Backward automatic calibration for three-dimensional landslide models

Back-analysis is broadly used for approaching geotechnical problems when monitoring data are available and information about the soils properties is of poor quality.For landslide stability assessment back-analysis calibration is usually carried out by time consuming trial-and-error procedure.This paper presents a new automatic Decision Support System that supports the selection of the soil parameters for three-dimensional models of landslides based on monitoring data.The method considering a pool of possible solutions,generated through permutation of soil parameters,selects the best ten configurations that are more congruent with the measured displacements.This reduces the operator biases while on the other hand allows the operator to control each step of the computation.The final selection of the preferred solution among the ten best-fitting solutions is carried out by an operator.The operator control is necessary as he may include in the final decision process all the qualitative elements that cannot be included in a qualitative analysis but nevertheless characterize a landslide dynamic as a whole epistemological subject,for example on the base of geomorphological evidence.A landslide located in Northeast Italy has been selected as example for showing the system potentiality.The proposed method is straightforward,scalable and robust and could be useful for researchers and practitioners.

Landslide Susceptibility Mapping Using RBFN-Based Ensemble Machine Learning Models

This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble learning techniques:DAGGING(DG),MULTIBOOST(MB),and ADABOOST(AB).This combination resulted in three distinct ensemble models:DG-RBFN,MB-RBFN,and AB-RBFN.Additionally,a traditional weighted method,Information Value(IV),and a benchmark machine learning(ML)model,Multilayer Perceptron Neural Network(MLP),were employed for comparison and validation.The models were developed using ten landslide conditioning factors,which included slope,aspect,elevation,curvature,land cover,geomorphology,overburden depth,lithology,distance to rivers and distance to roads.These factors were instrumental in predicting the output variable,which was the probability of landslide occurrence.Statistical analysis of the models’performance indicated that the DG-RBFN model,with an Area Under ROC Curve(AUC)of 0.931,outperformed the other models.The AB-RBFN model achieved an AUC of 0.929,the MB-RBFN model had an AUC of 0.913,and the MLP model recorded an AUC of 0.926.These results suggest that the advanced ensemble ML model DG-RBFN was more accurate than traditional statistical model,single MLP model,and other ensemble models in preparing trustworthy landslide susceptibility maps,thereby enhancing land use planning and decision-making.

Displacement field reconstruction in landslide physical modeling by using a terrain laser scanner e Part 2:Application and large strain/displacement and water effect analysis

Deformation analysis is fundamental in geotechnical modeling.Nevertheless,there is still a lack of an effective method to obtain the deformation field under various experimental conditions.In this study,we introduce a processebased physical modeling of a pileereinforced reservoir landslide and present an improved deformation analysis involving large strains and water effects.We collect multieperiod point clouds using a terrain laser scanner and reconstruct its deformation field through a point cloud processing workflow.The results show that this method can accurately describe the landslide surface deformation at any time and area by both scalar and vector fields.The deformation fields in different profiles of the physical model and different stages of the evolutionary process provide adequate and detailed landslide information.We analyze the large strain upstream of the pile caused by the pile installation and the consequent violent deformation during the evolutionary process.Furthermore,our method effectively overcomes the challenges of identifying targets commonly encountered in geotechnical modeling where water effects are considered and targets are polluted,which facilitates the deformation analysis at the wading area in a reservoir landslide.Eventually,combining subsurface deformation as well as numerical modeling,we comprehensively analyze the kinematics and failure mechanisms of this complicated object involving landslides and pile foundations as well as water effects.This method is of great significance for any geotechnical modeling concerning large-strain analysis and water effects.

Oxygen tension modulates cell function in an in vitro three-dimensional glioblastoma tumor model

Hypoxia is a typical feature of the tumor microenvironment,one of the most critical factors affecting cell behavior and tumor progression.However,the lack of tumor models able to precisely emulate natural brain tumor tissue has impeded the study of the effects of hypoxia on the progression and growth of tumor cells.This study reports a three-dimensional(3D)brain tumor model obtained by encapsulating U87MG(U87)cells in a hydrogel containing type I collagen.It also documents the effect of various oxygen concentrations(1%,7%,and 21%)in the culture environment on U87 cell morphology,proliferation,viability,cell cycle,apoptosis rate,and migration.Finally,it compares two-dimensional(2D)and 3D cultures.For comparison purposes,cells cultured in flat culture dishes were used as the control(2D model).Cells cultured in the 3D model proliferated more slowly but had a higher apoptosis rate and proportion of cells in the resting phase(G0 phase)/gap I phase(G1 phase)than those cultured in the 2D model.Besides,the two models yielded significantly different cell morphologies.Finally,hypoxia(e.g.,1%O2)affected cell morphology,slowed cell growth,reduced cell viability,and increased the apoptosis rate in the 3D model.These results indicate that the constructed 3D model is effective for investigating the effects of biological and chemical factors on cell morphology and function,and can be more representative of the tumor microenvironment than 2D culture systems.The developed 3D glioblastoma tumor model is equally applicable to other studies in pharmacology and pathology.

Exploring mechanism of hidden,steep obliquely inclined bedding landslides using a 3DEC model:A case study of the Shanyang landslide in Shaanxi Province,China

Catastrophic geological disasters frequently occur on slopes with obliquely inclined bedding structures(also referred to as obliquely inclined bedding slopes),where the apparent dip sliding is not readily visible.This phenomenon has become a focal point in landslide research.Yet,there is a lack of studies on the failure modes and mechanisms of hidden,steep obliquely inclined bedding slopes.This study investigated the Shanyang landslide in Shaanxi Province,China.Using field investigations,laboratory tests of geotechnical parameters,and the 3DEC software,this study developed a numerical model of the landslide to analyze the failure process of such slopes.The findings indicate that the Shanyang landslide primarily crept along a weak interlayer under the action of gravity.The landslide,initially following a dip angle with the support of a stable inclined rock mass,shifted direction under the influence of argillization in the weak interlayer,moving towards the apparent dip angle.The slide resistance effect of the karstic dissolution zone was increasingly significant during this process,with lateral friction being the primary resistance force.A reduction in the lateral friction due to karstic dissolution made the apparent dip sliding characteristics of the Shanyang landslide more pronounced.Notably,deformations such as bending and uplift at the slope’s foot suggest that the main slide resistance shifts from lateral friction within the karstic dissolution zone to the slope foot’s resistance force,leading to the eventual buckling failure of the landslide.This study unveils a novel failure mode of apparent dip creep-buckling in the Shanyang landslide,highlighting the critical role of lateral friction from the karstic dissolution zone in its failure mechanism.These insights offer a valuable reference for mitigating risks and preventing disasters related to obliquely inclined bedding landslides.

Virtual and augmented reality systems and three-dimensional printing of the renal model—novel trends to guide preoperative planning for renal cancer

ObjectiveThis study aimed to explore the applications of three-dimensional (3D) technology, including virtual reality, augmented reality (AR), and 3D printing system, in the field of medicine, particularly in renal interventions for cancer treatment.MethodsA specialized software transforms 2D medical images into precise 3D digital models, facilitating improved anatomical understanding and surgical planning. Patient-specific 3D printed anatomical models are utilized for preoperative planning, intraoperative guidance, and surgical education. AR technology enables the overlay of digital perceptions onto real-world surgical environments.ResultsPatient-specific 3D printed anatomical models have multiple applications, such as preoperative planning, intraoperative guidance, trainee education, and patient counseling. Virtual reality involves substituting the real world with a computer-generated 3D environment, while AR overlays digitally created perceptions onto the existing reality. The advances in 3D modeling technology have sparked considerable interest in their application to partial nephrectomy in the realm of renal cancer. 3D printing, also known as additive manufacturing, constructs 3D objects based on computer-aided design or digital 3D models. Utilizing 3D-printed preoperative renal models provides benefits for surgical planning, offering a more reliable assessment of the tumor's relationship with vital anatomical structures and enabling better preparation for procedures. AR technology allows surgeons to visualize patient-specific renal anatomical structures and their spatial relationships with surrounding organs by projecting CT/MRI images onto a live laparoscopic video. Incorporating patient-specific 3D digital models into healthcare enhances best practice, resulting in improved patient care, increased patient satisfaction, and cost saving for the healthcare system.

Displacement field reconstruction in landslide physical modeling by using a terrain laser scanner e Part 1:Methodology,error analysis and validation

Laser scanning technology has been widely used in landslide aspects.However,the existing deformation analysis based on terrain laser scanners can only provide limited information,which is insufficient for understanding landslide kinematics and failure mechanisms.To overcome this limitation,this paper proposes an automated method for processing point clouds collected in landslide physical modeling.This method allows the acquisition of quantitative three-dimensional(3D)deformation field information.The results show the organized and spatially related point cloud segmentation in terms of spherical targets.The segmented point clouds can be fitted to determine the locations of all preset targets and their corresponding location changes.The proposed method has been validated based on theoretical analysis and numerical and physical tests,which indicates that it can batch-process massive data sets with high computational efficiency and good noise resistance.Compared to existing methods,this method shows a significant potential for understanding landslide kinematics and failure mechanisms and advancing the application of 3D laser scanning in geotechnical modeling.

An attention-based teacher-student model for multivariate short-term landslide displacement prediction incorporating weather forecast data

Predicting the displacement of landslide is of utmost practical importance as the landslide can pose serious threats to both human life and property.However,traditional methods have the limitation of random selection in sliding window selection and seldom incorporate weather forecast data for displacement prediction,while a single structural model cannot handle input sequences of different lengths at the same time.In order to solve these limitations,in this study,a new approach is proposed that utilizes weather forecast data and incorporates the maximum information coefficient(MIC),long short-term memory network(LSTM),and attention mechanism to establish a teacher-student coupling model with parallel structure for short-term landslide displacement prediction.Through MIC,a suitable input sequence length is selected for the LSTM model.To investigate the influence of rainfall on landslides during different seasons,a parallel teacher-student coupling model is developed that is able to learn sequential information from various time series of different lengths.The teacher model learns sequence information from rainfall intensity time series while incorporating reliable short-term weather forecast data from platforms such as China Meteorological Administration(CMA)and Reliable Prognosis(https://rp5.ru)to improve the model’s expression capability,and the student model learns sequence information from other time series.An attention module is then designed to integrate different sequence information to derive a context vector,representing seasonal temporal attention mode.Finally,the predicted displacement is obtained through a linear layer.The proposed method demonstrates superior prediction accuracies,surpassing those of the support vector machine(SVM),LSTM,recurrent neural network(RNN),temporal convolutional network(TCN),and LSTM-Attention models.It achieves a mean absolute error(MAE)of 0.072 mm,root mean square error(RMSE)of 0.096 mm,and pearson correlation coefficients(PCCS)of 0.85.Additionally,it exhibits enhanced prediction stability and interpretability,rendering it an indispensable tool for landslide disaster prevention and mitigation.

Effectiveness of hybrid ensemble machine learning models for landslide susceptibility analysis:Evidence from Shimla district of North-west Indian Himalayan region

The Indian Himalayan region is frequently experiencing climate change-induced landslides.Thus,landslide susceptibility assessment assumes greater significance for lessening the impact of a landslide hazard.This paper makes an attempt to assess landslide susceptibility in Shimla district of the northwest Indian Himalayan region.It examined the effectiveness of random forest(RF),multilayer perceptron(MLP),sequential minimal optimization regression(SMOreg)and bagging ensemble(B-RF,BSMOreg,B-MLP)models.A landslide inventory map comprising 1052 locations of past landslide occurrences was classified into training(70%)and testing(30%)datasets.The site-specific influencing factors were selected by employing a multicollinearity test.The relationship between past landslide occurrences and influencing factors was established using the frequency ratio method.The effectiveness of machine learning models was verified through performance assessors.The landslide susceptibility maps were validated by the area under the receiver operating characteristic curves(ROC-AUC),accuracy,precision,recall and F1-score.The key performance metrics and map validation demonstrated that the BRF model(correlation coefficient:0.988,mean absolute error:0.010,root mean square error:0.058,relative absolute error:2.964,ROC-AUC:0.947,accuracy:0.778,precision:0.819,recall:0.917 and F-1 score:0.865)outperformed the single classifiers and other bagging ensemble models for landslide susceptibility.The results show that the largest area was found under the very high susceptibility zone(33.87%),followed by the low(27.30%),high(20.68%)and moderate(18.16%)susceptibility zones.The factors,namely average annual rainfall,slope,lithology,soil texture and earthquake magnitude have been identified as the influencing factors for very high landslide susceptibility.Soil texture,lineament density and elevation have been attributed to high and moderate susceptibility.Thus,the study calls for devising suitable landslide mitigation measures in the study area.Structural measures,an immediate response system,community participation and coordination among stakeholders may help lessen the detrimental impact of landslides.The findings from this study could aid decision-makers in mitigating future catastrophes and devising suitable strategies in other geographical regions with similar geological characteristics.

Maximum initial primary wave model for low-Froude-number reservoir landslides based on wave theory

The impulse waves induced by large-reservoir landslides can be characterized by a low Froude number.However,systematic research on predictive models specifically targeting the initial primary wave is lacking.Taking the Shuipingzi 1#landslide that occurred in the Baihetan Reservoir area of the Jinsha River in China as an engineering example,this study established a large-scale physical model(with dimensions of 30 m×29 m×3.5 m at a scale of 1:150)and conducted scaled experiments on 3D landslide-induced impulse waves.During the process in which a sliding mass displaced and compressed a body of water to generate waves,the maximum initial wave amplitude was found to be positively correlated with the sliding velocity and the volume of the landslide.With the increase in the water depth,the wave amplitude initially increased and then decreased.The duration of pressure exertion by the sliding mass at its maximum velocity directly correlated with an elevated wave amplitude.Based on the theories of low-amplitude waves and energy conservation,while considering the energy conversion efficiency,a predictive model for the initial wave amplitude was derived.This model could fit and validate the functions of wavelength and wave velocity.The accuracy of the initial wave amplitude was verified using physical experiment data,with a prediction accuracy for the maximum initial wave amplitude reaching 90%.The conversion efficiency(η)directly determined the accuracy of the estimation formula.Under clear conditions for landslide-induced impulse wave generation,estimating the value ofηthrough analogy cases was feasible.This study has derived the landslide-induced impulse waves amplitude prediction formula from the standpoints of wave theory and energy conservation,with greater consideration given to the intrinsic characteristics in the formation process of landslide-induced impulse waves,thereby enhancing the applicability and extensibility of the formula.This can facilitate the development of empirical estimation methods for landslide-induced impulse waves toward universality.

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.

Three-dimensional structural models,evolution and petroleum geological significances of transtensional faults in the Ziyang area,central Sichuan Basin,SW China

With drilling and seismic data of Transtensional(strike-slip)Fault System in the Ziyang area of the central Sichuan Basin,SW China plane-section integrated structural interpretation,3-D fault framework model building,fault throw analyzing,and balanced profile restoration,it is pointed out that the transtensional fault system in the Ziyang 3-D seismic survey consists of the northeast-trending F_(I)19 and F_(I)20 fault zones dominated by extensional deformation,as well as 3 sets of northwest-trending en echelon normal faults experienced dextral shear deformation.Among them,the F_(I)19 and F_(I)20 fault zones cut through the Neoproterozoic to Lower Triassic Jialingjiang Formation,presenting a 3-D structure of an“S”-shaped ribbon.And before Permian and during the Early Triassic,the F_(I)19 and F_(I)20 fault zones underwent at least two periods of structural superimposition.Besides,the 3 sets of northwest-trending en echelon normal faults are composed of small normal faults arranged in pairs,with opposite dip directions and partially left-stepped arrangement.And before Permian,they had formed almost,restricting the eastward growth and propagation of the F_(I)19 fault zone.The F_(I)19 and F_(I)20 fault zones communicate multiple sets of source rocks and reservoirs from deep to shallow,and the timing of fault activity matches well with oil and gas generation peaks.If there were favorable Cambrian-Triassic sedimentary facies and reservoirs developing on the local anticlinal belts of both sides of the F_(I)19 and F_(I)20 fault zones,the major reservoirs in this area are expected to achieve breakthroughs in oil and gas exploration.

Hyper accuracy three-dimensional virtual anatomical rainbow model facilitates surgical planning and safe selective clamping during robot-assisted partial nephrectomy

ObjectiveTo highlight the role of hyper accuracy three-dimensional(3D)reconstruction in facilitating surgical planning and guiding selective clamping during robot-assisted partial nephrectomy(RAPN).MethodsA transperitoneal RAPN was performed in a 62-year-old male patient presenting with a 4 cm right anterior interpolar renal mass(R.E.N.A.L nephrometry score 7A).An abnormal vasculature was observed,with a single renal vein and two right renal arteries originating superiorly to the vein and anterior,when dividing in their segmental branches.According to the hyper accuracy 3D(HA3D^(®))rainbow model(MEDICS Srl,Turin,Italy),one branch belonging to one of the segmental arteries was feeding the tumor.This allowed for an accurate prediction of the area vascularized by each arterial branch.The 3D model was included in the intraoperative console view during the whole procedure,using the TilePro feature.A step-by-step explanation of the procedure is provided in the video attached to the present article.ResultsThe operative time was 90 min with a warm ischemia time on selective clamping of 13 min.Estimated blood loss was 180 mL.No intraoperative complication was encountered and no drain was placed at the end of the procedure.The patient was discharged on postoperative Day 2,without any early postoperative complications.The final pathology report showed a pathological tumor stage 1 clear cell renal cell carcinoma with negative surgical margins.ConclusionThe present study and the attached video illustrate the value of 3D rainbow model during the planning and execution of a RAPN with selective clamping.It shows how the surgeon can rely on this model to be more efficient by avoiding unnecessary surgical steps,and to safely adopt a“selective”clamping strategy that can translate in minimal functional impact.

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.

A landslide monitoring method using data from unmanned aerial vehicle and terrestrial laser scanning with insufficient and inaccurate ground control points

Non-contact remote sensing techniques,such as terrestrial laser scanning(TLS)and unmanned aerial vehicle(UAV)photogrammetry,have been globally applied for landslide monitoring in high and steep mountainous areas.These techniques acquire terrain data and enable ground deformation monitoring.However,practical application of these technologies still faces many difficulties due to complex terrain,limited access and dense vegetation.For instance,monitoring high and steep slopes can obstruct the TLS sightline,and the accuracy of the UAV model may be compromised by absence of ground control points(GCPs).This paper proposes a TLS-and UAV-based method for monitoring landslide deformation in high mountain valleys using traditional real-time kinematics(RTK)-based control points(RCPs),low-precision TLS-based control points(TCPs)and assumed control points(ACPs)to achieve high-precision surface deformation analysis under obstructed vision and impassable conditions.The effects of GCP accuracy,GCP quantity and automatic tie point(ATP)quantity on the accuracy of UAV modeling and surface deformation analysis were comprehensively analyzed.The results show that,the proposed method allows for the monitoring accuracy of landslides to exceed the accuracy of the GCPs themselves by adding additional low-accuracy GCPs.The proposed method was implemented for monitoring the Xinhua landslide in Baoxing County,China,and was validated against data from multiple sources.

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.

GIS-based landslide susceptibility mapping using numerical risk factor bivariate model and its ensemble with linear multivariate regression and boosted regression tree algorithms

In this study, a novel approach of the landslide numerical risk factor(LNRF) bivariate model was used in ensemble with linear multivariate regression(LMR) and boosted regression tree(BRT) models, coupled with radar remote sensing data and geographic information system(GIS), for landslide susceptibility mapping(LSM) in the Gorganroud watershed, Iran. Fifteen topographic, hydrological, geological and environmental conditioning factors and a landslide inventory(70%, or 298 landslides) were used in mapping. Phased array-type L-band synthetic aperture radar data were used to extract topographic parameters. Coefficients of tolerance and variance inflation factor were used to determine the coherence among conditioning factors. Data for the landslide inventory map were obtained from various resources, such as Iranian Landslide Working Party(ILWP), Forestry, Rangeland and Watershed Organisation(FRWO), extensive field surveys, interpretation of aerial photos and satellite images, and radar data. Of the total data, 30% were used to validate LSMs, using area under the curve(AUC), frequency ratio(FR) and seed cell area index(SCAI).Normalised difference vegetation index, land use/land cover and slope degree in BRT model elevation, rainfall and distance from stream were found to be important factors and were given the highest weightage in modelling. Validation results using AUC showed that the ensemble LNRF-BRT and LNRFLMR models(AUC = 0.912(91.2%) and 0.907(90.7%), respectively) had high predictive accuracy than the LNRF model alone(AUC = 0.855(85.5%)). The FR and SCAI analyses showed that all models divided the parameter classes with high precision. Overall, our novel approach of combining multivariate and machine learning methods with bivariate models, radar remote sensing data and GIS proved to be a powerful tool for landslide susceptibility mapping.

Spatial prediction of landslide susceptibility using GIS-based statistical and machine learning models in Wanzhou County,Three Gorges Reservoir, China

Landslide susceptibility mapping is vital for landslide risk management and urban planning.In this study,we used three statistical models[frequency ratio,certainty factor and index of entropy(IOE)]and a machine learning model[random forest(RF)]for landslide susceptibility mapping in Wanzhou County,China.First,a landslide inventory map was prepared using earlier geotechnical investigation reports,aerial images,and field surveys.Then,the redundant factors were excluded from the initial fourteen landslide causal factors via factor correlation analysis.To determine the most effective causal factors,landslide susceptibility evaluations were performed based on four cases with different combinations of factors("cases").In the analysis,465(70%)landslide locations were randomly selected for model training,and 200(30%)landslide locations were selected for verification.The results showed that case 3 produced the best performance for the statistical models and that case 2 produced the best performance for the RF model.Finally,the receiver operating characteristic(ROC)curve was used to verify the accuracy of each model's results for its respective optimal case.The ROC curve analysis showed that the machine learning model performed better than the other three models,and among the three statistical models,the IOE model with weight coefficients was superior.

Mapping landslide susceptibility at the Three Gorges Reservoir, China, using gradient boosting decision tree,random forest and information value models

This work was to generate landslide susceptibility maps for the Three Gorges Reservoir(TGR) area, China by using different machine learning models. Three advanced machine learning methods, namely, gradient boosting decision tree(GBDT), random forest(RF) and information value(InV) models, were used, and the performances were assessed and compared. In total, 202 landslides were mapped by using a series of field surveys, aerial photographs, and reviews of historical and bibliographical data. Nine causative factors were then considered in landslide susceptibility map generation by using the GBDT, RF and InV models. All of the maps of the causative factors were resampled to a resolution of 28.5 m. Of the 486289 pixels in the area,28526 pixels were landslide pixels, and 457763 pixels were non-landslide pixels. Finally, landslide susceptibility maps were generated by using the three machine learning models, and their performances were assessed through receiver operating characteristic(ROC) curves, the sensitivity, specificity,overall accuracy(OA), and kappa coefficient(KAPPA). The results showed that the GBDT, RF and In V models in overall produced reasonable accurate landslide susceptibility maps. Among these three methods, the GBDT method outperforms the other two machine learning methods, which can provide strong technical support for producing landslide susceptibility maps in TGR.

A prediction model for horizontal run-out distance of landslides triggered by Wenchuan earthquake

The peak ground acceleration （PGA）, the volume of a sliding mass V, the height of a mountain HL and the slope angle θ of a mountain are four important parameters affecting the horizontal run-out distance of a landslide L. Correlations among them are studied statistically based on field investigations from 67 landslides triggered by the ground shaking and other factors during the Wenchuan earthquake, and then a prediction model for horizontal run-out distance L is developed in this study. This model gives due consideration to the implications of the above four parameters on the horizontal run-out distance L and the validity of the model is verified by the Donghekou and Magong Woqian landslides. At the same time, the advantages of the model are shown by comparing it with two other common prediction methods. The major findings drawn from the analyses and comparisons are： （1） an exponential relationship exists between L and log V, L and log HL, L and log PGA separately, but a negative exponential relationship exists between L and log tan0, which agrees with the statistical results; and （2） according to the analysis results of the relative relationship between the height of a mountain （H） and the place where the landslides occur, the probabilities at distances of2H/3-H, H/3-2H/3, and O-H/3 are 70.8%, 15.4%, and 13.8%, respectively, revealing that most landslides occurred at a distance of H/2-H. This prediction model can provide an effective technical support for the prevention and mitigation of landslide hazards.