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.

Probabilistic back-analysis of rainfall-induced landslides for slope reliability prediction with multi-source information

Probabilistic back-analysis is an important means to infer the statistics of uncertain soil parameters,making the slope reliability assessment closer to the engineering reality.However,multi-source information(including test data,monitored data,field observation and slope survival records)is rarely used in current probabilistic back-analysis.Conducting the probabilistic back-analysis of spatially varying soil parameters and slope reliability prediction under rainfalls by integrating multi-source information is a challenging task since thousands of random variables and high-dimensional likelihood function are usually involved.In this paper,a framework by integrating a modified Bayesian Updating with Subset simulation(mBUS)method with adaptive Conditional Sampling(aCS)algorithm is established for the probabilistic back-analysis of spatially varying soil parameters and slope reliability prediction.Within this framework,the high-dimensional probabilistic back-analysis problem can be easily tackled,and the multi-source information(e.g.monitored pressure heads and slope survival records)can be fully used in the back-analysis.A real Taoyuan landslide case in Taiwan,China is investigated to illustrate the effectiveness and performance of the established framework.The findings show that the posterior knowledge of soil parameters obtained from the established framework is in good agreement with the field observations.Furthermore,the updated knowledge of soil parameters can be utilized to reliably predict the occurrence probability of a landslide caused by the heavy rainfall event on September 12,2004 or forecast the potential landslides under future rainfalls in the Fuhsing District of Taoyuan City,Taiwan,China.

Dynamic assessment of rainfall-induced shallow landslide hazard

The assessment of rainfall-induced shallow landslide hazards is a significant issue in the Three Gorges Reservoir area in China due to the rapid development of land in the past two decades. In this study, a probabilistic analysis method that combines TRIGRS and the point-estimate method for evaluating the hazards of shallow landslides have been proposed under the condition of rainfall over a large area. TRIGRS provides the transient infiltration model to analyze the pore water pressure during a rainfall. The point-estimate method is used to analyze the uncertainty of the soil parameters, which is performed in the geographic information system(GIS). In this paper, we use this method to evaluate the hazards of shallow landslides in Badong County,Three Gorges Reservoir, under two different types of rainfall intensity, and the results are compared with the field investigation. The results showed that the distribution of the hazard map is consistent with the observed landslides. To some extent, the distributionof the hazard map reflects the spatial and temporal distribution of the shallow landslide caused by rainfall.

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.

Deformation,structure and potential hazard of a landslide based on InSAR in Banbar county,Xizang(Tibet)

The Tibetan Plateau is characterized by complex geological conditions and a relatively fragile ecological environment.In recent years,there has been continuous development and increased human activity in the Tibetan Plateau region,leading to a rising risk of landslides.The landslide in Banbar County,Xizang(Tibet),have been perturbed by ongoing disturbances from human engineering activities,making it susceptible to instability and displaying distinct features.In this study,small baseline subset synthetic aperture radar interferometry(SBAS-InSAR)technology is used to obtain the Line of Sight(LOS)deformation velocity field in the study area,and then the slope-orientation deformation field of the landslide is obtained according to the spatial geometric relationship between the satellite’s LOS direction and the landslide.Subsequently,the landslide thickness is inverted by applying the mass conservation criterion.The results show that the movement area of the landslide is about 6.57×10^(4)m^(2),and the landslide volume is about 1.45×10^(6)m^(3).The maximum estimated thickness and average thickness of the landslide are 39 m and 22 m,respectively.The thickness estimation results align with the findings from on-site investigation,indicating the applicability of this method to large-scale earth slides.The deformation rate of the landslide exhibits a notable correlation with temperature variations,with rainfall playing a supportive role in the deformation process and displaying a certain lag.Human activities exert the most substantial influence on the spatial heterogeneity of landslide deformation,leading to the direct impact of several prominent deformation areas due to human interventions.Simultaneously,utilizing the long short-term memory(LSTM)model to predict landslide displacement,and the forecast results demonstrate the effectiveness of the LSTM model in predicting landslides that are in a continuous development and movement phase.The landslide is still active,and based on the spatial heterogeneity of landslide deformation,new recommendations have been proposed for the future management of the landslide in order to mitigate potential hazards associated with landslide instability.

Identification and hazard analysis of landslides triggered by earthquakes and rainfall

This study aims to utilize the Small Baseline Subset Interferometric Synthetic Aperture Radar(SBAS-In SAR)technique and Google Earth optical remote sensing images to analyze the area within 20 km around the epicenter of a M 3.9, earthquake that occurred in Tanchang County, Gansu Province, on December 28, 2020. The objective is to identify potential earthquake-induced landslides, assess their scale, and determine their impact range. The study results reveal the successful identification of two potential landslides in the 20 km radius around the epicenter. Through time-series deformation analysis, it was observed that these potential landslides were significantly influenced by both the earthquake and rainfall. Further estimation of these potential landslides indicates maximum depths of 7.4 m and 14.1 m for the failure surfaces, with volumes of 9.02 × 10~4m~3and 25.5 ×10~4m~3, respectively. Finally, based on the simulation analysis of Massflow software, the maximum thickness of soil accumulation in the final accumulation area after sliding of the potential landslide in Shangyaai is 12 m, the area of the final accumulation area is 1.75 × 10~4m~2, and the farthest movement distance is 1124 m. The maximum thickness of soil accumulation in the final accumulation area after sliding of the potential landslide in Wangshancun is 8 m, the area of the final accumulation area is 7.89 × 10~4m~2, and the farthest movement distance is 742 m.

Strength softening models of soil and its application in rainfall-induced landslide simulation

In this study, strength softening models are developed for exploring rainfall-induced landslide mechanism based on Mohr Coulomb strength theory with both saturation degree and temporal evolution into consideration. According to the ratio of two time scales available, the model can be classified into three categories, i.e., instant softening model, delay softening model, and coupling softening model. Corresponding evolution functions are specified to represent these kinds of softening processes and then applied to simulate landslide of homogeneous slopes triggered by rainfall, therefrom, useful conclusions can be drawn in the end.

Examination of Rainfall-Induced Landslide Failure Mechanisms via a Centrifuge Physical Simulation Test

Rainfall is one of the most important factors contributing to landslides, and gentle bedding incline, high-rainfall induced landslides are common throughout the world. Field observations and theoretical analyses have been used to assess slope instability caused by permeability variation. In this study, the influence of rainfall infiltration on gentle bedding incline slope behaviour was investigated using a centrifuge physical simulation test. The magnitude, pattern and development of pore water and earth pressure at the interface;the shear failure surface features;and the corresponding deformation and failure processes were considered. A model with interbedded sand and mud was created, and a centrifuge was used to simulate both natural and rainfall conditions. The weak intercalation was composed of single-material silty clay, and the landslide mass was composed of red-bed sandstone. A combination of photography, pore water pressure measurements and earth pressure measurements were used to examine the relationship between the pore water pressure, earth pressure and failure modes. When the slope experiences overall instability, the curves of the earth pressure and pore water pressure dramatically decrease. The results reveal that the failure shear surface largely depends on the differential creep caused by the properties of the rock mass and the rainfall infiltration.

Failure analysis on a heavy rainfall-induced landslide in Huay Khab Mountain in Northern Thailand

On 28 th July 2018,a massive landslide occurred in a mountainous area in Northern Thailand.The landslide after ten days of heavy rainfall generated the movement of uphill mountain soil into the populated village.This study presents a comprehensive failure analysis of local rainfallinduced landslides based on topographical and geological information.Rainfall measurement data were gathered from two rainfall stations close to the study area.The rainfall records show that the total monthly rainfalls in 2018 were significantly higher than the average monthly rainfalls over the past decade.Site investigation started with an unmanned aerial photogrammetric survey to generate a digital elevation model.Then,dynamic probing test,microtremor survey,and electrical resistivity survey were carried out along undisturbed soils beside the failed slope to evaluate the thickness of the soft soil cover on top of the rock basement.During the site survey,residual soil samples were collected to determine engineering properties in the laboratory.Finally,a slope stability analysis was performed to assess the landslide hazard based on the results of aerial photogrammetric survey,field exploration,and laboratory tests.The slope stability analysis and rainfall records revealed that the Huay Khab landslide was mainly caused by an increase in the water content of residual soils due to the prolonged rainfall which led to a sharp decrease in the shear strength.This leads to the conclusion that the proposed landslide investigation program could be used to assess the potential of landslide failure due to prolonged rainfall on a local scale.

Exploring deep learning for landslide mapping:A comprehensive review

A detailed and accurate inventory map of landslides is crucial for quantitative hazard assessment and land planning.Traditional methods relying on change detection and object-oriented approaches have been criticized for their dependence on expert knowledge and subjective factors.Recent advancements in highresolution satellite imagery,coupled with the rapid development of artificial intelligence,particularly datadriven deep learning algorithms(DL)such as convolutional neural networks(CNN),have provided rich feature indicators for landslide mapping,overcoming previous limitations.In this review paper,77representative DL-based landslide detection methods applied in various environments over the past seven years were examined.This study analyzed the structures of different DL networks,discussed five main application scenarios,and assessed both the advancements and limitations of DL in geological hazard analysis.The results indicated that the increasing number of articles per year reflects growing interest in landslide mapping by artificial intelligence,with U-Net-based structures gaining prominence due to their flexibility in feature extraction and generalization.Finally,we explored the hindrances of DL in landslide hazard research based on the above research content.Challenges such as black-box operations and sample dependence persist,warranting further theoretical research and future application of DL in landslide detection.

A Hazard Assessment Method for Potential Earthquake-Induced Landslides – A Case Study in Huaxian County, Shaanxi Province

The hazard assessment of potential earthquake-induced landslides is an important aspect of the study of earthquake-induced landslides. In this study, we assessed the hazard of potential earthquake-induced landslides in Huaxian County with a new hazard assessment method. This method is based on probabilistic seismic hazard analysis and the Newmark cumulative displacement assessment model. The model considers a comprehensive suite of information, including the seismic activities and engineering geological conditions in the study area, and simulates the uncertainty of the intensity parameters of the engineering geological rock groups using the Monte Carlo method. Unlike previous assessment studies on ground motions with a given exceedance probability level, the hazard of earthquake-induced landslides obtained by the method presented in this study allows for the possibility of earthquake-induced landslides in different parts of the study area in the future. The assessment of the hazard of earthquake-induced landslides in this study showed good agreement with the historical distribution of earthquake-induced landslides. This indicates that the assessment properly reflects the macroscopic rules for the development of earthquake-induced landslides in the study area, and can provide a reference framework for the management of the risk of earthquakeinduced landslides and land planning.

CIS-Based Mapping and Zonation of Landslide Hazards in Xiaojiang Valley of Southwestern China

Through the field survey, previous researches and interpretation of aerial photos, a landslide information database of Xiaojiang Valley, Yunnan Province was set up based on the remote sensing (RS) and geographic information system (GIS) technologies. In the paper, a quantitative model for the landslide hazard assessment and zoning was presented, in which the potential energy could be obtained on basis of thorough analysis of the potential sliding volume, distance and direction of the landslide body. Taking landslide potential energy as the index of the hazard severity zonation, the study area was divided into severe, heavy, medium and light hazard zones.

Estimation of Seismic Landslide Hazard in the Eastern Himalayan Syntaxis Region of Tibetan Plateau

The eastern Himalayan syntaxis is one of the most tectonically active and earthquake-prone regions on Earth where earthquake-induced geological disasters occur frequently and caused great damages. With the planning and construction of Sichuan-Tibet highway, Sichuan-Tibet railway and hydropower development on the Yarlung Zangbo River etc. in recent years, it is very important to evaluate the seismic landslide hazard of this region. In this paper, a seismic landslide hazard map is produced based on seismic geological background analysis and field investigation using Newmark method with 10% PGA exceedance probabilities in future 50 years by considering the influence of river erosion, active faults and seismic amplification for the first time. The results show that the areas prone to seismic landslides are distributed on steep slopes along the drainages and the glacier horns as well as ridges on the mountains. The seismic landslide hazard map produced in this study not only predicts the most prone seismic landslide areas in the future 50 years but also provides a reference for mitigation strategies to reduce the exposure of the new building and planning projects to seismic landslides.

Probabilistic seismic landslide hazard assessment: a case study in Tianshui, Northwest China

Probabilistic analysis in the field of seismic landslide hazard assessment is often based on an estimate of uncertainties of geological, geotechnical,geomorphological and seismological parameters.However, real situations are very complex and thus uncertainties of some parameters such as water content conditions and critical displacement are difficult to describe with accurate mathematical models. In this study, we present a probabilistic methodology based on the probabilistic seismic hazard analysis method and the Newmark’s displacement model. The Tianshui seismic zone(105°00′-106°00′ E, 34°20′-34°40′ N) in the northeastern Tibetan Plateau were used as an example. Arias intensity with three standard probabilities of exceedance(63%, 10%, and 2% in 50 years) in accordance with building design provisions were used to compute Newmark displacements by incorporating the effects of topographic amplification.Probable scenarios of water content condition were considered and three water content conditions(dry,wet and saturated) were adopted to simulate the effect of pore-water on slope. The influence of 5 cm and 10 cm critical displacements were investigated in order to analyze the sensitivity of critical displacement to the probabilities of earthquake-induced landslide occurrence. The results show that water content in particular, have a great influence on the distribution of high seismic landslide hazard areas. Generally, the dry coverage analysis represents a lower bound for susceptibility and hazard assessment, and the saturated coverage analysis represents an upper bound to some extent. Moreover, high seismic landslide hazard areas are also influenced by the critical displacements. The slope failure probabilities during future earthquakes with critical displacements of 5 cm can increase by a factor of 1.2 to 2.3 as compared to that of 10 cm. It suggests that more efforts are required in order to obtain reasonable threshold values for slope failure. Considering the probable scenarios of water content condition which is varied with seasons, seismic landslide hazard assessments are carried out for frequent, occasional and rare earthquake occurrences in the Tianshui region, which can provide a valuable reference for landslide hazard management and infrastructure design in mountainous seismic zones.

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.

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.

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.

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.

GIS-based Earthquake-Triggered Landslide Hazard Zoning Using Contributing Weight Model

Earthquake-triggered landslides have aroused widespread attention because of their tremendous ability to harm people's lives and properties.The best way to avoid and mitigate their damage is to develop landslide hazard maps and make them available to the public in advance of an earthquake.Future construction can then be built according to the level of hazard and existing structures can be retrofit as necessary.During recent years various approaches have been made to develop landslide hazard maps using statistical analysis or physical models.However,these methods have limitations.This study introduces a new GIS-based approach,using the contributing weight model,to evaluate the hazard of seismically-induced landslides.In this study,the city and surrounding area of Dujiangyan was selected as the research area because of its moderate-high seismic activity.The parameters incorporated into the model that related to the probability of landslide occurrence were:slope gradient,slope aspect,geomorphology,lithology,base level,surface roughness,earthquake intensity,fault proximity,drainage proximity,and road proximity.The parameters were converted into raster data format with a resolution of 25×25m2 pixels.Analysis of the GIS correlations shows that the highest earthquake-induced landslide hazard areas are mainly in the hills and in some of the moderately steep mountainous areas of central Dujiangyan.The highest hazard zone covers an area of 11.1% of the study area,and the density distribution of seismically-induced landslides was 3.025/km2 from the 2008 Wenchuan earthquake.The moderately hazardous areas are mainly distributed within the moderately steep mountainous regions of the northern and southeastern parts of the study area and the hills of the northeastern part;covering 32.0% of the study area and with a density distribution of 2.123/km2 resulting from the Wenchuan earthquake.The lowest hazard areas are mainly distributed in the topographically flat plain in the northeastern part and some of the relatively gently slopes in the moderately steep mountainous areas of the northern part of Dujiangyan and the surrounding area.The lowest hazard areas cover 56.9% of the study area and exhibited landslide densities of 0.941/km2 and less from the Wenchuan earthquake.The quality of the hazard map was validated using a comparison with the distribution of landslides that were cataloged as occurring from the Wenchuan earthquake.43.1% of the study area consists of high and moderate hazardous zones,and these regions include 83.5% of landslides caused by the Wenchuan earthquake.The successful analysis shows that the contributing weight model can be effective for earthquake-triggered landslide hazard appraisal.The model's results can provide the basis for risk management and regional planning is.

GIS-based prediction method of shallow landslides induced by heavy rainfall in large mountainous areas

Rainwater runoff that does not infiltrate the soil during heavy rainfall may increase slope instability. The effect of runoff is usually neglected in conventional rainfall-induced slope failure analysis to simplify the model. To analyze the effect of runoff on slope stability, this study simultaneously simulated the effects of surface runoff and rainfall infiltration on bank slopes in the Three Gorges Reservoir Area. A shallow slope failure method that can be used to analyze runoff was proposed based on the modified Green-Ampt model, the simplified Saint-Venant model, and the infinite slope model. In this model, the modified Green–Ampt model was used to estimate the rainfall infiltration capacity and the wetting front depth. The eight-flow(D8) method and the simplified Saint-Venant model were selected to estimate the distribution of runoff. By considering the wetting front depth as the slip surface depth, the factor of safety of the slope could be determined using the infinite slope stability model. A comparison of the different models reveals that runoff can escalate the instability of certain slopes, causing stable slopes to become unstable. Comparison of the unstable areas obtained from the simulation with the actual landslide sites shows that the model proposed in this study can successfully predict landslides at these sites. The slope instability assessment model proposed in this study offers an alternative approach for estimating high-risk areas in large mountainous regions.