (peak ground acceleration, rainfall), the relationships between the distribution law of landslides and influencing factors. Finally, we used the logistic regression model, the weight of evidence model and the weight of evidence–logistic regression coupled model to evaluate the landslide susceptibility. [ABSTRACT FROM AUTHOR]

The selection of disaster-inducing factors and the construction of assessment models are two important stages in landslide susceptibility assessment. Existing research has neglected the influence of time-varying dynamic factors on landslide susceptibility. On the contrary, the best assessment model that fits the characteristics of disaster-pregnant environment in a certain area needs to be determined through a large number of comparative studies. In this paper, Boshan District, China was taken as the research area, and the assessment factor combination of static disaster-inducing factors and the change value of dynamic disaster-inducing factors in the current year was constructed. Landslide susceptibility modeling was carried out by random forest (RF), logistic regression (LR), support vector machine (SVM), stacking ensemble and convolutional neural network (CNN), and the assessment model with the highest accuracy was determined based on the area under the curve (AUC) method. Based on the geodetector, the interpretation degree of land use to landslide susceptibility and the relationship between the change information of dynamic disaster-inducing factors and the spatial distribution of landslide susceptibility were analyzed. The results show that CNN outperforms other models in the performance of modeling, with an AUC value of 0.920. The extremely high sensitive zones for landslides in the Boshan District were mainly distributed in the northwest, south, and east regions. The overall explanatory power of land use on landslide susceptibility shows a declining trend, suggesting that the spatial layout of land use in the Boshan District has been optimized. The rapidly growing population has destroyed the geological and hydrological environment and increased the probability of landslide susceptibility; Multiple acute changes of the normalized difference vegetation index (NDVI) in the opposite direction were more likely to trigger landslides, so it is not suitable to carry out logging, planting and other work repeatedly in a short time. This research can provide a theoretical foundation for land use planning and landslide prevention policies in the Boshan District. [ABSTRACT FROM AUTHOR]

The impact of earthquake-induced landslides is a global concern, particularly in the Himalayas and its nearby region, leading to substantial socioeconomic losses. High seismicity along with intense rainfall and steep slopes make the Himalayan region more vulnerable to these landslides. Existing research on regional scale analysis has mainly focused on studying landslides triggered by rainfall or earthquakes separately, with limited studies considering the combined effects of both. The objective of this research is to develop a GIS-based data integration approach for mapping shallow translational landslide susceptibility at regional scale, considering the combined effect of earthquakes and rainfall. The methodology utilizes a combination of the pseudostatic approach and hydrological models, taking advantage of publicly available topographic, seismic, geological, and remote sensing data and requiring basic geotechnical properties obtained from conventional tests to determine factor of safety (FoS). The approach has been implemented along an important and strategic highway corridor in the Indian state of Sikkim, located in the Eastern Himalayan region. The FoS distribution maps developed using the proposed approach have been validated against the reported landslides triggered in the study area due to the 2011 moment magnitude (Mw) 6.9 Sikkim earthquake. The proposed approach performed well in terms of prediction, with a success rate of 74.75%. Finally, the FoS distribution maps are generated for different scenarios. These maps provide significant insights that can be utilized by local governments, transportation agencies, and policymakers to proactively identify high-risk zones and develop early warning systems to mitigate the risk. Practical Applications: The Himalayan region has experienced a surge in tourist activity and infrastructure development in the past decade. However, the steep slopes, coupled with high seismic activity and heavy monsoonal rainfall, make it naturally prone to landslides. Landslides triggered by earthquakes can further worsen the effects of the seismic activity by damaging infrastructure, including roads, leading to challenges in rescue operations, disruptions in the supply of essential commodities, and inconvenience to travelers. The occurrence of earthquake during the monsoonal season can significantly increase the likelihood of landslides. To address this issue, a methodology has been proposed to identify areas prone to landslides caused by combined action of rainfall and earthquakes, focusing on a strategic highway in the Eastern Himalayas. By considering different scenarios of rainfall and earthquakes, various maps have been created which highlights the high-risk zones. These maps serve as valuable guides, indicating where it's unsafe to construct infrastructure and which highway sections are more susceptible to landslides. Equipped with this information, policy makers can construct more robust roads, plan alternative routes, ensure better connectivity, and provide early warnings to minimize the disruptive effects of landslides on people and infrastructure. [ABSTRACT FROM AUTHOR]

The landslide susceptibility map estimates the quantitative relationship between known landslides and control factors, and it has been used for site selection of infrastructures and geo-disaster management. As landslides and rockfalls occur frequently in mountainous areas in Hebei Province, China, due to road construction, the managing government needs to evaluate the vulnerability of geo-disasters in the road slopes to avoid unfavorable site selection for subsequent road constructions. Some typical collector road slopes were used as the study area in Pingshan County, Hebei Province. By analyzing the landslide triggering factors, we determined classification criteria and proposed a comprehensive method for determining the weighting. The respective weighting was calculated by the AHP and CRITIC method, and the combination weighting was determined by the game theory method. The landslide susceptibility of collector roads was evaluated and mapped using the ArcGIS platform. The susceptibility map was validated using landslide field investigation. The validation results show the effectiveness of the susceptibility methods, given the good number of correctly classified landslides. The landslide susceptibility map could have a significant impact on reducing the vulnerability of infrastructure to landslides in Hebei Province, China. [ABSTRACT FROM AUTHOR]

This study breaks new ground by developing a multi-hazard vulnerability map for the Tensift watershed and the Haouz plain in the Moroccan High Atlas area. The unique juxtaposition of flat and mountainous terrain in this area increases sensitivity to natural hazards, making it an ideal location for this research. Previous extreme events in this region have underscored the urgent need for proactive mitigation strategies, especially as these hazards increasingly intersect with human activities, including agriculture and infrastructure development. In this study six advanced machine learning (ML) models were used to comprehensively assess the combined probability of three significant natural hazards: flooding, gully erosion, and landslides. These models rely on causal factors derived from reputable sources, including geology, topography, meteorology, human activities, and hydrology. The research's rigorous validation process, which includes metrics such as specificity, precision, sensitivity, and accuracy, underlines the robust performance of all six models. The validation process involved comparing the model's predictions with actual hazard occurrences over a specific period. According to the outcomes in terms of the area under curve (AUC), the XGBoost model emerged as the most predictive, with remarkable AUC values of 93.41% for landslides, 91.07% for gully erosion and 93.78% for flooding. Based on the overall findings of this study, a multi-hazard risk map was created using the relationship between flood risk, gully erosion, and landslides in a geographic information system (GIS) architecture. The innovative approach presented in this work, which combined ML algorithms with geographical data, demonstrates the power of these tools in sustainable land management and the protection of communities and their assets in the Moroccan High Atlas and regions with similar topographical, geological, and meteorological conditions that are vulnerable to the aforementioned risks. [ABSTRACT FROM AUTHOR]

Seismic landslide susceptibility evaluation models are usually built on the basis of historical sample data; however, the evaluation results are often unsatisfactory when the environmental settings differ between the historical sample data region and application region. Therefore, similarity between the environmental settings is important for the application of such models. In this paper, a seismic landslide susceptibility evaluation model was first built using data from the 2008 Ms 8.0 Wenchuan earthquake-induced landslide, and the model was then used to evaluate the 2022 Ms 6.8 Luding earthquake area. In addition, the grade of susceptibility is typically represented by the landslide density, which is insufficient for capturing the details of landslides, such as their sizes, frequencies, and spatial distribution patterns. The authors therefore use a large and concentrated landslide as the susceptibility grade for the Luding earthquake area. The test results demonstrate that these two areas have similar background environments. The area under the curve (AUC) value of the receiver operating characteristics (ROC) curve of the evaluation accuracy for the model applied to the Luding earthquake area is 0.889, which indicates relatively high accuracy. Besides, the results also demonstrate that the evaluations are consistent with the disaster situation of the Moxi Platform, Wandong Village, as well as the Dagangshan Hydropower Station area. Therefore, it is reliable to apply the susceptibility evaluation model based on the Wenchuan earthquake data to the Luding earthquake area. These results show that better evaluations can be obtained based on environmental similarity tests between the areas used for historical data modeling and areas to which the models are applied. [ABSTRACT FROM AUTHOR]

Introduction: The Indian Himalayas' susceptibility to landslides, particularly as a location where climate change effects may be event catalysts, necessitates the development of dependable landslide susceptibility maps (LSM). Method: This study diverges from traditional binary classification models, framing LSM as a positive-unlabeled learning problem. This approach acknowledges that regions without recorded landslides are not necessarily at low risk but could simply have not experienced landslides yet. The study utilizes novel positive-unlabeled learning-enhanced algorithms—Random Forest, K-Nearest Neighbor, and Decision Tree—to create LSM for Chamoli district, India. Eleven causative factors for landslides are identified, including elevation, aspect, slope, geology, geomorphology, distance to lineament, lithology, NDVI, distance to river, distance to road and residential land use. To address spatial correlation biases, instead of randomly splitting the dataset, the study adopts spatial splitting to get the training and testing datasets. Conclusion: The study reveals that positive-unlabeled learning substantially improves the Area Under Curve and recall, leading to a more conservative LSM compared to binary classification methods. Analysis shows that the southern region of Chamoli exhibits high recall but lower accuracy, suggesting a latent high landslide susceptibility despite a lack of historical landslides in this region. The study also quantifies the impact of human activity on landslide risk, indicating an elevated threat to life and the local economy, especially in Chamoli's southwestern areas. [ABSTRACT FROM AUTHOR]

Coseismic landslides have the potential to cause catastrophic disasters. Thus, it is of crucial importance to conduct a comprehensive regional assessment of susceptibility to coseismic landslides. This study rigorously interprets 13,759 coseismic landslides triggered by the 2022 Luding earthquake within the seismic zone. Employing the Newmark method, we systematically assess the susceptibility to coseismic landslides through the application of six distinct displacement regression models. The efficacy of these models is validated against the actual landslide inventory using the area under the receiver operating characteristic (ROC) curve. A hazard map of coseismic landslides is generated based on the displacement regression model with the highest degree of fit. The results show that Moxi Town, Detuo Town, the flanks of the Daduhe River, Wandonghe River, Hailuogou River, and Yanzigou River are high-susceptibility areas for coseismic landslides. This study explores factors influencing model fit, revealing that the inclusion of the epicentral distance and the distance to the seismogenic fault in displacement prediction enhances model performance. Nevertheless, in close proximity to fault zones, the distance to the seismogenic fault exerts a more significant influence on the spatial distribution density of coseismic landslides compared to the epicentral distance. Conversely, in regions situated further from fault zones, the epicentral distance has a greater impact on the spatial distribution density of coseismic landslides compared to the distance to the seismogenic fault. These findings contribute to a nuanced understanding of coseismic landslide susceptibility and offer valuable insights for future Newmark method-based coseismic landslide displacement calculations. [ABSTRACT FROM AUTHOR]

Landslide event detection poses a significant challenge in the remote sensing community, especially with the advancements in computer vision technology. As computational capabilities continue to grow, the traditional manual and partially automated methods of landslide recognition from remote sensing data are transitioning towards automatic approaches using deep learning algorithms. Moreover, attention models, encouraged by the human visual system, have emerged as crucial modules in diverse applications including natural hazard assessment. Therefore, we suggest a novel and intelligent generalized efficient layer aggregation network (GELAN) based on two prevalent attention modules, efficient channel attention (ECA) and convolutional block attention module (CBAM), to enrich landslide detection techniques from satellite images. CBAM and ECA are separately integrated into GELAN at different locations. The experiments are conducted using satellite images of the Nepal Himalayan region. Standard metrics such as precision, recall, F-score, and mAP (mean average precision) are considered for quantitative evaluation. GELANc+CBAM (F-score = 81.5%) demonstrates the best performance. This study underscores the suitability of the proposed approach in up-to-date inventory creation and accurate landslide mapping for disaster recovery and response efforts. Moreover, it contributes to developing early prediction models for landslide hazards. [ABSTRACT FROM AUTHOR]

• A regional CDW landfill landslide risk assessment method is developed. • Most identified landfills located at city administrative borders. • Nearly 70 % of landfills in Shenzhen are at high landslide risk. • Landfills at city internal administrative junctions typically face high risks. In recent years, construction and demolition waste (CDW) landfills landslide accidents have occurred globally, with consequences varying due to surrounding environmental factors. Risk monitoring is crucial to mitigate these risks effectively. Existing studies mainly focus on improving risk assessment accuracy for individual landfills, lacking the ability to rapidly assess multiple landfills at a regional scale. This study proposes an innovative approach utilizing deep learning models to quickly locate suspected landfills and develop risk assessment models based on surrounding environmental factors. Shenzhen, China, with significant CDW disposal pressure, is chosen as the empirical research area. Empirical findings from this study include: (1) the identification of 52 suspected CDW landfills predominantly located at the administrative boundaries within Shenzhen, specifically in the Longgang, Guangming, and Bao'an districts; (2) landfills at the lower risk of landslides are typically found near the northern borders adjacent to cities like Huizhou and Dongguan; (3) landfills situated at the internal administrative junctions generally exhibit higher landslide risks; (4) about 70 % of these landfills are high-risk, mostly located in densely populated areas with substantial rainfall and complex topographies. This study advances landfill landslide risk assessments by integrating computer vision and environmental analysis, providing a robust method for governments to rapidly evaluate risks at CDW landfills regionally. The adaptable models can be customized for various urban and broadened to general landfills by adjusting specific indicators, enhancing environmental safety protocols and risk management strategies effectively. [ABSTRACT FROM AUTHOR]

Precise landslide monitoring is crucial for understanding and mitigating their impact. The Three Gorges Dam has exacerbated landslides due to steep slopes and rising water levels. This study used ALOS-2 PALSAR-2 (2016–2017) and Sentinel-1A (2016–2018) data to monitor the Daping slope. Findings showed deformation rates of −86.3 mm/y (ALOS-2) and −62 mm/y (Sentinel-1A), confirmed by GNSS data. Analysis indicated that rainfall and water level fluctuations drive the Daping landslide, highlighting key factors influencing landslides in the Three Gorges region and their threats to life and property. [ABSTRACT FROM AUTHOR]

The appropriate selection of machine learning samples forms the foundation for utilizing machine learning models. However, in landslide susceptibility evaluation, discrepancies arise when non-landslide samples are positioned within areas prone to landslides or demonstrate spatial biases, leading to differences in model predictions. To address the impact of non-landslide sample selection on landslide susceptibility predictions, this study uses the western region of Henan Province as a case study. Utilizing historical data, remote sensing interpretation, and field surveys, a sample dataset comprising 834 landslide points is obtained. Ten environmental factors, including elevation, slope, aspect, profile curvature, land cover, lithology, topographic wetness index, distance from river, distance from faults, and distance from road, are chosen to establish an evaluation index system. Negative sample sampling areas are delineated based on the susceptibility assessment outcomes derived from the information value model. Two sampling strategies, whole-region random sampling (I) and partition-based random sampling (II), are employed. Random Forest (RF) and Back Propagation Neural Network (BPNN) models are used to forecast and delineate landslide susceptibility in the western region of Henan Province, with prediction accuracy evaluated. The model prediction accuracy is ranked as follows: II-BPNN (AUC = 0.9522) > II-RF (AUC = 0.9464) > I-RF (AUC = 0.8247) > I-BPNN (AUC = 0.8068). Under the Receiver Operating Characteristic (AUC) curve and accuracy, the II-RF and II-BPNN models exhibit increases in the region by 12.17% and 15.61%, respectively, compared to the I-RF and I-BPNN models. Moreover, the II-BPNN model shows improvements over the I-BPNN model with increases in AUC and accuracy by 14.54% and 16.52%, respectively. This indicates enhancements in model performance and predictive capability. In terms of recall and specificity, the II-RF and II-BPNN models demonstrate increases in recall by 15.09% and 17.47%, respectively, and in specificity by 15.80% and 14.99%, respectively. These findings suggest that the optimized models have better predictive capabilities for identifying landslide and non-landslide areas, effectively reducing the uncertainty introduced by point data in landslide risk prediction. [ABSTRACT FROM AUTHOR]

Landslide is a typical geological disaster distributed in most countries worldwide. Due to long-term natural weathering and human engineering disturbances, the instability of landslides is prone to occur. Once monitoring and disposal methods are implemented inappropriately, they can lead to landslide hazards, seriously threatening the safety of people's lives and property. For a long time, extensive research on landslide monitoring has been conducted from various countries, providing crucial technical support for reducing the incidence and severity of landslide hazards. However, considering the complex geological conditions of actual landslides and the direct impact of internal and external factors such as rainfall, storms, and earthquakes, the early warning accuracy of landslide hazards is still relatively low. Therefore, based on advanced research achievements, it is significant to carry out research on the current status and development trends of landslide monitoring technology. Based on the Web of Science core database, this study quantitatively analyzes the advanced research achievements in global landslide monitoring in the past decade using bibliometric analysis. A systematic analysis of landslide monitoring technology development is conducted according to each study's publication time, keywords, and countries. On this basis, a multi-dimensional monitoring system for landslides was proposed, which utilizes the complementary advantages of multi-dimensional monitoring technology to achieve all-round, high-precision, and real-time monitoring of landslides. Finally, taking the Xinpu landslide in the Three Gorges Region of China as an example, a multi-source and multi-field-monitoring experiment was conducted. The application of landslide multi-field-monitoring technology provides an essential reference for monitoring, early warning, as well as the scientific prevention and control of landslide hazard. [ABSTRACT FROM AUTHOR]

To overcome the reliance on large samples and high-quality data in existing evaluation methods, while also improving evaluation efficiency and accuracy, this paper proposes a method for rapid landslide hazard assessment. This method utilizes existing research findings and specific analytical techniques for the study area to conduct rapid assessments. Taking the landslide in Yongxing Town, Mingshan Area, Ya'an City, Sichuan Province as an example, the Analytic Hierarchy Process (AHP) is combined with the Information Value (IV) method, Certainty Factor (CF) method, and Frequency Ratio (FR) method from previous studies, The AHP-IV and AHP-FR methods assess the study area as a moderately hazardous zone, while the AHP-CF method assesses it as a slightly hazardous zone. Affected by the strong 2013 Lushan earthquake, the landslide in the study area caused permanent damage. Field investigation results show that the landslide hazard in the study area is moderate, and the AHP-IV and AHP-FR methods are more consistent with the actual field results. The AHP-CF method, due to not considering the water system factor and having certain errors in its discrimination method, leans towards a safer assessment, The results of the three evaluation methods are somewhat consistent. [ABSTRACT FROM AUTHOR]

The Northwestern Yunnan Region (NWYR), located on the southeastern edge of the Tibetan Plateau, is characterized by a combination of low-crustal flow and gravitational collapse, giving rise to a complex network of active faults. This presents significant seismic hazards, particularly due to the potential for multi-segment ruptures and resulting landslides, as demonstrated by the historical 1515 M 7.8 Yongshen Earthquake. This article presented a novel seismic hazard modeling study for the NWYR, integrating fault slip parameters and assessing multi-segment rupturing risks. Among the four potential multi-segment rupture combination models examined, Model 1, characterized by multi-segment rupture combinations on single faults, particularly fracturing the Zhongdian fault, emerges as the most suitable for the NWYR, supported by the alignment of modeled seismicity rates with fault slip rates. Our analysis demonstrated that peak ground-motion acceleration values, calculated with a 475-year return period from modeled seismicity rates, exhibited a strong correlation with fault distribution, averagely higher than the China Seismic Ground Motion Parameters Zonation Map. Furthermore, we conducted simulations to forecast landslide occurrence probabilities across our peak ground-motion acceleration distribution map. Our findings underscored that the observed combinations of multi-segment ruptures and their associated behaviors were in alignment with the small block rotation triggered by the gravitational collapse of the Tibetan Plateau. This result highlighted the intricate interplay between multi-segment rupturing hazards and regional geological dynamics. [ABSTRACT FROM AUTHOR]

Climate change and climate variation influence the occurrence of natural disasters, especially water-related disasters. Landslides are a serious hydrogeohazard in Thailand. Hence, this study aims to project the spatial changes in the landslide susceptibility area in the Nakhon Si Thammarat province of southern Thailand. The study utilizes five climate models of CMIP6 (INM-CM4-8, IITM-ESM, MPI-ESM1-2-LR, CNRM-ESM2-1 and CNRM-CM6.-1) and conducts analyses based on 2 shared socioeconomic pathways (SSPs) of tier 1, which include SSP2-4.5 and SSP5-8.5. The linear scaling bias correction technique is applied to adjust for any biases in the climate models, and the model results are combined using the ensemble mean method. To achieve the study aims, a GIS-aided physically based landslide susceptibility model is used to predict changes in spatial aspects of the landslide susceptibility area. The analysis predicted spatial changes in the landslide susceptibility area over the next 20 years (2023 to 2042). According to the analysis, the results showed that the maximum increase in landslide susceptibility areas is approximately 29%, and the maximum decrease in landslide susceptibility areas is approximately 25% under SSP2-4.5. For SSP5-8.5, the maximum increase in landslide susceptibility areas is approximately 31%, and the maximum decrease in landslide susceptibility areas is approximately 35%. Moreover, the fluctuation of rainfall strongly influences the increase or decrease in landslide susceptibility areas. However, the landslide-prone areas remain located in areas that have experienced landslides in the past. [ABSTRACT FROM AUTHOR]

This study presents a comprehensive analysis of natural hazard susceptibility in the Makedonska Kamenica municipality of North Macedonia, encompassing erosion assessment, landslides, flash floods, and forest fire vulnerability. Employing advanced GIS and remote sensing (RS) methodologies, hazard models were meticulously developed and integrated to discern areas facing concurrent vulnerabilities. Findings unveil substantial vulnerabilities prevalent across the area, notably along steep terrain gradients, river valleys, and deforested landscapes. Erosion assessment reveals elevated rates, with a mean erosion coefficient (Z) of 0.61 and an annual erosion production of 182,712.9 m3, equivalent to a specific erosion rate of 961.6 m3/km2/year. Landslide susceptibility analysis identifies 31.8% of the municipality exhibiting a very high probability of landslides, while flash flood susceptibility models depict 3.3% of the area prone to very high flash flood potential. Forest fire susceptibility mapping emphasizes slightly less than one-third of the municipality's forested area is highly or very highly susceptible to fires. Integration of these hazard models elucidates multi-hazard zones, revealing that 11.0% of the municipality's territory faces concurrent vulnerabilities from excessive erosion, landslides, flash floods, and forest fires. These zones are predominantly located in upstream areas, valleys of river tributaries, and the estuary region. The identification of multi-hazard zones underscores the critical need for targeted preventive measures and robust land management strategies to mitigate potential disasters and safeguard both human infrastructure and natural ecosystems. Recommendations include the implementation of enhanced monitoring systems, validation methodologies, and community engagement initiatives to bolster hazard preparedness and response capabilities effectively. [ABSTRACT FROM AUTHOR]

Landslides triggered by rainfall are among the most frequent causes of natural disasters in mountainous terrains. However, landslide susceptibility assessments are often limited due to the scarcity of reliable observations. Due to this lack of data, especially in developing countries, remote sensing is used for landslide susceptibility analysis. This study presents the application of remote sensing data and a logistic regression model to assess landslide susceptibility in a basin on a remote terrain in the northern Colombian Andes, where a rainstorm on May 18th, 2015, triggered more than 40 landslides and an associated debris flow afterwards. The methodology applied is based on free access remote sensing tools, since the study area is considered a scarce-data zone. The results show that free remote sensing tools provide enough information to run a model as logistic regression and achieve a successful first approach to the landslide susceptibility map of complex terrains as the study area. This suggests that the proposed methodology could be implemented in several regions with similar characteristics based only on free access information. [ABSTRACT FROM AUTHOR]

The suddenness of landslide disasters often causes significant loss of life and property. Accurate assessment of landslide disaster susceptibility is of great significance in enhancing the ability of accurate disaster prevention. To address the problems of strong subjectivity in the selection of assessment indicators and low efficiency of the assessment process caused by the insufficient application of a priori knowledge in landslide susceptibility assessment, in this paper, we propose a novel landslide susceptibility assessment framework by combing domain knowledge graph and machine learning algorithms. Firstly, we combine unstructured data, extract priori knowledge based on the Unified Structure Generation for Universal Information Extraction Pre-trained model (UIE) fine-tuned with a small amount of labeled data to construct a landslide susceptibility knowledge graph. We use Paired Relation Vectors (PairRE) to characterize the knowledge graph, then construct a target area characterization factor recommendation model by calculating spatial correlation, attribute similarity, Term Frequency–Inverse Document Frequency (TF-IDF) metrics. We select the optimal model and optimal feature combination among six typical machine learning (ML) models to construct interpretable landslide disaster susceptibility assessment mapping. Experimental validation and analysis are carried out on the three gorges area (TGA), and the results show the effectiveness of the feature factors recommended by the knowledge graph characterization learning, with the overall accuracy of the model after adding associated disaster factors reaching 87.2%. The methodology proposed in this research is a better contribution to the knowledge and data-driven assessment of landslide disaster susceptibility. [ABSTRACT FROM AUTHOR]

The accurate prediction of landslide susceptibility relies on effectively handling landslide absence samples in machine learning (ML) models. However, existing research tends to generate these samples in feature space, posing challenges in field validation, or using physics-informed models, thereby limiting their applicability. The rapid progress of interferometric synthetic aperture radar (InSAR) technology may bridge this gap by offering satellite images with extensive area coverage and precise surface deformation measurements at millimeter scales. Here, we propose an InSAR-based sampling strategy to generate absence samples for landslide susceptibility mapping in the Badong–Zigui area near the Three Gorges Reservoir, China. We achieve this by employing a Small Baseline Subset (SBAS) InSAR to generate the annual average ground deformation. Subsequently, we select absence samples from slopes with very slow deformation. Logistic regression, support vector machine, and random forest models demonstrate improvement when using InSAR-based absence samples, indicating enhanced accuracy in reflecting non-landslide conditions. Furthermore, we compare different integration methods to integrate InSAR into ML models, including absence sampling, joint training, overlay weights, and their combination, finding that utilizing all three methods simultaneously optimally improves landslide susceptibility models. [ABSTRACT FROM AUTHOR]

Landslide susceptibility denotes the likelihood of a disaster event under specific conditions. The assessment of landslide susceptibility has transitioned from qualitative to quantitative methods. With the integration of information technology in geological hazard analysis, a range of quantitative models for assessing landslide susceptibility has emerged and is now widely used. To compare and evaluate the accuracy of these models, this study focuses on Xupu County in Hunan Province, applying several models, including the CF model, FR model, CF-LR coupled model, FR-LR coupled model, SVM model, and RF model, to assess regional landslide susceptibility. ROC curves are used to evaluate the reliability of the model's predictions. The evaluation results reveal that the CF model (AUC = 0.756), FR model (AUC = 0.764), CF-LR model (AUC = 0.776), FR-LR model (AUC = 0.781), SVM model (AUC = 0.814), and RF model (AUC = 0.912) all have AUC values within the range of 0.7–0.9, indicating that the overall accuracy of the models is good and can provide a reference for landslide susceptibility zoning in the study area. Among these, the Random Forest model demonstrates the best accuracy for landslide susceptibility zoning in the study area. By extracting the extremely high susceptibility zones from the landslide susceptibility zonings obtained by six models, a comparative analysis of model adaptability was conducted. The results indicate that the Random Forest model has the best adaptability under specific conditions in Xupu County. [ABSTRACT FROM AUTHOR]

This study develops a model to assess building vulnerability across Xinxing County by integrating quantitative derivation with machine learning techniques. Building vulnerability is characterized as a function of landslide hazard risk and building resistance, wherein landslide hazard risk is derived using CNN (1D) for nine hazard-causing factors (elevation, slope, slope shape, geotechnical body type, geological structure, vegetation cover, watershed, and land-use type) and landslide sites; building resistance is determined through quantitative derivation. After evaluating the building susceptibility of all the structures, the susceptibility of each village is then calculated through subvillage statistics, which are aimed at identifying the specific needs of each area. Simultaneously, different landslide hazard classes are categorized, and an analysis of the correlation between building resistance and susceptibility reveals that building susceptibility exhibits a positive correlation with landslide hazard and a negative correlation with building resistance. Following a comprehensive assessment of building susceptibility in Xinxing County, a sample encompassing different landslide intensity areas and susceptibility classes of buildings was chosen for on-site validation, thus yielding an accuracy rate of the results as high as 94.5%. [ABSTRACT FROM AUTHOR]

Landslides pose a significant risk to human life and property, making landslide susceptibility mapping (LSM) a crucial component of landslide risk assessment. However, spatial correlations among mapping units are often neglected in statistical or machine learning models proposed for LSM. This study proposes KNN-GCN, a deep learning model for slope-unit-based LSM based on a graph convolutional network (GCN) and the K-nearest neighbor (KNN) algorithm. The model was experimentally applied to the Lueyang region and validated through the following steps. Firstly, we collected data for 15 landslide causal factors and from landslide inventories and established a slope unit map (SUM) through slope unit division. Next, we performed a multicollinearity analysis of landslide causal factors and divided the training and test sets at a 7:3 ratio. We then constructed a GCN model based on a slope unit graph (SUG) generated from the SUM using the KNN algorithm. The proposed KNN-GCN model was tuned using a grid search with fivefold cross-validation on the training set, and then trained and validated on training and test sets separately. Finally, the performance of the KNN-GCN model was compared with that of six other models which were categorized into two groups: CG#1 was the traditional KNN, support vector regression (SVC), and automated machine learning (AutoML), and CG#2 included KNN-G, SVC-G and AutoML-G with additional spatial information. Our results demonstrate that the proposed model achieves superior performance (area under the curve [AUC] = 0.8351) and generates the most comprehensible susceptibility map with distinct boundaries between different susceptibility levels. Notably, while the proposed KNN-GCN model displays exceptional performance in slope-unit-based LSM, its implementation requires high-level computing resources, and it is not recommended for small datasets. [ABSTRACT FROM AUTHOR]

Machine learning (ML)-based landslide susceptibility mapping (LSM) has achieved substantial success in landslide risk management applications. However, the complexity of classically trained ML is often beyond nonexperts. With the rapid growth of practical applications, an "off-the-shelf" ML technique that can be easily used by nonexperts is highly relevant. In the present study, a new paradigm for an end-to-end ML modeling was adopted for LSM in the Three Gorges Reservoir area (TGRA) using automated machine learning (AutoML) as the backend model support for the paradigm. A well-defined database consisting of data from 290 landslides and 11 conditioning factors was collected for implementing AutoML and compared with classically trained ML approaches. The stacked ensemble model from AutoML achieved the best performance (0.954), surpassing the support vector machine with artificial bee colony optimization (ABC-SVM, 0.931), gray wolf optimization (GWO-SVM, 0.925), particle swarm optimization (PSO-SVM, 0.925), water cycle algorithm (WCA-SVM, 0.925), grid search (GS-SVM, 0.920), multilayer perceptron (MLP, 0.908), classification and regression tree (CART, 0.891), K-nearest neighbor (KNN, 0.898), and random forest (RF, 0.909) in terms of the area under the receiver operating characteristic curve (AUC). Notable improvements of up to 11% in AUC demonstrate that the AutoML approach succeeded in LSM and could be used to select the best model with minimal effort or intervention from the user. Moreover, a simple model that has been customarily ignored by practitioners and researchers has been identified with performance satisfying practical requirements. The experimental results indicate that AutoML provides an attractive alternative to manual ML practice, especially for practitioners with little expert knowledge in ML, by delivering a high-performance off-the-shelf solution for ML model development for LSM. [ABSTRACT FROM AUTHOR]

Co-seismic landslide detection is essential for post-disaster rescue and risk assessment after an earthquake event. However, a variety of ground objects, including roads and bare land, have spectral characteristics similar to those of co-seismic landslides, making it difficult to gather information and assess their impact rapidly and accurately. Therefore, an automatic detection method based on a deep learning model, named ENVINet5, with multiple features (ENVINet5_MF) was proposed to solve this problem and improve the detection accuracy of co-seismic landslides. The ENVINet5_MF method is advantageous for co-seismic landslide detection because it features a landslide gain index (LGI) that effectively eliminates the spectral interference of bare land and roads. We conducted two experiments using multi-temporal PlanetScope images acquired in Hokkaido, Japan, and Mainling, China. The accuracy evaluation and rationality analysis show that ENVINet5_MF performed better than comparative methods and that the co-seismic landslide areas detected by ENVINet5_MF were the most consistent with ground reference data. The findings of this study suggest that ENVINet5_MF can provide an efficient and accurate method for coseismic landslide detection to ensure a rapid response to co-seismic landslide disasters. [ABSTRACT FROM AUTHOR]

Machine learning models are widely used for landslide susceptibility prediction (LSP). To better develop a landslide susceptibility prediction model for the Loess Plateau, this study compared different machine-learning models (Logistic regression (LR), support vector machines (SVM), random forests (RF), Naïve Bayes (NB), and multilayer perceptron (MLP)). Using Xunyi County, China as the study area, 1096 landslides were collected and divided into a training set (70%) and a test set (30%). Significant influencing factors were selected from 20 landslide factors using GeoDetector. The relationships between these factors and landslides were determined by normalized frequency ratios. Five trained machine learning models calculated landslide susceptibility indices and generated landslide susceptibility maps. Additionally, the accuracy (ACC), precision (PRE), recall (REC), F1 score, AUC values, LSI distribution characteristics, and overlay analysis of historical landslides with LSM were used to evaluate the performance of the models. The results show that the LSP results of the five models are generally reasonable. The results further indicated that the use of GeoDetector was able to filter out the main factors of eolian landslides, improving the predictive performance of the model and obtaining better LSMs. The RF model had the best overall performance, followed by the SVM, and the MLP model created LSM high susceptibility zones that could contain the highest number of historical landslides. The q-values of factor contributions indicate that elevation, NDVI, rainfall, POI kernel density, and RDLS are the main factors controlling landslides, which need to be paid attention to for landslide control in the Loess Plateau region. The results of this study can provide a reference for the follow-up study of landslide prevention and control, especially landslide susceptibility modeling in the Loess Plateau. [ABSTRACT FROM AUTHOR]

Land degradation (LD) is a significant environmental issue that needs to be spatially mapped in different areas. This research provides a framework to prioritize the geo-environmental and anthropogenic factors on LD in a semi-arid region, Qazvin Plain, in Iran based on the maximum entropy model for the first time and also to produce the LD hazard map. The LD inventory map that shows the occurrence points of LD was prepared based on the decreasing trend of net primary productivity (NPP) over 20 years. 120 random points were selected as degraded sites where NPP showed a decreasing trend. Several environmental and anthropogenic factors including temperature, rainfall, land use, normalized difference vegetation index (NDVI), vegetation soil salinity index (VSSI), visible and shortwave infrared drought index (VSDI), electrical conductivity (EC) and sodium adsorption ratio (SAR) of groundwater, groundwater table, annual depletion of groundwater resources, slope, aspect, and altitude were considered as predictive factors of LD and their relative contributions were determined using the maximum entropy model. According to the findings, 49.74% of the region was in the class of low degradation. Also, 22.57%, 17.87%, and 9.82% of the plain were related to the moderate, high, and very high degradation classes, respectively. The model specified altitude as the most significant variable influencing LD followed by land use, slope, and VSSI. The least important variable affecting LD in the study area was the aspect. The results of modeling LD also showed that the areas most sensitive to LD were frequently rangelands which are mostly found on steep slopes and highlands. Based on the UAC value, the model illustrated a very good efficiency with a value of 0.8. According to the results, the maximum entropy model successfully mapped the LD hazard in the Qazvin plain. [ABSTRACT FROM AUTHOR]

On August 12, 2015, a catastrophic landslide occurred in Shanyang County, Shaanxi Province, China, resulting in 7 deaths and 53 missing. This study investigates the lifecycle evolution and failure mechanism of the Shanyang landslide with multi-source remote sensing data, emphasizing the critical role of locked segments in the Shanyang landslide. Differential interferometric analysis and deformation decomposition were utilized to reveal the pre-failure deformation pattern of the Shanyang landslide. Creeping deformation was found along the underlying soft layer 4 months prior to the landslide, with the deformation mainly occurring downslope and controlled by the locked segment at the front edge of the slope. The integration of a 1:1000 pre-failure topographic map and a high-precision post-failure digital elevation model determined the landslide volume to be 1.60 × 106 m3 and revealed a maximum travel distance of 500 m. Combining engineering geological zoning with deformation data, the Shanyang landslide was classified as a typical locked-segment-dominated slide in soft-hard interbedded strata, with rainfall as a key deformation influence factor. Finally, using the time series deformation from SBAS-InSAR, the post-failure stability of the landslide area was analyzed. This study demonstrates the potential of integrating multi-temporal remote sensing techniques to identify the entire deformation and destruction process of landslides and their influencing factors, which offers valuable insights for improving early landslide warnings and hazard assessments. [ABSTRACT FROM AUTHOR]

Most regional landslide susceptibility models do not consider the evolving soil hydrological conditions leading up to a multiple occurrence regional landslide event. This results in inaccurate predictions due to the non-linear behaviour of the terrain. To address this, we have developed a simple and efficient model that incorporates the mid-term evolution of soil hydrological conditions. The model combines a water balance model and a geotechnical model based on infinite slope theory. The analysis of 561 high-intensity rainfall events in a typhoon-prone region of the Philippines revealed that the percolation of water during the 5-month wet season is crucial in determining landslide susceptibility. Consequently, high-intensity rainfall events at the start of the wet season are less likely to trigger landslides, while later events are more hazardous. We analysed the change in landslide susceptibility during the 2018 rainy season by comparing the probability of failure (PoF) before and after three high-intensity rainfall events (July, August and September). Only the event in September caused a significant increase in the probability of failure (PoF). The model showed an accuracy of 0.63, with stable cells better represented than unstable cells. The antecedent hydrological conditions on the lower soil layers are responsible for changes in landslide susceptibility. Our findings support the hypothesis that new approaches to developing hydro-meteorological thresholds for landslide early warning systems should be evaluated, especially in regions with strong seasonality. [ABSTRACT FROM AUTHOR]