Landslide susceptibility mapping using random forest and boosted tree models in Pyeong-Chang,Korea

Landslides susceptibility maps were constructed in the Pyeong-Chang area, Korea, using the Random Forest and Boosted Tree models. Landslide locations were randomly selected in a 50/50 ratio for training and validation of the models. Seventeen landslide-related factors were extracted and constructed in a spatial database. The relationships between the observed landslide locations and these factors were identified by using the two models. The models were used to generate a landslide susceptibility map and the importance of the factors was calculated. Finally, the landslide susceptibility maps were validated. Finally, landslide susceptibility maps were generated. For the Random Forest model, the validation accuracy in regression and classification algorithms showed 79.34 and 79.18%, respectively, and for the Boosted Tree model, these were 84.87 and 85.98%, respectively. The two models showed satisfactory accuracies, and the Boosted Tree model showed better results than the Random Forest model.     

Landslide susceptibility mapping by remote sensing and geomorphological data: case studies on the Sorrentina Peninsula (Southern Italy)

The Sorrentina Peninsula is a densely populated area with high touristic impact. It is located in a morphologically complex zone of Southern Italy frequently affected by dangerous and calamitous landslides. This work contributes to the prevention of such natural disasters by applying a GIS-based interdisciplinary approach aimed to map the areas more potentially prone to trigger slope instability phenomena. We have developed the Landslide Susceptibility Index (LSI) combining five weighted and ranked susceptibility parameters on a GIS platform. These parameters are recognized in the literature as the main predisposing factors for triggering landslides. This work combines analyses conducted on Remote Sensing, Geo-Lithology and Morphometry data and it is organized in the following logical steps: i) Multi-temporal InSAR technique was applied to Envisat-ASAR (2003–2010) and COSMO-SkyMed (2013–2015) datasets to obtain the ground displacement time series and the relative mean ground velocity maps. InSAR allowed the detection of the areas that are subjected to ground deformation and the main affected municipalities; ii) Such deformation areas were investigated through airborne photo interpretation to identify the presence of geomorphological peculiarities connected to potential slope instability. Subsequently, some of these peculiarities were checked on the field; iii) In these deformation areas the susceptibility parameters were mapped in the entire territory of Amalfi and Conca dei Marini and then investigated with a multivariate analysis to derive the classes and the respective weights used in the LSI calculation. The resulting LSI map classifies the two municipalities with high spatial resolution (2m) according to five classes of instability. The map highlights that the high/very high susceptibility zones cover 6% of the investigated territory and correspond to potential landslide source areas characterized by 25°-70° slope angles. A spatial analysis between the map of the historical landslides and the areas classified according to susceptibility allowed testing of the reliability of the LSI Index, resulting in 85% prediction accuracy.     

Optimizing landslide susceptibility mapping in the Kongtong District,NW China: comparing the subdivision criteria of factors

Abstract

The standards applied to reclassify landslide-conditioning factors differ among studies and may change the accuracy of identifying landslide-prone areas. Therefore, we identified two standards per factor (elevation, aspect, slope, proximity to roads and proximity to streams) from the existing literature and set them as predisposing criteria in this paper. In addition to the five factors, lithology represented by types and a landslide inventory map produced from field surveys were also used in mapping. Thirty-two landslide susceptibility maps were generated based on weights-of-evidence and evaluated using the relative operative characteristic method. The results show that the subdivision criteria of factors change the accuracy, with the success rate varying from 84.34% to 87.51%. The map with the highest value captures more landslides in relatively higher susceptibility classes and is therefore considered the optimal one. Ultimately, a simplified mode of combining subdivision criteria is proposed to simplify comparison.     

Landslide vulnerability assessment and zonation through ranking of causative parameters based on landslide density-derived statistical indicators

The research presented in this article is based on a new technique governed by three different statistical indicators determined for each causative parameter, viz. highest density, average density and co-efficient of variation of landslides. Each of these indicators was assigned a rank value between 1 and 14 depending upon its variation among the 14 causative parameters. The aggregate of the three types of rank values estimate the total ranking value (TRV) for each causative parameter. The study area is divided into 78,256 spatial units and for each such spatial unit, the influence of the different causative parameters is determined as the product of the experts' weight of the associated sub-category and the TRV of the causative parameter that categorizes the study area into various zones. The efficacy of the proposed technique is demonstrated by the occurrence of significantly high prediction accuracy of 84%.     

Investigation of automatic feature weighting methods (Fisher,Chi-square and Relief-F) for landslide susceptibility mapping

In landslide susceptibility mapping, factor weights have been usually determined by expert judgements. A novel methodology for weighting landslide causative factors by integrating statistical feature weighting algorithms was proposed. The primary focus of this study is to investigate the effectiveness of automatic feature weighting algorithms, namely Fisher, Chi-square and Relief-F algorithms. Analytic hierarchy process (AHP) method was used as a benchmark method to compare the performances of the weighting algorithms. All weighted factors were tested using factor-weighted overlay method, and quality of these maps was assessed using overall accuracy, area under the ROC curve (AUC) and success rate curve. In addition, Wilcoxon’s signed-rank test was applied to evaluate statistical differences between both estimated overall accuracies and AUCs, respectively. Results showed that the weights determined by feature weighting methods outperformed the conventional AHP method by about 6% and this level of differences was found to be statistically significant.     

Landslide susceptibility assessment using evidential belief function,certainty factor and frequency ratio model at Baxie River basin,NW China

This study evaluates and compares landslide susceptibility maps of the Baxie River basin, Gansu Province, China, using three models: evidential belief function (EBF), certainty factor (CF) and frequency ratio (FR). First, a landslide inventory map is constructed from satellite image interpretation and extensive field data. Second, the study area is partitioned into 17,142 slope units, and modelled using nine landslide influence parameters: elevation, slope angle, slope aspect, relief amplitude, cutting depth, gully density, lithology, normalized difference vegetation index and distance to roads. Finally, landslide susceptibility maps are presented based on EBF, CF and FR models and validated using area under curve (AUC) analysis. The success rates of the EBF, CF and FR models are 0.8038, 0.7924 and 0.8088, respectively, while the prediction rates of the three models are 0.8056, 0.7922 and 0.7989, respectively. The result of this study can be reliably used in land use management and planning.     

A GIS-based comparative study of Dempster-Shafer,logistic regression and artificial neural network models for landslide susceptibility mapping

The main aim of present study is to compare three GIS-based models, namely Dempster–Shafer (DS), logistic regression (LR) and artificial neural network (ANN) models for landslide susceptibility mapping in the Shangzhou District of Shangluo City, Shaanxi Province, China. At First, landslide locations were identified by aerial photographs and supported by field surveys, and a total of 145 landslide locations were mapped in the study area. Subsequently, the landslide inventory was randomly divided into two parts (70/30) using Hawths Tools in ArcGIS 10.0 for training and validation purposes, respectively. In the present study, 14 landslide conditioning factors such as altitude, slope angle, slope aspect, topographic wetness index, sediment transport index, stream power index, plan curvature, profile curvature, lithology, rainfall, distance to rivers, distance to roads, distance to faults and normalized different vegetation index were used to detect the most susceptible areas. In the next step, landslide susceptible areas were mapped using the DS, LR and ANN models based on landslide conditioning factors. Finally, the accuracies of the landslide susceptibility maps produced from the three models were verified using the area under the curve (AUC). The validation results showed that the landslide susceptibility map generated by the ANN model has the highest training accuracy (73.19%), followed by the LR model (71.37%), and the DS model (66.42%). Similarly, the AUC plot for prediction accuracy presents that ANN model has the highest accuracy (69.62%), followed by the LR model (68.94%), and the DS model (61.39%). According to the validation results of the AUC curves, the map produced by these models exhibits the satisfactory properties.     

Evaluation of environmental parameters in logistic regression models for landslide susceptibility mapping

Abstract

The aim of this study was to determine how well the landslide susceptibility parameters, obtained by data-dependent statistical models, matched with the parameters used in the literature. In order to achieve this goal, 20 different environmental parameters were mapped in a well-studied landslide-prone area, the Asarsuyu catchment in northwest Turkey. A total of 4400 seed cells were generated from 47 different landslides and merged with different attributes of 20 different environmental causative variables into a database. In order to run a series of logistic regression models, different random landslide-free sample sets were produced and combined with seed cells. Different susceptibility maps were created with an average success rate of nearly 80%. The coherence among the models showed spatial correlations greater than 90%. Models converged in the parameter selection peculiarly, in that the same nine of 20 were chosen by different logistic regression models. Among these nine parameters, lithology, geological structure (distance/density), landcover-landuse, and slope angle were common parameters selected by both the regression models and literature. Accuracy assessment of the logistic models was assessed by absolute methods. All models were field checked with the landslides resulting from the 12 November 1999, Kayna?li Earthquake (Ms = 7.2).     

Application of frequency ratio,weights of evidence and evidential belief function models in landslide susceptibility mapping

The landslide hazard occurred in Taibai County has the characteristics of the typical landslides in mountain hinterland. The slopes mainly consist of residual sediments and locate along the highway. Most of them are in the less stable state and in high risk during rainfall in flood season especially. The main purpose of this paper is to produce landslide susceptibility maps for Taibai County (China). In the first stage, a landslide inventory map and the input layers of the landslide conditioning factors were prepared in the geographic information system supported by field investigations and remote sensing data. The landslides conditioning factors considered for the study area were slope angle, altitude, slope aspect, plan curvature, profile curvature, distance to faults, distance to rivers, distance to roads, normalized difference vegetation index, lithological unit, rainfall and land use. Subsequently, the thematic data layers of conditioning factors were integrated by frequency ratio (FR), weights of evidence (WOE) and evidential belief function (EBF) models. As a result, landslide susceptibility maps were obtained. In order to compare the predictive ability of these three models, a validation procedure was conducted. The curves of cumulative area percentage of ordered index values vs. the cumulative percentage of landslide numbers were plotted and the values of area under the curve (AUC) were calculated. The predictive ability was characterized by the AUC values and it indicates that all these models considered have relatively similar and high accuracies. The success rate of FR, WOE and EBF models was 0.9161, 0.9132 and 0.9129, while the prediction rate of the three models was 0.9061, 0.9052 and 0.9007, respectively. Considering the accuracy and simplicity comprehensively, the FR model is the optimum method. These landslide susceptibility maps can be used for preliminary land use planning and hazard mitigation purpose.     

Comparison of landslide susceptibility mapping based on statistical index,certainty factors,weights of evidence and evidential belief function models

The main aim of this study was to produce landslide susceptibility maps using statistical index (SI), certainty factors (CF), weights of evidence (WoE) and evidential belief function (EBF) models for the Long County, China. Firstly, a landslide inventory map, including a total of 171 landslides, was compiled on the basis of earlier reports, interpretation of aerial photographs and supported by extensive field surveys. Thereafter, all landslides were randomly separated into two data sets: 70% landslides (120 points) were selected for establishing the model and the remaining landslides (51 points) were used for validation purposes. Eleven landslide conditioning factors, such as slope aspect, slope angle, plan curvature, profile curvature, altitude, distance to faults, distance to roads, distance to rivers, lithology, NDVI and land use, were considered for landslide susceptibility mapping in this study. Then, the SI, CF, WoE and EBF models were used to produce the landslide susceptibility maps for the study area. Finally, the four models were validated using area under the curve (AUC) method. According to the validation results, the EBF model (AUC = 78.93%) has a higher prediction accuracy than the SI model (AUC = 77.72%), the WoE model (AUC = 77.62%) and the CF model (AUC = 77.72%). Similarly, the validation results also indicate that the EBF model has the highest training accuracy of 80.25%, followed by SI (79.80%), WoE (79.71%) and CF (79.67%) models.     

Spatial distribution and susceptibility analyses of pre-earthquake and coseismic landslides related to the Ms 6.5 earthquake of 2014 in Ludian,Yunan, China

On 3 August 2014, an earthquake struck Ludian County, Yunnan Province, China, which has caused a large number of coseismic landslides. Visual interpretation permitted 284 and 1053 landslides before and after the event to be mapped, respectively. This work attempted to analyse these two kinds of landslides. Conditioning factors, such as slope angle, aspect, curvature, elevation, distance from drainages, intensity and lithology, and the index of Landslide Number Density (LND) were used to describe the spatial distribution of these landslides. Then, the pre-earthquake and coseismic landslide susceptibility maps were produced using the information value model. The areas under curve are 84.73 and 77.05%, for the pre-earthquake and coseismic landslides, respectively. The results show that the LND values as well as the information values of coseismic landslides are larger than those of the pre-earthquake case. This also indicates that this Ludian earthquake has a relatively larger ability to trigger landslides.     

An assessment on the use of Terra ASTER L3A data in landslide susceptibility mapping

The main purpose of the present study is to evaluate the potential use of Terra ASTER data—the L3A DEM and its derivatives in landslide susceptibility mapping. For the purpose, an appropriate application site from the Western Black Sea region of Turkey—the Kelemen catchment area was selected. During the analyses, a two-stage comparative evaluation was carried out. In the first stage, the differences between the DEMs obtained from Terra ASTER L3A data and the conventional topographic data; and their first and second derivatives were investigated. Subsequently, different susceptibility maps were produced by using the DEMs and the topographic attributes obtained from both source of data in addition to the spectral information acquired from satellite sensor. According to the results of the comparative evaluations, a strong correlation between Terra ASTER L3A DEM and the conventional topographic data was obtained. However, depending on the increment of the degree of the derivative, an evident decrease in the spatial correlations was observed. On the contrary, the final model performance, prediction capacity, and the spatial performance statistics for the landslide susceptibility maps produced by using both source of data were found as very high and close to each other.     

Flood susceptibility mapping using frequency ratio and weights-of-evidence models in the Golastan Province,Iran

Flood is one of the most devastating natural disasters with socio-economic and environmental consequences. Thus, comprehensive flood management is essential to reduce the flood effects on human lives and livelihoods. The main goal of this study was to investigate the application of the frequency ratio (FR) and weights-of-evidence (WofE) models for flood susceptibility mapping in the Golestan Province, Iran. At first, a flood inventory map was prepared using Iranian Water Resources Department and extensive field surveys. In total, 144 flood locations were identified in the study area. Of these, 101 (70%) floods were randomly selected as training data and the remaining 43 (30%) cases were used for the validation purposes. In the next step, flood conditioning factors such as lithology, land-use, distance from rivers, soil texture, slope angle, slope aspect, plan curvature, topographic wetness index (TWI) and altitude were prepared from the spatial database. Subsequently, the receiver operating characteristic (ROC) curves were drawn for produced flood susceptibility maps and the area under the curves (AUCs) was computed. The final results indicated that the FR (AUC = 76.47%) and WofE (AUC = 74.74%) models have almost similar and reasonable results. Therefore, these flood susceptibility maps can be useful for researchers and planner in flood mitigation strategies.     

Spatial model integration for shallow landslide susceptibility and its runout using a GIS-based approach in Yongin,Korea

Rainfall-triggered shallow landslide is very common in Korean mountains and the socioeconomic impact is much higher than in the past due to population pressure in hazardous zones. Present study is an attempt toward the development of a methodology for the integration of shallow landslide susceptibility zones and runout zones that could be reached by mobilized mass. Landslide occurrence areas in Yongin were determined based on the interpretation of aerial photographs and extensive field surveys. Nineteen landslide-related factors maps were collected and analysed in geographic information system environment. Among 109 identified landslides, about 85% randomly selected training landslide data from inventory map was used to generate an evidential belief function model and remaining 15% landslides were used to validate the shallow landslide susceptibility map. The resulting susceptibility map had a success rate of 89.2% and a predictive accuracy of 92.1%. A runout propagation from high susceptible area was obtained from the modified multiple-flow direction algorithm. A matrix was used to integrate the shallow landslide susceptibility classes and the runout probable zone. Thus, each pixel had a susceptibility class in relation to its failure probability and runout susceptibility class. The study of landslide potential and its propagation can be used to obtain a spatial prediction for landslides, which could contribute to landslide risk mitigation.     

金沙江流域滑坡易发性空间预报分析

灾害易发性预报是提高灾害防控能力的第一步.针对位于云南省内的金沙江流域因地势险峻、生态环境脆弱,加之近年来人为活动增多已成为地质灾害高发区的现状,本文以金沙江德钦至华坪段滑坡灾害为例,运用Maxent和随机森林两种机器学习模型对滑坡空间分布作归因与预测,并对两者之间的差异进行对比分析.试验结果表明,随机森林模型的预测精...     

Improving the reliability of landslide susceptibility mapping through spatial uncertainty analysis: a case study of Al Hoceima,Northern Morocco

This paper aims at providing an answer as to whether generalization obtained with data-driven modelling can be used to gauge the plausibility of the physically based (PB) model’s prediction. Two statistical models namely; Weight of Evidence (WofE) and Logistic Regression (LR), and a PB model using the infinite slope assumptions were evaluated and compared with respect to their abilities to predict susceptible areas to shallow landslides at the 1:10.000 urban scale. Threshold-dependent performance metrics showed that the three methods produced statistically comparable results in terms of success and prediction rates. However, with the Area Under the receiver operator Curve (AUC), statistical models are more accurate (88.7 and 84.6% for LR and WofE, respectively) than the PB model (only 69.8%). Nevertheless, in such data-sparse situation, the usual approaches for validation, i.e. comparing observed with predicted data, are insufficient, formal uncertainty analysis (UA) is a means for evaluating the validity and reliability of the model. We then refitted the PB model using a stochastic modification of the infinite slope stability model input scheme using Monte Carlo (MC) method backed with sensitivity analysis (SA). For statistical models, we used an informal Student t-test for estimating the certainty of the predicted probability (PP) at each location. Both modelling outputs independently show a high validity; and whereas the level of confidence in LR and WofE models remained the same after performance re-evaluation, the accuracy of the PB model showed an improvement (AUC = 72%). This result is reasonable and provides a further validation of PB model. So, in urban slope analysis, where PB diagnostic is necessary, statistical and PB modelling may play equally supportive roles in landslide hazard assessment.     

GIS支持下应用PSO-SVM模型预测滑坡易发性

地质灾害不仅造成了严重的经济损失和生态破坏,同时也威胁着人类的生存。地质灾害易发性评价是地质灾害风险评价的基础,以往的研究中重在探讨易发性评价方法的选取,而对于地质灾害易发性指数如何分级的研究较少。为了探索地质灾害易发性评价精度验证与定量的分级标准,以四川省汶川县为例,选取12种广泛应用的地质灾害易发性影响因子,运用信息量模型进行易发性评价,运用成功率曲线检验模型的评价精度,提出历史地质灾害累计比例分段法,并与其他8种分级方法进行对比分析与分级精度验证。研究结果表明,用验证样本成功率曲线与非灾害点样本成功率曲线两种方法检验模型评价精度确定了评价模型预测结果的合理性。历史地质灾害累计比例分段法在易发性分级面积比例精度验证、地质灾害频率比分级精度验证与发生地质灾害位置分级精度验证3种方式中均显现出较好的合理性,在9种分级方法中为最优分级标准。     

Predictive mapping of mosquito distribution based on environmental and anthropogenic factors in Taita Hills,Kenya

Mosquitoes are vectors for numerous pathogens, which are collectively responsible for millions of human deaths each year. As such, it is vital to be able to accurately predict their distributions, particularly in areas where species composition is unknown. Species distribution modeling was used to determine the relationship between environmental, anthropogenic and distance factors on the occurrence of two mosquito genera, Culex Linnaeus and Stegomyia Theobald (syn. Aedes), in the Taita Hills, southeastern Kenya. This study aims to test whether any of the statistical prediction models produced by the Biomod2 package in R can reliably estimate the distributions of mosquitoes in these genera in the Taita Hills; and to examine which factors best explain their presence. Mosquito collections were acquired from 122 locations between January–March 2016 along transects throughout the Taita Hills. Environmental-, anthropogenic- and distance-based geospatial data were acquired from the Taita Hills geo-database, satellite- and aerial imagery and processed in GIS software. The Biomod2 package in R, intended for ensemble forecasting of species distributions, was used to generate predictive models. Slope, human population density, normalized difference vegetation index, distance to roads and elevation best estimated Culex distributions by a generalized additive model with an area under the curve (AUC) value of 0.791. Mean radiation, human population density, normalized difference vegetation index, distance to roads and mean temperature resulted in the highest AUC (0.708) value in a random forest model for Stegomyia distributions. We conclude that in the process towards more detailed species-level maps, with our study results, general assumptions can be made about the distribution areas of Culex and Stegomyia mosquitoes in the Taita Hills and the factors which influence their distribution.     

四川茂县叠溪镇新磨村滑坡特征与成因机制初步研究

长期以来,中国四川省茂县地区受地质、地形条件和构造活动的影响,滑坡等地质灾害频发,给人民的生命财产和公路等基础设施安全带来了巨大的威胁,因此需要对滑坡隐患区域进行有效识别和监测。以时序哨兵1号A、B卫星(Sentinel-1A/1B)影像为数据源,利用时间序列合成孔径雷达干涉测量(interferometric synthetic aperture radar, InSAR)技术对茂县岷江河谷区段的潜在滑坡隐患开展识别监测,对重点区段进行了分析,同时分析探讨了InSAR滑坡监测中不同轨道数据的视线方向形变测量灵敏度差异。从实验结果中成功探测识别出了茂县岷江河谷沟口乡至石大关乡段的20余处滑坡隐患,现场实地考察验证了识别结果的准确性,证明了时序InSAR方法在高山河谷区滑坡隐患识别监测中的有效性。     

Effect of flying altitude,scanning angle and scanning mode on the accuracy of ALS based forest inventory

Airborne laser scanning (ALS) is a widely used technology in the mapping of environment and forests. Data acquisition costs and the accuracy of the forest inventory are closely dependent on some extrinsic parameters of the ALS survey. These parameters have been assessed in numerous studies about a decade ago, but since then ALS devices have developed and it is possible that previous findings do not hold true with newer technology. That is why, the effect of flying altitudes (2000, 2500 or 3000 m), scanning angles (±15° and ±20° off nadir) and scanning modes (single- and multiple pulses in air) with the area-based approach using a Leica ALS70HA-laser scanner was studied here. The study was conducted in a managed pine-dominated forest area in Finland, where eight separate discrete-return ALS data were acquired. The comparison of datasets was based on the bootstrap approach with 5-fold cross validation. Results indicated that the narrower scanning angle (±15° i.e. 30°) led to slightly more accurate estimates of plot volume (RMSE%: 21–24 vs. 22.5–25) and mean height (RMSE%: 8.5–11 vs. 9–12). We also tested the use case where the models are constructed using one data and then applied to other data gathered with different parameters. The most accurate models were identified using the bootstrap approach and applied to different datasets with and without refitting. The bias increased without refitting the models (bias%: volume 0 ± 10, mean height 0 ± 3), but in most cases the results did not differ much in terms of RMSE%. This confirms previous observations that models should only be used for datasets collected under similar data acquisition conditions. We also calculated the proportions of echoes as a function of height for different echo categories. This indicated that the accuracy of the inventory is affected more by the height distribution than the proportions of echo categories.