Automated machine learning for rainfall-induced landslide hazard mapping in Luhe County of Guangdong Province,China

Landslide hazard mapping is essential for regional landslide hazard management.The main objective of this study is to construct a rainfall-induced landslide hazard map of Luhe County,China based on an automated machine learning framework(AutoGluon).A total of 2241 landslides were identified from satellite images before and after the rainfall event,and 10 impact factors including elevation,slope,aspect,normalized difference vegetation index(NDVI),topographic wetness index(TWI),lithology,land cover,distance to roads,distance to rivers,and rainfall were selected as indicators.The WeightedEnsemble model,which is an ensemble of 13 basic machine learning models weighted together,was used to output the landslide hazard assessment results.The results indicate that landslides mainly occurred in the central part of the study area,especially in Hetian and Shanghu.Totally 102.44 s were spent to train all the models,and the ensemble model WeightedEnsemble has an Area Under the Curve(AUC)value of92.36%in the test set.In addition,14.95%of the study area was determined to be at very high hazard,with a landslide density of 12.02 per square kilometer.This study serves as a significant reference for the prevention and mitigation of geological hazards and land use planning in Luhe County.

Landslide hazard susceptibility evaluation based on SBAS-InSAR technology and SSA-BP neural network algorithm:A case study of Baihetan Reservoir Area

Landslide hazard susceptibility evaluation takes on critical significance in early warning and disaster prevention and reduction.In order to solve the problems of poor effectiveness of landslide data and complex calculation of weights for multiple evaluation factors in the existing landslide susceptibility evaluation models,in this study,a method of landslide hazard susceptibility evaluation is proposed by combining SBAS-InSAR(Small Baseline Subsets-Interferometric Synthetic Aperture Radar)and SSA-BP(Sparrow Search Algorithm-Back Propagation)neural network algorithm.The SBAS-InSAR technology is adopted to identify potential landslide hazards in the study area,update the cataloging data of landslide hazards,and 11 evaluation factors are chosen for constructing the SSA-BP model for training and validation.Baihetan Reservoir area is selected as a case study for validation.As indicated by the results,the application of SBAS-InSAR technology,combined with both ascending and descending orbit data,effectively addresses the incomplete identification of landslide hazards caused by geometric distortion of single orbit SAR data(e.g.,shadow,overlay,and perspective contraction)in deep canyon areas,thereby enabling the acquisition of up-to-date landslide hazard data.Moreover,in comparison to the conventional BP(Back Propagation)algorithm,the accuracy of the model constructed by the SSA-BP algorithm exhibits a significant increase,with mean squared error and mean absolute error reduced by 0.0142 and 0.0607,respectively.Additionally,during the process of susceptibility evaluation,the SSA-BP model effectively circumvents the issue of considerable manual interventions in calculating the weight of evaluation factors.The area under the curve of this model reaches 0.909,surpassing BP(0.835),random forest(0.792),and the information value method(0.699).The risk of landslide occurrence in the Baihetan Reservoir area is positively correlated with slope,surface temperature,and deformation rate,while it is negatively correlated with fault distance and normalized difference vegetation index.Geological lithology exerts minimal influence on the occurrence of landslides,with the risk being low in forest land and high in grassland.The method proposed in this study provides a useful reference for disaster prevention and mitigation departments to perform landslide hazard susceptibility evaluations in deep canyon areas under complex geological conditions.

GIS COMPONENT BASED 3D LANDSLIDE HAZARD ASSESSMENT SYSTEM: 3DSLOPEGIS

In this paper, based on a new Geographic Information System (GIS) grid-based three-dimensional (3D) deterministic model and taken the slope unit as the study object, the landslide hazard is mapped by the index of the 3D safety factor. Compared with the one-dimensional (1D) model of infinite slope, which is now widely used for deterministic model based landslide hazard assessment in GIS, the GIS grid-based 3D model is more acceptable and is more adaptable for three-dimensional landslide. Assuming the initial slip as the lower part of an ellipsoid, the 3D critical slip surface in the 3D slope stability analysis is obtained by means of a minimization of the 3D safety factor using the Monte Carlo random simulation. Using a hydraulic model tool for the watershed analysis in GIS, an automatic process has been developed for identifying the slope unit from digital elevation model (DEM) data. Compared with the grid-based landslide hazard mapping method, the slope unit possesses clear topographical meaning, so its results are more credible. All the calculations are implemented by a computational program, 3DSlopeGIS, in which a GIS component is used for fulfilling the GIS spatial analysis function, and all the data for the 3D slope safety factor calculation are in the form of GIS data (the vector and the grid layers). Because of all these merits of the GIS-based 3D landslide hazard mapping method, the complex algorithms and iteration procedures of the 3D problem can also be perfectly implemented.

A multi-objective decision-making method for the treatment scheme of landslide hazard

The treatment engineering of landslide hazard is a complicated systemengineering. The selecting treatment scheme is influenced by many factors such as technology,economics, environment, and risk. The decision-making of treatment schemes of landslide hazard is aproblem of comprehensive judgment with multi-hierarchy and multi-objective. The traditional analysishierarchy process needs identity test. The traditional analysis hierarchy process is improved bymeans of optimal transfer matrix here. An improved hierarchy decision-making model for the treatmentof landslide hazard is set up. The judgment matrix obtained by the method can naturally meet therequirement of identity, so the identity test is not necessary. At last, the method is applied tothe treatment decision-making of the dangerous rock mass at the Slate Mountain, and its applicationis discussed in detail.

Disaster reduction stick equipment: A method for monitoring and early warning of pipeline-landslide hazards

Oil and gas pipelines are of great importance in China,and pipeline security problems pose a serious threat to society and the environment.Pipeline safety has therefore become an integral part of the entire national economy.Landslides are the most harmful type of pipeline accident,and have directed increasing public attention to safety issues.Although some useful results have been obtained in the investigation and prevention of pipeline-landslide hazards,there remains a need for effective monitoring and early warning methods,especially when the complexity of pipeline-landslides is considered.Because oil and gas pipeline-landslides typically occur in the superficial soil layers,monitoring instruments must be easy to install and must cause minimal disturbance to the surrounding soil and pipeline.To address the particular characteristics of pipelinelandslides,we developed a multi-parameter integrated monitoring system called disaster reduction stick equipment.In this paper,we detail this monitoring and early warning system for pipeline-landslide hazards based on an on-site monitoring network and early warning algorithms.The functionality of our system was verified by its successful application to the Chongqing Loujiazhuang pipeline-landslide in China.The results presented here provide guidelines for the monitoring,early warning,and prevention of pipeline geological hazards.

Landslide Hazard and Risk Assessment on the Northern Slope of Mt. Changbai, China

Landslide hazard and risk assessment on the northern slope of Mt. Changbai, a well-known tourist attraction near the North Korean-Chinese border, are assessed. This study is divided into two parts, namely, landslide hazard zonation and risk assessment. The 1992 Anbalagan and Singh method of landslide hazard zonation （LHZ） was modified and used in this area. In this way, an Associative Analysis Method was used in representative areas to get a measure for controlling factors （slope gradient, relative relief, vegetation, geology, discontinuity development, weak layer thickness and ground water）. For the membership degree of factor to slope failure, the middle range of limited values was used to calculate LHZ. Based on an estimation of the potential damage from slope failure, a reasonable risk assessment map was obtained using the relationship of potential damage and probable hazard to aid future planning and prediction and to avert loss of life.

Remote Sense and GIS-Based Division of Landslide Hazard Degree in Wanzhou District of the Three Gorges Reservoir Area

An evaluation model divided landslide hazard degrees in Wanzhou District of Three Gorges Reservoir Area. The model was established by GIS techniques and took land use/cover, stratum characters, slope aspect, slope gradient, elevation difference and slope shape as evaluation factors. The data of land use/cover were obtained by remote sensing, and the weights of the factors mentioned above were established by the analytic hierarchy process （AHP）. The results indicate, low danger areas in the studied area account for 66.51%, and high danger areas and very high danger areas occupy 1/3 of the total area. The regions of high and very high danger are mainly located around the urban area of Wanzhou District and on the banks of the Yangtze River with a relatively large area, where collapse and landslide directly threats densely populated areas and Three Gorges Reservoir. Slope destabilization, if occurs, will bring huge loss to social economy. All research results are consistent with the actual conditions; therefore, they can be regarded as a useful basis for planning and constructing of the reservoir area.

Landslide Hazard Zonation Mapping in Ghat Road Section of Kolli Hills, India

Landslides are the most common natural disaster in hilly terrain which causes changes in landscape and damage to life and property. The main objective of the present study was to carry out landslide hazard zonation mapping on 1:50,000 scale along ghat road section of Kolli hills using a Landslide Hazard Evaluation Factor(LHEF) rating scheme. The landslide hazard zonation map has been prepared by overlaying the terrain evaluation maps with facet map of the study area. The terrain evaluation maps include lithology, structure, slope morphometry, relative relief, land use and land cover and hydrogeological condition. The LHEF rating scheme and the Total Estimated Hazard(TEHD) were calculated as per the Bureau of Indian Standard(BIS) guidelines(IS: 14496(Part-2) 1998) for the purpose of preparation of Landslide Hazard Zonation(LHZ) map in mountainous terrains. The correction due to triggering factors such as seismicity, rainfall and anthropogenic activities were also incorporated with Total Estimated Hazard to get final corrected TEHD. The landslide hazard zonation map was classified as the high, moderate and low hazard zones along the ghat road section based on corrected TEHD.

Regional landslide hazard assessment based on Distance Evaluation Model

There are many factors influencing landslide occurrence.The key for landslide control is to confirm the regional landslide hazard factors.The Cameron Highlands of Malaysia was selected as the study area.By bivariate statistical analysis method with GIS software the authors analyzed the relationships among landslides and environmental factors such as lithology,geomorphy,elevation,road and land use.Distance Evaluation Model was developed with Landslide Density(LD).And the assessment of landslide hazard of Cameron Highlands was performed.The result shows that the model has higher prediction precision.

Landslide Hazard Mapping Using GIS and Weight of Evidence Model in Qingshui River Watershed of 2008 Wenchuan Earthquake Struck Region

Tens of thousands of landslides were triggered by May 12, 2008 earthquake over a broad area. The main purpose of this article is to apply and verify earthquake-triggered landslide hazard analysis techniques by using weight of evidence modeling in Qingshui （清水） River watershed, Deyang （德阳） City, Sichuan （四川） Province, China. Two thousand three hundred and twenty-one landslides were interpreted in the study area from aerial photographs and multi-source remote sensing imageries post-earthquake, verified by field surveys. The landslide inventory in the study area was established. A spatial database, including landslides and associated controlling parameters that may have influence on the occurrence of landslides, was constructed from topographic maps, geological maps, and enhanced thematic mapper （ETM＋） remote sensing imageries. The factors that influence landslide occurrence,such as slope angle, aspect, curvature, elevation, flow accumulation, distance from drainages, and distance from roads were calculated from the topographic maps. Lithology, distance from seismogenic fault, distance from all faults, and distance from stratigraphic boundaries were derived from the geological maps. Normalized difference vegetation index （NDV1） was extracted from ETM＋ images. Seismic intensity zoning was collected from Wenchuan （汶川） Ms8.0 Earthquake Intensity Distribution Map published by the China Earthquake Administration.Landslide hazard indices were calculated using the weight of evidence model, and landslide hazard maps were calculated from using different controlling parameters cases. The hazard map was compared with known landslide locations and verified. The success accuracy percentage of using all 13 controlling parameters was 71.82%. The resulting landslide hazard map showed five classes of landslide hazard, i.e., very high, high, moderate, low, and very low. The validation results showed satisfactory agreement between the hazard map and the existing landslides distribution data. The landslide hazard map can be used to identify and delineate unstable hazard-prone areas. It can also help planners to choose favorable locations for development schemes, such as infrastructural, buildings, road constructions, and environmental protection.

Hazard assessment of landslide disaster using information value method and analytical hierarchy process in highly tectonic Chamba region in bosom of Himalaya

The present study is focused on a comparative evaluation of landslide disaster using analytical hierarchy process and information value method for hazard assessment in highly tectonic Chamba region in bosom of Himalaya. During study, the information about the causative factors was generated and the landslide hazard zonation maps were delineated using Information Value Method(IV) and Analytical Hierarchy Process(AHP) using Arc GIS(ESRI). For this purpose, the study area was selected in a part of Ravi river catchment along one of the landslide prone Chamba to Bharmour road corridor of National Highway(NH^(-1)54 A) in Himachal Pradesh, India. A numeral landslide triggering geoenvironmental factors i.e. slope, aspect, relative relief, soil, curvature, land use and land cover(LULC), lithology, drainage density, and lineament density were selected for landslide hazard mapping based on landslide inventory. Landslide hazard zonation map was categorized namely "very high hazard, high hazard, medium hazard, low hazard, and very low hazard". The results from these two methods were validated using Area Under Curve(AUC) plots. It is found that hazard zonation map prepared using information value method and analytical hierarchy process methods possess the prediction rate of 78.87% and 75.42%, respectively. Hence, landslide hazardzonation map obtained using information value method is proposed to be more useful for the study area. These final hazard zonation maps can be used by various stakeholders like engineers and administrators for proper maintenance and smooth traffic flow between Chamba and Bharmour cities, which is the only route connecting these tourist places.

Approaches for Delineating Landslide Hazard Areas Using Different Training Sites in an Advanced Artificial Neural Network Model

The current paper presents landslide hazard analysis around the Cameron area, Malaysia, using advanced artificial neural networks with the help of Geographic Information System (GIS) and remote sensing techniques. Landslide locations were determined in the study area by interpretation of aerial photographs and from field investigations. Topographical and geological data as well as satellite images were collected, processed, and constructed into a spatial database using GIS and image processing. Ten factors were selected for landslide hazard including: 1) factors related to topography as slope, aspect, and curvature; 2) factors related to geology as lithology and distance from lineament; 3) factors related to drainage as distance from drainage; and 4) factors extracted from TM satellite images as land cover and the vegetation index value. An advanced artificial neural network model has been used to analyze these factors in order to establish the landslide hazard map. The back-propagation training method has been used for the selection of the five different random training sites in order to calculate the factor's weight and then the landslide hazard indices were computed for each of the five hazard maps. Finally, the landslide hazard maps (five cases) were prepared using GIS tools. Results of the landslides hazard maps have been verified using landslide test locations that were not used during the training phase of the neural network. Our findings of verification results show an accuracy of 69%, 75%, 70%, 83% and 86% for training sites 1, 2, 3, 4 and 5 respectively. GIS data was used to efficiently analyze the large volume of data, and the artificial neural network proved to be an effective tool for landslide hazard analysis. The verification results showed sufficient agreement between the presumptive hazard map and the existing data on landslide areas.

Debris flow and landslide hazard mapping and risk analysis in China

This paper assesses the hazardousness, vulnerability and risk of debris flow and landslide in China and compiles maps with a scale of 1：6000000, based on Geographical Information System （GIS） technology, hazard regionalization map, socioeconomic data from 2000. Integrated hazardousness of debris flow and landslide is equivalent to the sum of debris flow hazardousness and landslide hazardousness. Vulnerability is assessed by employing a simplified assessment model. Risk is calculated by the following formula： Risk = Hazardousness × Vulnerability. The analysis results of assessment of hazardousness, vulnerability and risk show that there are extremely high risk regions of 104 km2, high risk regions of 283008 km2, moderate risk regions of 3161815 km2, low risk regions of 3299604km2, and extremely low risk regions of 2681709 km2. Exploitation activities should be prohibited in extremely high risk and high risk regions and restricted in moderate risk regions. The present study on risk analysis of debris flow and landslide not only sheds new light on the future work in this direction but also provides a scientific basis for disaster prevention and mitigation policy making.

Geotechnical and GIS-based environmental factors and vulnerability studies of the Okemesi landslide,Nigeria

Landslide is a geological hazard typically associated with extreme events such as earthquakes,heavy rainfall,volcanic eruptions,changes in groundwater level,etc.This study was carried out in Okemesi-Ekiti(also known as Okemesi),Southwest Nigeria,with the purpose of using remote sensing and GIS technologies to analyze the environmental factors(grain size,direct shear strength resistance,rainfall data,wet density,surface,and slope)resulting in the occurrence of the Okemesi landslide.The study also aimed to conduct a vulnerability analysis in the study area to identify regions with a probability of landslide occurrence.The grain size analysis of the soil in the Okemesi landslide area showed that slope materials comprised 17.14%gravel,59.31%sand,and 19.48%fines,thus the soil type could be classified as poorly graded gravely sand with a high possibility of landslide occurrence.The geomorphic characteristics of the study area was characterized by slopes ranging from 0.00°to 49.00°,while most slopes in the area were less than 8.00°.The slope aspect direction was mainly in south(157.51°–202.50°),southwest(202.51°–247.50°),west(247.51°–292.50°),and north(0.00°–22.50°and 337.51°–360.00°).The highlands were primarily bounded by the slope directions of north(0.00°–22.50°and 337.51°–360.00°),northeast(22.51°–67.50°),east(67.51°–112.51°),and southeast(112.51°–157.50°),which indicated the potential direction of mass movement.The study area can be divided into three vulnerability zones:high,medium,and low,with the area percentages of 9.00%,61.80%,and 29.20%,respectively.The analysis suggested that the Okemesi landslide was likely triggered by rainfall,which might have weakened the physical structure of slope materials.Understanding the causes and impacts of landslides is crucial for policymakers to implement measures to mitigate landslide hazards,protect infrastructure,and prevent the loss of life in the landslide-prone regions.

Landslide susceptibility analysis of Karakoram highway using analytical hierarchy process and scoops 3D

Landslides are prevalent,regular,and expensive hazards in the Karakoram Highway(KKH)region.The KKH connects Pakistan with China in the present China-Pakistan Economic Corridor(CPEC)context.This region has not only immense economic importance but also ecological significance.The purpose of the study was to map the landslide-prone areas along KKH using two different techniquesAnalytical Hierarchy Process(AHP)and Scoops 3 D model.The causative parameters for running AHP include the lithology,presence of thrust,land use land cover,precipitation,and Digital Elevation Model(DEM)derived variables(slope,curvature,aspect,and elevation).The AHP derived final landslide susceptibility map was classified into four zones,i.e.,low,moderate,high,and extremely high.Over 80%of the study area falls under the moderate(43%)and high(40%)landslide susceptible zones.To assess the slope stability of the study area,the Scoops 3 D model was used by integrating with the earthquake loading data.The results of the limit equilibrium analysis categorized the area into four groups(low,moderate,high,and extremely high mass)of slope failure.The areas around Main Mantle Thrust(MMT)including Dubair,Jijal,and Kohistan regions,had high volumes of potential slope failures.The results from AHP and Scoops 3 D techniques were validated with the landslides inventory record of the Geological Survey of Pakistan and Google Earth.The results from both the techniques showed similar output that coincides with the known landslides areas.However,Scoops 3 D provides not only susceptible zones but also the range of volume of the potential slope failures.Further,these techniques could be used in other mountainous areas,which could help in the landslide mitigation measures.

Numerical Modeling of Giant Badu Landslide Reactivated by Excavation in China

In southwest of China, landslide reactivation caused by excavation has caused huge property and human losses, and posed severely threaten to the construction and operation of the man-made linear structures. A reactivated landslide is a complex process. The engineering practices have shown that a correct understanding of the reactivated mechanism of an ancient giant landslide is significant for the landslide mitigation. In this paper, a case study of the ancient Badu landslide that underwent multiple reactivations during the construction of Nanning-Kunming railway was discussed. The landslide characteristics are described and the reactivated features and progressive failure of the landslide are revealed. The reactivated mechanism of the landslide is analyzed by use of geological process analysis method and is simulated using the 3D FEM （finite element method）. At last, the reactivated mechanism mode of Badu giant landslide is put forward, namely ＂creeping-tensile cracking-shear breaking with zoning and grading features＂. The understanding of this kind of reactivated mechanism had helped engineers to take efficient and economic mitigation measures to stabilize the landslide.

The formation of the Wulipo landslide and the resulting debris flow in Dujiangyan City, China

The Wulipo landslide, triggered by heavy rainfall on July 10, 2013, transformed into debris flow,resulted in the destruction of 12 houses, 44 deaths, and 117 missing. Our systematic investigation has led to the following results and to a new understanding about the formation and evolution process of this hazard. The fundamental factors of the formation of the landslide are a high-steep free surface at the front of the slide mass and the sandstone-mudstone mixed stratum structure of the slope. The inducing factor of the landslide is hydrostatic and hydrodynamic pressure change caused by heavy continuous rainfall. The geological mechanical model of the landslide can be summarized as "instability-translational slide-tension fracture-collapse" and the formation mechanism as "translational landslide induced by heavy rainfall". The total volume of the landslide is 124.6×104 m3, and 16.3% of the sliding mass was dropped down from the cliff and transformed into debris flow during the sliding process, which enlarged 46.7% of the original sliding deposit area. The final accumulation area is found to be 9.2×104 m2. The hazard is a typical example of a disaster chain involving landslide and its induced debris flow. The concealment and disaster chain effect is the main reason for the heavy damage. In future risk assessment, it is suggested to enhance the research onpotential landslide identification for weakly intercalated slopes. By considering the influence of the behaviors of landslide-induced debris flow, the disaster area could be determined more reasonably.

Geoinformation techniques in natural hazard modeling:Preface

There are number of geoinformation approaches and modeling tools to the numerical measurement of natural hazards,including direct and indirect heuristic approaches,and deterministic,probabilistic,statistical and data mining approaches（Pradhan and Buchroithner,2012;Pradhan et al.,2012,2014;Pradhan,2013）.In this thematic section of Geoscience Frontiers,a set of six contributions are assembled that provide a window on various parameters,

A Heterogeneous Sampling Strategy to Model Earthquake‑Triggered Landslides

Regional modeling of landslide hazards is an essential tool for the assessment and management of risk in mountain environments.Previous studies that have focused on modeling earthquake-triggered landslides report high prediction accuracies.However,it is common to use a validation strategy with an equal number of landslide and non-landslide samples,scattered homogeneously across the study area.Consequently,there are overestimations in the epicenter area,and the spatial pattern of modeled locations does not agree well with real events.In order to improve landslide hazard mapping,we proposed a spatially heterogeneous non-landslide sampling strategy by considering local ratios of landslide to non-landslide area.Coseismic landslides triggered by the 2008 Wenchuan Earthquake on the eastern Tibetan Plateau were used as an example.To assess the performance of the new strategy,we trained two random forest models that shared the same hyperparameters.The frst was trained using samples from the new heterogeneous strategy,and the second used the traditional approach.In each case the spatial match between modeled and measured(interpreted)landslides was examined by scatterplot,with a 2 km-by-2 km fshnet.Although the traditional approach achieved higher AUC_(ROC)(0.95)accuracy than the proposed one(0.85),the coefcient of determination(R^(2))for the new strategy(0.88)was much higher than for the traditional strategy(0.55).Our results indicate that the proposed strategy outperforms the traditional one when comparing against landslide inventory data.Our work demonstrates that higher prediction accuracies in landslide hazard modeling may be deceptive,and validation of the modeled spatial pattern should be prioritized.The proposed method may also be used to improve the mapping of precipitation-induced landslides.Application of the proposed strategy could beneft precise assessment of landslide risks in mountain environments.

Poisson's ratios and S-wave velocities of the Xishancun landslide,Sichuan,China,inferred from high-frequency receiver functions of local earthquakes

Landslides are recurrent geological phenomena on Earth that cause heavy casualties and property losses annually.In this study,we use the V_(p)-k stacking and nonlinear waveform inversion methods of high-frequency receiver functions extracted from local earthquakes,to sequentially invert Poisson’s ratios and S-wave velocities of the Quaternary Xishancun landslide,which is composed of three segments,i.e.,h1,h2,and h3 from bottom to top.Our results show that Poisson’s ratio values are generally higher than 0.33 and that the S-wave velocities vary from 0.1 to 0.9 km s^(-1).High Poisson’s ratios(>0.44)are mainly distributed in the juncture regions between different segments,as well as the western edge of h2.These zones show significant variation in landslide thickness and are potentially hazardous areas.Low velocities of 0.05–0.2 km s^(-1)with thicknesses of 10–30m are widely observed in the lower layer of the landslide.The high Poisson’s ratios and low-velocity layer may be related to water-rich materials in these areas.Our study suggests that the high-frequency receiver functions from local earthquakes can be used to delineate geotechnical structures,which is valuable for landslide stability analysis and hazard mitigation.