Modelling of debris-flow susceptibility and propagation: a case study from Northwest Himalaya

The geological and geographical position of the Northwest Himalayas makes it a vulnerable area for mass movements particularly landslides and debris flows. Mass movements have had a substantial impact on the study area which is extending along Karakorum Highway(KKH) from Besham to Chilas. Intense seismicity, deep gorges, steep terrain and extreme climatic events trigger multiple mountain hazards along the KKH, among which debris flow is recognized as the most destructive geohazard. This study aims to prepare a field-based debris flow inventory map at a regional scale along a 200 km stretch from Besham to Chilas. A total of 117 debris flows were identified in the field, and subsequently, a point-based debris-flow inventory and catchment delineation were performed through Arc GIS analysis. Regional scale debris flow susceptibility and propagation maps were prepared using Weighted Overlay Method(WOM) and Flow-R technique sequentially. Predisposing factors include slope, slope aspect, elevation, Topographic Roughness Index(TRI), Topographic Wetness Index(TWI), stream buffer, distance to faults, lithology rainfall, curvature, and collapsed material layer. The dataset was randomly divided into training data(75%) and validation data(25%). Results were validated through the Receiver Operator Characteristics(ROC) curve. Results show that Area Under the Curve(AUC) using WOM model is 79.2%. Flow-R propagation of debris flow shows that the 13.15%, 22.94%, and 63.91% areas are very high, high, and low susceptible to debris flow respectively. The propagation predicated by Flow-R validates the naturally occurring debris flow propagation as observed in the field surveys. The output of this research will provide valuable input to the decision makers for the site selection, designing of the prevention system, and for the protection of current infrastructure.

How do the landslide and non-landslide sampling strategies impact landslide susceptibility assessment? d A catchment-scale case study from China

The aim of this study is to investigate the impacts of the sampling strategy of landslide and non-landslide on the performance of landslide susceptibility assessment(LSA).The study area is the Feiyun catchment in Wenzhou City,Southeast China.Two types of landslides samples,combined with seven non-landslide sampling strategies,resulted in a total of 14 scenarios.The corresponding landslide susceptibility map(LSM)for each scenario was generated using the random forest model.The receiver operating characteristic(ROC)curve and statistical indicators were calculated and used to assess the impact of the dataset sampling strategy.The results showed that higher accuracies were achieved when using the landslide core as positive samples,combined with non-landslide sampling from the very low zone or buffer zone.The results reveal the influence of landslide and non-landslide sampling strategies on the accuracy of LSA,which provides a reference for subsequent researchers aiming to obtain a more reasonable LSM.

Knock-out of BnHva22c reduces the susceptibility of Brassica napus to infection with the fungal pathogen Verticillium longisporum

Verticillium longisporum(Vl43)is a soilborne hemibiotrophic fungal pathogen causing stem striping on oilseed rape(OSR)and severe yield losses.Breeding for resistant varieties is the most promising approach to control this disease.Here,we report the identification of Hva22c as a novel susceptibility factor and its potential for improving OSR resistance.Hva22c is a member of the Hva22 gene family,originally described for barley(Hordeum vulgare).Several Hva22 members have been located at the endoplasmic reticulum.Hva22c is up-regulated in response to Vl43 in both Arabidopsis and OSR.We demonstrate that knock-out of Hva22c in OSR by CRISPR/Cas9 and its homolog in Arabidopsis by T-DNA insertion reduced plants’susceptibility to Vl43 infection and impaired the development of disease symptoms.To understand the underlying mechanism,we analysed transcriptomic data from infected and non-infected roots of hva22c knock-out and wild type plants.We identified a homozygous mutant with frame-shifts in all four BnHva22c loci displaying a vastly altered transcriptional landscape at 6 dpi.Significantly,a large set of genes was suppressed under mock conditions including genes related to the endomembrane systems.Among the up-regulated genes we found several defense-related and phytohormone-responsive genes when comparing mutant to the wild type.These results demonstrate that Hva22c is functionally required for a fully compatible plant-fungus interaction.Its loss of function reduces plant susceptibility,most likely due to endoplasmatic reticulum and Golgi dysfunction accompanied by additionally activated defense responses.These findings can help improve OSR resistance to V.longisporum infection.

Comparison of debris flow susceptibility assessment methods:support vector machine,particle swarm optimization,and feature selection techniques

The selection of important factors in machine learning-based susceptibility assessments is crucial to obtain reliable susceptibility results.In this study,metaheuristic optimization and feature selection techniques were applied to identify the most important input parameters for mapping debris flow susceptibility in the southern mountain area of Chengde City in Hebei Province,China,by using machine learning algorithms.In total,133 historical debris flow records and 16 related factors were selected.The support vector machine(SVM)was first used as the base classifier,and then a hybrid model was introduced by a two-step process.First,the particle swarm optimization(PSO)algorithm was employed to select the SVM model hyperparameters.Second,two feature selection algorithms,namely principal component analysis(PCA)and PSO,were integrated into the PSO-based SVM model,which generated the PCA-PSO-SVM and FS-PSO-SVM models,respectively.Three statistical metrics(accuracy,recall,and specificity)and the area under the receiver operating characteristic curve(AUC)were employed to evaluate and validate the performance of the models.The results indicated that the feature selection-based models exhibited the best performance,followed by the PSO-based SVM and SVM models.Moreover,the performance of the FS-PSO-SVM model was better than that of the PCA-PSO-SVM model,showing the highest AUC,accuracy,recall,and specificity values in both the training and testing processes.It was found that the selection of optimal features is crucial to improving the reliability of debris flow susceptibility assessment results.Moreover,the PSO algorithm was found to be not only an effective tool for hyperparameter optimization,but also a useful feature selection algorithm to improve prediction accuracies of debris flow susceptibility by using machine learning algorithms.The high and very high debris flow susceptibility zone appropriately covers 38.01%of the study area,where debris flow may occur under intensive human activities and heavy rainfall events.

Liquefaction susceptibility and deformation characteristics of saturated coral sandy soils subjected to cyclic loadings-a critical review

Coral sandy soils widely exist in coral island reefs and seashores in tropical and subtropical regions.Due to the unique marine depositional environment of coral sandy soils,the engineering characteristics and responses of these soils subjected to monotonic and cyclic loadings have been a subject of intense interest among the geotechnical and earthquake engineering communities.This paper critically reviews the progress of experimental investigations on the undrained behavior of coral sandy soils under monotonic and cyclic loadings over the last three decades.The focus of coverage includes the contractive-dilative behavior,the pattern of excess pore-water pressure(EPWP)generation and the liquefaction mechanism and liquefaction resistance,the small-strain shear modulus and strain-dependent shear modulus and damping,the cyclic softening feature,and the anisotropic characteristics of undrained responses of saturated coral sandy soils.In particular,the advances made in the past decades are reviewed from the following aspects:(1)the characterization of factors that impact the mechanism and patterns of EPWP build-up;(2)the identification of liquefaction triggering in terms of the apparent viscosity and the average flow coefficient;(3)the establishment of the invariable form of strain-based,stress-based,or energy-based EPWP ratio formulas and the unique relationship between the new proxy of liquefaction resistance and the number of cycles required to reach liquefaction;(4)the establishment of the invariable form of the predictive formulas of small strain modulus and strain-dependent shear modulus;and(5)the investigation on the effects of stress-induced anisotropy on liquefaction susceptibility and dynamic deformation characteristics.Insights gained through the critical review of these advances in the past decades offer a perspective for future research to further resolve the fundamental issues concerning the liquefaction mechanism and responses of coral sandy sites subjected to cyclic loadings associated with seismic events in marine environments.

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.

Glacial debris flow susceptibility mapping based on combined models in the Parlung Tsangpo Basin,China

Machine learning(ML)-based prediction models for mapping hazard(e.g.,landslide and debris flow)susceptibility have been widely developed in recent research.However,in some specific areas,ML models have limited application because of the uncertainties in identifying negative samples.The Parlung Tsangpo Basin exemplifies a region prone to recurrent glacial debris flows(GDFs)and is characterized by a prominent landform featuring deep gullies.Considering the limitations of the ML model,we developed and compared two combined statistical models(FA-WE and FA-IC)based on factor analysis(FA),weight of evidence(WE),and the information content(IC)method.The final GDF susceptibility maps were generated by selecting 8 most important static factors and considering the influence of precipitation.The results show that the FA-IC model has the best performance.The areas with a very high susceptibility to GDFs are primarily located in the narrow valley section upstream,on both sides of the valley in the middle and downstream of the Parlung Tsangpo River,and in the narrow valley section of each tributary.These areas encompass 86 gullies and are characterized as"narrow and steep".

Comparative study of different machine learning models in landslide susceptibility assessment: A case study of Conghua District, Guangzhou, China

Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Conghua District,which is the most prone to landslide disasters in Guangzhou,was selected for landslide susceptibility evaluation.The evaluation factors were selected by using correlation analysis and variance expansion factor method.Applying four machine learning methods namely Logistic Regression(LR),Random Forest(RF),Support Vector Machines(SVM),and Extreme Gradient Boosting(XGB),landslide models were constructed.Comparative analysis and evaluation of the model were conducted through statistical indices and receiver operating characteristic(ROC)curves.The results showed that LR,RF,SVM,and XGB models have good predictive performance for landslide susceptibility,with the area under curve(AUC)values of 0.752,0.965,0.996,and 0.998,respectively.XGB model had the highest predictive ability,followed by RF model,SVM model,and LR model.The frequency ratio(FR)accuracy of LR,RF,SVM,and XGB models was 0.775,0.842,0.759,and 0.822,respectively.RF and XGB models were superior to LR and SVM models,indicating that the integrated algorithm has better predictive ability than a single classification algorithm in regional landslide classification problems.

Fast measurement and prediction method for electromagnetic susceptibility of receiver

Aiming at evaluating and predicting rapidly and accurately a high sensitivity receiver’s adaptability in complex electromagnetic environments,a novel testing and prediction method based on dual-channel multi-frequency is proposed to improve the traditional two-tone test.Firstly,two signal generators are used to generate signals at the radio frequency(RF)by frequency scanning,and then a rapid measurement at the intermediate frequency(IF)output port is carried out to obtain a huge amount of sample data for the subsequent analysis.Secondly,the IF output response data are modeled and analyzed to construct the linear and nonlinear response constraint equations in the frequency domain and prediction models in the power domain,which provide the theoretical criteria for interpreting and predicting electromagnetic susceptibility(EMS)of the receiver.An experiment performed on a radar receiver confirms the reliability of the method proposed in this paper.It shows that the interference of each harmonic frequency and each order to the receiver can be identified and predicted with the sensitivity model.Based on this,fast and comprehensive evaluation and prediction of the receiver’s EMS in complex environment can be efficiently realized.

Uncertainties of landslide susceptibility prediction: Influences of random errors in landslide conditioning factors and errors reduction by low pass filter method

In the existing landslide susceptibility prediction(LSP)models,the influences of random errors in landslide conditioning factors on LSP are not considered,instead the original conditioning factors are directly taken as the model inputs,which brings uncertainties to LSP results.This study aims to reveal the influence rules of the different proportional random errors in conditioning factors on the LSP un-certainties,and further explore a method which can effectively reduce the random errors in conditioning factors.The original conditioning factors are firstly used to construct original factors-based LSP models,and then different random errors of 5%,10%,15% and 20%are added to these original factors for con-structing relevant errors-based LSP models.Secondly,low-pass filter-based LSP models are constructed by eliminating the random errors using low-pass filter method.Thirdly,the Ruijin County of China with 370 landslides and 16 conditioning factors are used as study case.Three typical machine learning models,i.e.multilayer perceptron(MLP),support vector machine(SVM)and random forest(RF),are selected as LSP models.Finally,the LSP uncertainties are discussed and results show that:(1)The low-pass filter can effectively reduce the random errors in conditioning factors to decrease the LSP uncertainties.(2)With the proportions of random errors increasing from 5%to 20%,the LSP uncertainty increases continuously.(3)The original factors-based models are feasible for LSP in the absence of more accurate conditioning factors.(4)The influence degrees of two uncertainty issues,machine learning models and different proportions of random errors,on the LSP modeling are large and basically the same.(5)The Shapley values effectively explain the internal mechanism of machine learning model predicting landslide sus-ceptibility.In conclusion,greater proportion of random errors in conditioning factors results in higher LSP uncertainty,and low-pass filter can effectively reduce these random errors.

Identifying genetic susceptibility to Aspergillus fumigatus infection using collaborative cross mice and RNA-Seq approach

Background:Aspergillus fumigatus(Af)is one of the most ubiquitous fungi and its infection potency is suggested to be strongly controlled by the host genetic back-ground.The aim of this study was to search for candidate genes associated with host susceptibility to Aspergillus fumigatus(Af)using an RNAseq approach in CC lines and hepatic gene expression.Methods:We studied 31 male mice from 25 CC lines at 8 weeks old;the mice were infected with Af.Liver tissues were extracted from these mice 5 days post-infection,and next-generation RNA-sequencing(RNAseq)was performed.The GENE-E analysis platform was used to generate a clustered heat map matrix.Results:Significant variation in body weight changes between CC lines was ob-served.Hepatic gene expression revealed 12 top prioritized candidate genes differ-entially expressed in resistant versus susceptible mice based on body weight changes.Interestingly,three candidate genes are located within genomic intervals of the previ-ously mapped quantitative trait loci(QTL),including Gm16270 and Stox1 on chromo-some 10 and Gm11033 on chromosome 8.Conclusions:Our findings emphasize the CC mouse model's power in fine mapping the genetic components underlying susceptibility towards Af.As a next step,eQTL analysis will be performed for our RNA-Seq data.Suggested candidate genes from our study will be further assessed with a human cohort with aspergillosis.

Landslide susceptibility prediction using slope unit-based machine learning models considering the heterogeneity of conditioning factors

To perform landslide susceptibility prediction(LSP),it is important to select appropriate mapping unit and landslide-related conditioning factors.The efficient and automatic multi-scale segmentation(MSS)method proposed by the authors promotes the application of slope units.However,LSP modeling based on these slope units has not been performed.Moreover,the heterogeneity of conditioning factors in slope units is neglected,leading to incomplete input variables of LSP modeling.In this study,the slope units extracted by the MSS method are used to construct LSP modeling,and the heterogeneity of conditioning factors is represented by the internal variations of conditioning factors within slope unit using the descriptive statistics features of mean,standard deviation and range.Thus,slope units-based machine learning models considering internal variations of conditioning factors(variant slope-machine learning)are proposed.The Chongyi County is selected as the case study and is divided into 53,055 slope units.Fifteen original slope unit-based conditioning factors are expanded to 38 slope unit-based conditioning factors through considering their internal variations.Random forest(RF)and multi-layer perceptron(MLP)machine learning models are used to construct variant Slope-RF and Slope-MLP models.Meanwhile,the Slope-RF and Slope-MLP models without considering the internal variations of conditioning factors,and conventional grid units-based machine learning(Grid-RF and MLP)models are built for comparisons through the LSP performance assessments.Results show that the variant Slopemachine learning models have higher LSP performances than Slope-machine learning models;LSP results of variant Slope-machine learning models have stronger directivity and practical application than Grid-machine learning models.It is concluded that slope units extracted by MSS method can be appropriate for LSP modeling,and the heterogeneity of conditioning factors within slope units can more comprehensively reflect the relationships between conditioning factors and landslides.The research results have important reference significance for land use and landslide prevention.

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.

Comparison of LR,5-CV SVM,GA SVM,and PSO SVM for landslide susceptibility assessment in Tibetan Plateau area,China

The applicability of statistics-based landslide susceptibility assessment methods is affected by the number of historical landslides.Previous studies have proposed support vector machine(SVM)as a small-sample learning method.However,those studies demonstrated that different parameters can affect model performance.We optimized the SVM and obtained models as 5-fold cross validation(5-CV)SVM,genetic algorithm(GA)SVM,and particle swarm optimization(PSO)SVM.This study compared the prediction performances of logistic regression(LR),5-CV SVM,GA SVM,and PSO SVM on landslide susceptibility mapping,to explore the spatial distribution of landslide susceptibility in the study area in Tibetan Plateau,China.A geospatial database was established based on 392 historical landslides and 392 non-landslides in the study area.We used 11 influencing factors of altitude,slope,aspect,curvature,lithology,normalized difference vegetation index(NDVI),distance to road,distance to river,distance to fault,peak ground acceleration(PGA),and rainfall to construct an influencing factor evaluation system.To evaluate the models,four susceptibility maps were compared via receiver operating characteristics(ROC)curve and the results showed that prediction rates for the models are 84%(LR),87%(5-CV SVM),85%(GA SVM),and 90%(PSO SVM).We also used precision,recall,F1-score and accuracy to assess the quality performance of these models.The results showed that the PSO SVM had greater potential for future implementation in the Tibetan Plateau area because of its superior performance in the landslide susceptibility assessment.

Common susceptibility variants of KDR and IGF-1R are associated with poststroke depression in the Chinese population

Background Depression,one of the most frequent complications after stroke,increases the disease’s burden and physical disability.Poststroke depression(PSD)is a multifactorial disease with genetic,environmental and biological factors involved in its occurrence.Genetic studies on PSD to date have mainly focused on the monoamine system and brain-derived neurotrophic factors.However,understanding is still limited about the influence of the single nucleotide polymorphism(SNP)of other neurotrophic factors on PSD.Aims The present study aimed to investigate the relationship between seven vascular endothelial growth factor(VEGF)family gene variants that occur with PSD.Methods A multicentre candidate gene study from five hospitals in Jiangsu Province from June 2013 to December 2014 involved 121 patients with PSD and 131 patients with non-PSD.Demographic characteristics and neuropsychological assessments were collected.Theχ^(2)test was used to evaluate categorical variables,while the independent t-test was applied to continuous variables.SNPs in seven genes(VEGFA,VEGFB,KDR,FLT-1,IGF-1,IGF-1R and PlGF)were genotyped.Single-marker association for PSD was analysed byχ^(2)tests and logistic regression using SPSS and PLINK software.Results Patients with PSD included more women and those with lower education levels,lower body mass indexes,lower Mini-Mental State Examination scores,and higher scores on the 17-item Hamilton Depression Rating Scale than non-PSD patients.Ninety-two SNPs with seven genes were genotyped and passed quality control.The rs7692791 CC genotypes,the C allele of KDR and the rs9282715 T allele of IGF-1R increased the risk for PSD(χ^(2)=7.881,p=0.019;χ^(2)=4.259,p=0.039;χ^(2)=4.222,p=0.040,respectively).In addition,the SNP rs7692791 of KDR was significantly associated with PSD by the logistic regression of an additive model(p=0.015,OR=9.584,95%CI:1.549 to 59.31).Conclusions Patients with rs7692791 C allele carriers or the CC genotype of KDR and the rs9282715 T allele of IGF-1R may have PSD susceptibility.Findings such as these may help clinicians to identify the high-risk population for PSD earlier and,thus,enable them to provide more timely interventions.

GIS-based flash flooding susceptibility analysis and water management in arid mountain ranges:Safaga Region,Red Sea Mountains,Egypt

The Safaga Region(SR)is part of the Red Sea mountain range in Egypt.Catastrophic flash flooding is now an inescapable event,wreaking havoc and causing massive loss of life and property.The majority of the floodwater,however,has been wasted as runoff to the Red Sea,which,if used wisely,could meet a fraction of the water demands for a variety of applications in this area.The current work aims to use GIS techniques to integrate remote sensing data for evaluating,mitigating,and managing flash floods in SR.The data set comprised Tropical Rainfall Measuring Mission(TRMM)thematic rainfall data,1:50,000 scale topographical map sheets,geological maps,the ASTER Digital Elevation Model(ASTER GDEM),Landsat 7 Enhanced Thematic Mapper"(ETM7+),and Landsat 8 Operational Land Imager.The flash flood risk model of SR is developed using ArcGIS-10.3 geoprocessing tools integrating all the causal factors thematic maps.The final flood risk model for the SR suggests that 57%of the total basins in the SR are at high risk of flooding.Almost 38%of all basins are at moderate flood risk.The remaining 5%of basins are less prone to flooding.Flood-prone zones were identified,suitable dam-building sites were located,and extremely probable areas for water recharge were recognized.On the basis of reliable scientific data,structural and non-structural mitigation strategies that might reduce the damage susceptibility,alleviate the sensitivity of the flash flood,and best utilize its water supply were recommended.

A machine learning-based study of multifactor susceptibility and risk control of induced seismicity in unconventional reservoirs

A comprehensive dataset from 594 fracturing wells throughout the Duvernay Formation near Fox Creek, Alberta, is collected to quantify the influences of geological, geomechanical, and operational features on the distribution and magnitude of hydraulic fracturing-induced seismicity. An integrated machine learning-based investigation is conducted to systematically evaluate multiple factors that contribute to induced seismicity. Feature importance indicates that a distance to fault, a distance to basement, minimum principal stress, cumulative fluid injection, initial formation pressure, and the number of fracturing stages are among significant model predictors. Our seismicity prediction map matches the observed spatial seismicity, and the prediction model successfully guides the fracturing job size of a new well to reduce seismicity risks. This study can apply to mitigating potential seismicity risks in other seismicity-frequent regions.

Evaluation of deep learning algorithms for landslide susceptibility mapping in an alpine-gorge area:a case study in Jiuzhaigou County

With its high mountains,deep valleys,and complex geological formations,the Jiuzhaigou County has the typical characteristics of a disaster-prone mountainous region in southwestern China.On August 8,2017,a strong Ms 7.0 earthquake occurred in this region,causing some of the mountains in the area to become loose and cracked.Therefore,a survey and evaluation of landslides in this area can help to reveal hazards and take effective measures for subsequent disaster management.However,different evaluation models can yield different spatial distributions of landslide susceptibility,and thus,selecting the appropriate model and performing the optimal combination of parameters is the most effective way to improve susceptibility evaluation.In order to construct an evaluation indicator system suitable for Jiuzhaigou County,we extracted 12 factors affecting the occurrence of landslides,including slope,elevation and slope surface,and made samples.At the core of the transformer model is a self-attentive mechanism that enables any two of the features to be interlinked,after which feature extraction is performed via a forward propagation network(FFN).We exploited its coding structure to transform it into a deep learning model that is more suitable for landslide susceptibility evaluation.The results show that the transformer model has the highest accuracy(86.89%),followed by the random forest and support vector machine models(84.47%and 82.52%,respectively),and the logistic regression model achieves the lowest accuracy(79.61%).Accordingly,this deep learning model provides a new tool to achieve more accurate zonation of landslide susceptibility in Jiuzhaigou County.

Integrating predictive modeling techniques with geospatial data for landslide susceptibility assessment in northern Pakistan

The eastern road section of the ChinaPakistan Economic Corridor(CPEC)traverses the challenging terrain of northern Pakistan,where frequent landslides pose a significant threat to socioeconomic development and infrastructure.However,the insufficient data on landslide hazards presents a substantial challenge to practical mitigation efforts.Therefore,we conducted an extensive study to gain insight into landslide assessment along the Mansehra-Muzaffarabad-Mirpur and Mangla(MMMM)Expressway.This study involved preparing a landslide inventory,analyzing landslide causative factors,and developing landslide susceptibility models(LSMs)using published data,remote sensing interpretations,field excursions and integrated predictive techniques.We first used Pearson's correlation coefficient(PCC),variable importance factors(VIF),and information gain ratio(IGR)to evaluate multicollinearity among the selected landslide causative factors(LCFs).Then,the topographic roughness index(TRI)with VIF>5 and PCC>0.7 was considered a redundant factor and thus removed before the data modeling.Finally,we adopted multiple machine-learning methods to analyze landslide susceptibility.The results indicate that the landslide inventory contains 1,776 events,of which 674 were classified based on geometrical and lithological configurations.The IGR results show that the rainfall,lithology,PGA,drainage density,slope,and distance to fault are the most effective LCFs.The AUC values for random forest(RF)(0.901),extreme gradient boosting(XGBoost)(0.884),and K-nearest neighbor(KNN)(0.872)remained higher than evidential belief function(EBF)(0.833),weight of evidence(WoE)(0.820),and certainty factor(CF)(0.810),respectively.The RF model outperformed all other models in terms of prediction.However,these models are accurate but newer in the area;thus,susceptible zones were verified with comprehensive field investigations.The northern and central regions accounted for the high and very high susceptibility classes in the final landslide susceptibility mapping(LSM)compared to the southern areas.

Landslide susceptibility mapping of mountain roads based on machine learning combined model

Landslide susceptibility mapping of mountain roads is frequently confronted by insufficient historical landslide sample data,multicollinearity of existing evaluation index factors,and inconsistency of evaluation factors due to regional environmental variations.Then,a single machine learning model can easily become overfitting,thus reducing the accuracy and robustness of the evaluation model.This paper proposes a combined machine-learning model to address the issues.The landslide susceptibility in mountain roads were mapped by using factor analysis to normalize and reduce the dimensionality of the initial condition factor and generating six new combination factors as evaluation indexes.The mountain roads in the Youxi County,Fujian Province,China were used for the landslide susceptibility mapping.Three most frequently used machine learning techniques,support vector machine(SVM),random forest(RF),and artificial neural network(ANN)models,were used to model the landslide susceptibility of the study area and validate the accuracy of this evaluation index system.The global minimum variance portfolio was utilized to construct a machine learning combined model.5-fold cross-validation,statistical indexes,and AUC(Area Under Curve)values were implemented to evaluate the predictive accuracy of the landslide susceptibility model.The mean AUC values for the SVM,RF,and ANN models in the training stage were 89.2%,88.5%,and 87.9%,respectively,and 78.0%,73.7%,and 76.7%,respectively,in the validating stage.In the training and validation stages,the mean AUC values of the combined model were 92.4% and 87.1%,respectively.The combined model provides greater prediction accuracy and model robustness than one single model.