Uncertainties of landslide susceptibility prediction considering different landslide types

Most literature related to landslide susceptibility prediction only considers a single type of landslide,such as colluvial landslide,rock fall or debris flow,rather than different landslide types,which greatly affects susceptibility prediction performance.To construct efficient susceptibility prediction considering different landslide types,Huichang County in China is taken as example.Firstly,105 rock falls,350 colluvial landslides and 11 related environmental factors are identified.Then four machine learning models,namely logistic regression,multi-layer perception,support vector machine and C5.0 decision tree are applied for susceptibility modeling of rock fall and colluvial landslide.Thirdly,three different landslide susceptibility prediction(LSP)models considering landslide types based on C5.0 decision tree with excellent performance are constructed to generate final landslide susceptibility:(i)united method,which combines all landslide types directly;(ii)probability statistical method,which couples analyses of susceptibility indices under different landslide types based on probability formula;and(iii)maximum comparison method,which selects the maximum susceptibility index through comparing the predicted susceptibility indices under different types of landslides.Finally,uncertainties of landslide susceptibility are assessed by prediction accuracy,mean value and standard deviation.It is concluded that LSP results of the three coupled models considering landslide types basically conform to the spatial occurrence patterns of landslides in Huichang County.The united method has the best susceptibility prediction performance,followed by the probability method and maximum susceptibility method.More cases are needed to verify this result in-depth.LSP considering different landslide types is superior to that taking only a single type of landslide into account.

Insights into some large-scale landslides in southeastern margin of Qinghai-Tibet Plateau

The southeastern margin of Qinghai-Tibet Plateau(SMQTP)is of a typical large landslide-prone area due to intense tectonic activity,deeply incised valleys,high geostress and frequent earthquakes.To gain insights into large landslides in southeastern margin of Qinghai-Tibet Plateau,an area covering 3.34×105 km2 that extends 80e150 km on both sides of the Sichuan-Tibet traffic corridors(G318)was used to examine the spatial distribution and corresponding characteristics of landslides.The results showed that the study area contains at least 629 large landslides that are mainly concentrated on 7 zones(zones IeVII).Zones IeVII are in the southern section of the Longmenshan fault zone(with no large river)and sections with Dadu River,Jinsha River,Lancang River,Nujiang River and Yarlung Zangbo River.There are more landslides in the Jinsha River section(totaling 186 landslides)than the other sections.According to the updated Varnes classification,408 large landslides(64.9%)were recognized and divided into 4 major types,i.e.flows(275 cases),slides(58 cases),topples(44 cases)and slope deformations(31 cases).Flows,which consist of rock avalanches and iceerock avalanches,are the most common landslide type.Large landslide triggers(178 events,28.3%)are also recognized,and earthquakes may be the most common trigger.Due to the limited data,these landslide type classifications and landslide triggers are perhaps immature,and further systematic analysis is needed.

Dynamic process simulation with a Savage-Hutter type model for the intrusion of landslide into river

Natural damming of rivers by mass movements is a very common and potentially dangerous phenomena which has been documented all over the world. In this paper, a two-layer model of Savage-Hutter type is presented to simulate the dynamic procedure for the intrusion of landslide into rivers. The two-layer shallow water system is derived by depth averaging the incompressible Navier-Stokes equations with the hydrostatic assumption. A high order accuracy scheme based on the finite volume method is proposed to solve the presented model equations. Several numerical tests are performed to verify the realiability and feasibility of the proposed model. The numerical results indicate that the proposed method can be competent for simulating the dynamic process of landslide intrusion into the river. The interaction effect between both layers has a significant impact on the landslide movement, water fluctuation and wave propagation.

Enhancing landslide susceptibility mapping incorporating landslide typology via stacking ensemble machine learning in Three Gorges Reservoir,China

Different types of landslides exhibit distinct relationships with environmental conditioning factors.Therefore,in regions where multiple types of landslides coexist,it is required to separate landslide types for landslide susceptibility mapping(LSM).In this paper,a landslideprone area located in Chongqing Province within the middle and upper reaches of the Three Gorges Reservoir area(TGRA),China,was selected as the study area.733 landslides were classified into three types:reservoir-affected landslides,non-reservoir-affected landslides,and rockfalls.Four landslide inventory datasets and 15 landslide conditional factors were trained by three Machine Learning models(logistic regression,random forest,support vector machine),and a Deep Learning(DL)model.After comparing the models using receiver operating characteristics(ROC),the landslide susceptibility indexes of three types landslides were acquired by the best performing model.These indexes were then used as input to generate the final map based on the Stacking method.The results revealed that DL model showed the best performance in LSM without considering landslide types,achieving an area under the curve(AUC)of 0.854 for testing and 0.922 for training.Moreover,when we separated the landslide types for LSM,the AUC improved by 0.026 for testing and 0.044 for training.Thus,this paper demonstrates that considering different landslide types in LSM can significantly improve the quality of landslide susceptibility maps.These maps in turn,can be valuable tools for evaluating and mitigating landslide hazards.

Mapping landslide susceptibility and types using Random Forest

Landslides are one of the most destructive natural hazards;they can drastically alter landscape morphology,destroy man-made struc-tures,and endanger people’s life.Landslide susceptibility maps(LSMs),which show the spatial likelihood of landslide occurrence,are crucial for environmental management,urban planning,and minimizing economic losses.To date,the majority of research into data mining LSM uses small-scale case studies focusing on a single type of landslide.This paper presents a data mining approach to producing LSM for a large,heterogeneous region that is susceptible tomultipletypesoflandslides.UsingacasestudyofPiedmont,Italy,a Random Forest algorithm is applied to produce both susceptibility maps and classification maps.These maps are combined to give a highly accurate(over 85%classification accuracy)LSM which con-tains a large amount of information and is easy to interpret.This novel method of mapping landslide susceptibility demonstrates the efficacy of Random Forest to produce highly accurate susceptibility maps for alargeheterogeneousregion withouttheneed formultiple susceptibility assessments.