Validation of an artificial neural network model for landslide susceptibility mapping

The aim of this study was to validate an artificial neural network model at Youngin, Janghung, and Boeun, Korea, using the geographic information system (GIS). The factors that influence landslide occurrence, such as the slope, aspect, curvature, and geomorphology of topography, the type, material, drainage, and effective thickness of soil, the type, diameter, age, and density of forest, distance from lineament, and land cover were either calculated or extracted from the spatial database and Landsat TM satellite images. Landslide susceptibility was analyzed using the landslide occurrence factors provided by the artificial neural network model. The landslide susceptibility analysis results were validated and cross-validated using the landslide locations as study areas. For this purpose, weights for each study area were calculated by the artificial neural network model. Among the nine cases, the best accuracy (81.36%) was obtained in the case of the Boeun-based Janghung weight, whereas the Janghung-based Youngin weight showed the worst accuracy (71.72%).     

Ensemble-based landslide susceptibility maps in Jinbu area, Korea

Ensemble techniques were developed, applied and validated for the analysis of landslide susceptibility in Jinbu area, Korea using the geographic information system (GIS). Landslide-occurrence areas were detected in the study by interpreting aerial photographs and field survey data. Landslide locations were randomly selected in a 70/30 ratio for training and validation of the models, respectively. Topography, geology, soil and forest databases were also constructed. Maps relevant to landslide occurrence were assembled in a spatial database. Using the constructed spatial database, 17 landslide-related factors were extracted. The relationships between the detected landslide locations and the factors were identified and quantified by frequency ratio, weight of evidence, logistic regression and artificial neural network models and their ensemble models. The relationships were used as factor ratings in the overlay analysis to create landslide susceptibility indexes and maps. Then, the four landslide susceptibility maps were used as new input factors and integrated using the frequency ratio, weight of evidence, logistic regression and artificial neural network models as ensemble methods to make better susceptibility maps. All of the susceptibility maps were validated by comparison with known landslide locations that were not used directly in the analysis. As the result, the ensemble-based landslide susceptibility map that used the new landslide-related input factor maps showed better accuracy (87.11% in frequency ratio, 83.14% in weight of evidence, 87.79% in logistic regression and 84.54% in artificial neural network) than the individual landslide susceptibility maps (84.94% in frequency ratio, 82.82% in weight of evidence, 87.72% in logistic regression and 81.44% in artificial neural network). All accuracy assessments showed overall satisfactory agreement of more than 80%. The ensemble model was found to be more effective in terms of prediction accuracy than the individual model.     

The Application of Artificial Neural Networks to Landslide Susceptibility Mapping at Janghung, Korea

The purpose of this study was to develop techniques for landslide susceptibility using artificial neural networks and then to apply these to the selected study area at Janghung in Korea. Landslide locations were identified from interpretation of satellite images and field survey data, and a spatial database of the topography, soil, forest, and land use. Thirteen landslide-related factors were extracted from the spatial database. These factors were then used with an artificial neural network to analyze landslide susceptibility. Each factor's weight was determined by the back-propagation training method. Five different training sets were applied to analyze and verify the effect of training. Then the landslide susceptibility indices were calculated using the back-propagation weights, and susceptibility maps were constructed from Geographic Information System (GIS) data for the five cases. Landslide locations were used to verify results of the landslide susceptibility maps and to compare them. The artificial neural network proved to be an effective tool for analyzing landslide susceptibility.     

Regional landslide susceptibility analysis using back-propagation neural network model at Cameron Highland,Malaysia

This paper presents landslide susceptibility analysis around the Cameron Highlands area, Malaysia using a geographic information system (GIS) and remote sensing techniques. Landslide locations were identified in the study area from interpretation of aerial photographs and field surveys. Topographical, geological data and satellite images were collected, processed, and constructed into a spatial database using GIS and image processing. Ten landslide occurrence factors were selected as: topographic slope, topographic aspect, topographic curvature and distance from drainage, lithology and distance from lineament, soil type, rainfall, land cover from SPOT 5 satellite images, and the vegetation index value from SPOT 5 satellite image. These factors were analyzed using an advanced artificial neural network model to generate the landslide susceptibility map. Each factor’s weight was determined by the back-propagation training method. Then, the landslide susceptibility indices were calculated using the trained back-propagation weights, and finally, the landslide susceptibility map was generated using GIS tools. The results of the neural network model suggest that the effect of topographic slope has the highest weight value (0.205) which has more than two times among the other factors, followed by the distance from drainage (0.141) and then lithology (0.117). Landslide locations were used to validate the results of the landslide susceptibility map, and the verification results showed 83% accuracy. The validation results showed sufficient agreement between the computed susceptibility map and the existing data on landslide areas.     

Quantitative landslide susceptibility mapping at Pemalang area,Indonesia

For quantitative landslide susceptibility mapping, this study applied and verified a frequency ratio, logistic regression, and artificial neural network models to Pemalang area, Indonesia, using a Geographic Information System (GIS). Landslide locations were identified in the study area from interpretation of aerial photographs, satellite imagery, and field surveys; a spatial database was constructed from topographic and geological maps. The factors that influence landslide occurrence, such as slope gradient, slope aspect, curvature of topography, and distance from stream, were calculated from the topographic database. Lithology was extracted and calculated from geologic database. Using these factors, landslide susceptibility indexes were calculated by frequency ratio, logistic regression, and artificial neural network models. Then the landslide susceptibility maps were verified and compared with known landslide locations. The logistic regression model (accuracy 87.36%) had higher prediction accuracy than the frequency ratio (85.60%) and artificial neural network (81.70%) models. The models can be used to reduce hazards associated with landslides and to land-use planning.     

基于GIS与WOE-BP模型的滑坡易发性评价

区域滑坡易发性研究对地质灾害风险管理具有重要意义.以往研究中,将多元统计模型与机器学习方法相结合用于滑坡易发性评价的研究较少.以三峡库区万州区为例,首先选取9种指标因子（坡度、坡向、剖面曲率、地表纹理、地层岩性、斜坡结构、地质构造、水系分布及土地利用类型）作为滑坡易发性评价指标.基于证据权模型（weights of evidence,WOE）计算得到的对比度和滑坡面积比与分级面积比的相对大小,对各指标因子进行状态分级;再利用粒子群法优化的BP神经网络模型（PSO-BP）得到各指标因子权重.综合两种模型确定的状态分级权重和指标因子权重（WOE-BP）计算滑坡易发性指数（landslide susceptibility index,LSI）,基于GIS平台得到全区滑坡易发性分区图.结果表明:水系、地层岩性和地质构造是影响万州区滑坡发育的主要指标因子;WOE-BP模型的预测精度为80.8%,优于WOE模型的73.1%和BP神经网络模型的71.6%,可为定量计算指标因子权重和优化滑坡易发性评价提供有效途径.      

Landslide susceptibility analysis and its verification using likelihood ratio, logistic regression, and artificial neural network models: case study of Youngin, Korea

The likelihood ratio, logistic regression, and artificial neural networks models are applied and verified for analysis of landslide susceptibility in Youngin, Korea, using the geographic information system. From a spatial database containing such data as landslide location, topography, soil, forest, geology, and land use, the 14 landslide-related factors were calculated or extracted. Using these factors, landslide susceptibility indexes were calculated by likelihood ratio, logistic regression, and artificial neural network models. Before the calculation, the study area was divided into two sides (west and east) of equal area, for verification of the models. Thus, the west side was used to assess the landslide susceptibility, and the east side was used to verify the derived susceptibility. The results of the landslide susceptibility analysis were verified using success and prediction rates. The verification results showed satisfactory agreement between the susceptibility map and the existing data on landslide locations.     

A subjective and objective integrated weighting method for landslides susceptibility mapping based on GIS

The purpose of this study is to present a weighting method, integrating subjective weight with objective weight, for landslides susceptibility mapping based on geographical information system (GIS). First, the landslide inventory, aspect, slope, proximity to streams of drainage network, proximity to railway, proximity to road, topography, elevation, lithology, tectonic activity and annual precipitation, including their subclasses, were taken as independent landslide causal factors. Second, objective weights of the causal factors were calculated according to the landslide area density based on entropy weighting method, and key factors were selected according to the rank of the objective weights. Third, trapezoidal fuzzy number weighting approach was used to assess the sub-classes of each key factor. Finally, a case study was carried out in Guizhou province, China. A landslide susceptibility map was created using weighted linear combination model based on GIS. Using a predicted map of probability, the study area was classified into four categories of landslide susceptibility: low, moderate, moderate-high, and high.     

Use of an artificial neural network for analysis of the susceptibility to landslides at Boun,Korea

The purpose of this study was to develop landslide susceptibility analysis techniques using artificial neural networks and to apply the resulting techniques to the study area of Boun in Korea. Landslide locations were identified in the study area from interpretation of aerial photographs and field survey data. A spatial database of the topography, soil type, timber cover, geology, and land cover was constructed and the landslide-related factors were extracted from the spatial database. Using these factors, the susceptibility to landslides was analyzed by artificial neural network methods. The results of the landslide susceptibility maps were compared and verified using known landslide locations at another area, Yongin, in Korea. A Geographic Information System (GIS) was used to analyze efficiently the vast amount of data and an artificial neural network turned out to be an effective tool to analyze the landslide susceptibility.     

Landslide susceptibility maps comparing frequency ratio and artificial neural networks: a case study from the Nepal Himalaya

This study considers landslide susceptibility mapping by means of frequency ratio and artificial neural network approaches using geographic information system (GIS) techniques as a basic analysis tool. The selected study area was that of the Panchthar district, Nepal. GIS was used for the management and manipulation of spatial data. Landslide locations were identified from field survey and aerial photographic interpretation was used for location of lineaments. Ten factors in total are related to the occurrence of landslides. Based on the same set of factors, landslide susceptibility maps were produced from frequency ratio and neural network models, and were then compared and evaluated. The weights of each factor were determined using the back-propagation training method. Landslide susceptibility maps were produced from frequency ratio and neural network models, and they were then compared by means of their checking. The landslide location data were used for checking the results with the landslide susceptibility maps. The accuracy of the landslide susceptibility maps produced by the frequency ratio and neural networks is 82.21 and 78.25%, respectively.     

Landslide susceptibility zonation using statistical and machine learning approaches in Northern Lecco,Italy

This study deals with landslide susceptibility mapping in the northern part of Lecco Province, Lombardy Region, Italy. In so doing, a valid landslide inventory map and thirteen predisposing factors (including elevation, slope aspect, slope degree, plan curvature, profile curvature, distance to waterway, distance to road, distance to fault, soil type, land use, lithology, stream power index, and topographic wetness index) form the spatial database within geographic information system. The used predictive models comprise a bivariate statistical approach called frequency ratio (FR) and two machine learning tools, namely multilayer perceptron neural network (MLPNN) and adaptive neuro-fuzzy inference system (ANFIS). These models first use landslide and non-landslide records for comprehending the relationship between the landslide occurrence and predisposing factors. Then, landslide susceptibility values are predicted for the whole area. The accuracy of the produced susceptibility maps is measured using area under the curve (AUC) index, according to which, the MLPNN (AUC?=?0.916) presented the most accurate map, followed by the ANFIS (AUC?=?0.889) and FR (AUC?=?0.888). Visual interpretation of the susceptibility maps, FR-based correlation analysis, as well as the importance assessment of predisposing factors, all indicated the significant contribution of the road networks to the crucial susceptibility of landslide. Lastly, an explicit predictive formula is extracted from the implemented MLPNN model for a convenient approximation of landslide susceptibility value.

     

遗传算法优化BP网络在滑坡灾害预测中的应用研究

在陕西省宝鸡市附近长寿沟地区滑坡详细调查和遥感解译的基础上,完成了1∶10000滑坡编目图。通过使用GIS的水文分析功能,运用正反DEM技术,将长寿沟地区划分为216个自然斜坡单元,其中包括123个滑坡单元和93个未发生滑坡单元,分析滑坡发生与坡高、坡度、坡向、坡形、人类工程活动和水文地质条件影响因子之间的统计规律。利用经遗传算法优化后的BP神经网络对80个滑坡样本和40个未滑坡样本进行训练学习,然后再利用训练好的网络对预测样本进行评价分析。结果表明:43个已滑坡单元中只有3个被误判为无滑坡,正确率为9302%,53个未滑坡单元中有10个被预测为滑坡,正确率为8113%,总体正确率为8646%。通过对被预测为滑坡的10个斜坡单元进行分析,发现这些单元在坡形、坡高等影响因素的组合上已经具备了发生滑坡的条件,虽然目前没有发生滑坡,但作为潜在的滑坡危险区,可以为滑坡灾害预测预报和防灾减灾工作提供参考。     

Combining landslide susceptibility maps obtained from frequency ratio,logistic regression,and artificial neural network models using ASTER images and GIS

Landslide-related factors were extracted from Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) images, and integrated techniques were developed, applied, and verified for the analysis of landslide susceptibility in Boun, Korea, using a geographic information system (GIS). Digital elevation model (DEM), lineament, normalized difference vegetation index (NDVI), and land-cover factors were extracted from the ASTER images for analysis. Slope, aspect, and curvature were calculated from a DEM topographic database. Using the constructed spatial database, the relationships between the detected landslide locations and six related factors were identified and quantified using frequency ratio (FR), logistic regression (LR), and artificial neural network (ANN) models. These relationships were used as factor ratings in an overlay analysis to create landslide susceptibility indices and maps. Three landslide susceptibility maps were then combined and applied as new input factors in the FR, LR, and ANN models to make improved susceptibility maps. All of the susceptibility maps were verified by comparison with known landslide locations not used for training the models. The combined landslide susceptibility maps created using three landslide-related input factors showed improved accuracy (87.00% in FR, 88.21% in LR, and 86.51% in ANN models) compared to the individual landslide susceptibility maps (84.34% in FR, 85.40% in LR, and 74.29% in ANN models) generated using the six factors from the ASTER images.     

Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network models

This paper summarizes findings of landslide hazard analysis on Penang Island, Malaysia, using frequency ratio, logistic regression, and artificial neural network models with the aid of GIS tools and remote sensing data. Landslide locations were identified and an inventory map was constructed by trained geomorphologists using photo-interpretation from archived aerial photographs supported by field surveys. A SPOT 5 satellite pan sharpened image acquired in January 2005 was used for land-cover classification supported by a topographic map. The above digitally processed images were subsequently combined in a GIS with ancillary data, for example topographical (slope, aspect, curvature, drainage), geological (litho types and lineaments), soil types, and normalized difference vegetation index (NDVI) data, and used to construct a spatial database using GIS and image processing. Three landslide hazard maps were constructed on the basis of landslide inventories and thematic layers, using frequency ratio, logistic regression, and artificial neural network models. Further, each thematic layer’s weight was determined by the back-propagation training method and landslide hazard indices were calculated using the trained back-propagation weights. The results of the analysis were verified and compared using the landslide location data and the accuracy observed was 86.41, 89.59, and 83.55% for frequency ratio, logistic regression, and artificial neural network models, respectively. On the basis of the higher percentages of landslide bodies predicted in very highly hazardous and highly hazardous zones, the results obtained by use of the logistic regression model were slightly more accurate than those from the other models used for landslide hazard analysis. The results from the neural network model suggest the effect of topographic slope is the highest and most important factor with weightage value (1.0), which is more than twice that of the other factors, followed by the NDVI (0.52), and then precipitation (0.42). Further, the results revealed that distance from lineament has the lowest weightage, with a value of 0. This shows that in the study area, fault lines and structural features do not contribute much to landslide triggering.     

Comparing data-driven landslide susceptibility models based on participatory landslide inventory mapping in Purwosari area,Yogyakarta, Java

There are different approaches and techniques for landslide susceptibility mapping. However, no agreement has been reached in both the procedure and the use of specific controlling factors employed in the landslide susceptibility mapping. Each model has its own assumption, and the result may differ from place to place. Different landslide controlling factors and the completeness of landslide inventory may also affect the different result. Incomplete landslide inventory may produce significance error in the interpretation of the relationship between landslide and controlling factor. Comparing landslide susceptibility models using complete inventory is essential in order to identify the most realistic landslide susceptibility approach applied typically in the tropical region Indonesia. Purwosari area, Java, which has total 182 landslides occurred from 1979 to 2011, was selected as study area to evaluate three data-driven landslide susceptibility models, i.e., weight of evidence, logistic regression, and artificial neural network. Landslide in the study area is usually affected by rainfall and anthropogenic activities. The landslide typology consists of shallow translational and rotational slide. The elevation, slope, aspect, plan curvature, profile curvature, stream power index, topographic wetness index, distance to river, land use, and distance to road were selected as landslide controlling factors for the analysis. Considering the accuracy and the precision evaluations, the weight of evidence represents considerably the most realistic prediction capacities (79%) when comparing with the logistic regression (72%) and artificial neural network (71%). The linear model shows more powerful result than the nonlinear models because it fits to the area where complete landslide inventory is available, the landscape is not varied, and the occurence of landslide is evenly distributed to the class of controlling factor.     

A novel hybrid integration model using support vector machines and random subspace for weather-triggered landslide susceptibility assessment in the Wuning area (China)

This study proposed a hybrid modeling approach using two methods, support vector machines and random subspace, to create a novel model named random subspace-based support vector machines (RSSVM) for assessing landslide susceptibility. The newly developed model was then tested in the Wuning area, China, to produce a landslide susceptibility map. With the purpose of achieving the objective of the study, a spatial dataset was initially constructed that includes a landslide inventory map consisting of 445 landslide regions. Then, various landslide-influencing factors were defined, including slope angle, aspect, altitude, topographic wetness index, stream power index, sediment transport index, soil, lithology, normalized difference vegetation index, land use, rainfall, distance to roads, distance to rivers, and distance to faults. Next, the result of the RSSVM model was validated using statistical index-based evaluations and the receiver operating characteristic curve approach. Then, to evaluate the performance of the suggested RSSVM model, a comparison analysis was performed to other existing approaches such as artificial neural network, Naïve Bayes (NB) and support vector machine (SVM). In general, the performance of the RSSVM model was better than the other models for spatial prediction of landslide susceptibility. The AUC results of the applied models are as follows: RSSVM (AUC = 0.857), followed by MLP (AUC = 0.823), SVM (AUC = 0.814) and NB (AUC = 0.783). The present study indicates that RSSVM can be used for landslide susceptibility evaluation, and the results are very useful for local governments and people living in the Wuning area.     

Prediction of groundwater inrush into coal mines from aquifers underlying the coal seams in China: vulnerability index method and its construction

Groundwater inrushes often occur in the coal mines of China. One of the water sources is the aquifers underlying the coal seams. Because such a water hazard is affected by many factors, data collected from various sources need to be evaluated to predict its occurrence. This paper introduces an innovative approach in which the water inrush risk is represented by the vulnerability index. This method combines the geographic information system and the artificial neural network. The artificial neural network is used to estimate the weight of each factor. Unlike the traditional prediction method in which two controlling factors are often evaluated without regard to their relative importance, this new approach incorporates multi-factors and describes the non-linear dynamical processes.     

Assessing landslide exposure in areas with limited landslide information

Landslide risk assessment is often a difficult task due to the lack of temporal data on landslides and triggering events (frequency), run-out distance, landslide magnitude and vulnerability. The probability of occurrence of landslides is often very difficult to predict, as well as the expected magnitude of events, due to the limited data availability on past landslide activity. In this paper, a qualitative procedure for assessing the exposure of elements at risk is presented for an area of the Apulia region (Italy) where no temporal information on landslide occurrence is available. Given these limitations in data availability, it was not possible to produce a reliable landslide hazard map and, consequently, a risk map. The qualitative analysis was carried out using the spatial multi-criteria evaluation method in a global information system. A landslide susceptibility composite index map and four asset index maps (physical, social, economic and environmental) were generated separately through a hierarchical procedure of standardising and weighting. The four asset index maps were combined in order to obtain a qualitative weighted assets map, which, combined with the landslide susceptibility composite index map, has provided the final qualitative landslide exposure map. The resulting map represents the spatial distribution of the exposure level in the study area; this information could be used in a preliminary stage of regional planning. In order to demonstrate how such an exposure map could be used in a basic risk assessment, a quantification of the economic losses at municipal level was carried out, and the temporal probability of landslides was estimated, on the basis of the expert knowledge. Although the proposed methodology for the exposure assessment did not consider the landslide run-out and vulnerability quantification, the results obtained allow to rank the municipalities in terms of increasing exposure and risk level and, consequently, to identify the priorities for designing appropriate landslide risk mitigation plans.     

Landslide susceptibility zonation method based on C5.0 decision tree and K-means cluster algorithms to improve the efficiency of risk management

Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments,but most studies use GIS-based classification methods to conduct susceptibility zonation.This study presents a machine learning approach based on the C5.0 decision tree(DT)model and the K-means cluster algorithm to produce a regional landslide susceptibility map.Yanchang County,a typical landslide-prone area located in northwestern China,was taken as the area of interest to introduce the proposed application procedure.A landslide inventory containing 82 landslides was prepared and subse-quently randomly partitioned into two subsets:training data(70％landslide pixels)and validation data(30％landslide pixels).Fourteen landslide influencing factors were considered in the input dataset and were used to calculate the landslide occurrence probability based on the C5.0 decision tree model.Susceptibility zonation was implemented according to the cut-off values calculated by the K-means clus-ter algorithm.The validation results of the model performance analysis showed that the AUC(area under the receiver operating characteristic(ROC)curve)of the proposed model was the highest,reaching 0.88,compared with traditional models(support vector machine(SVM)=0.85,Bayesian network(BN)=0.81,frequency ratio(FR)=0.75,weight of evidence(WOE)=0.76).The landslide frequency ratio and fre-quency density of the high susceptibility zones were 6.76/km2 and 0.88/km2,respectively,which were much higher than those of the low susceptibility zones.The top 20％interval of landslide occurrence probability contained 89％of the historical landslides but only accounted for 10.3％of the total area.Our results indicate that the distribution of high susceptibility zones was more focused without contain-ing more"stable"pixels.Therefore,the obtained susceptibility map is suitable for application to landslide risk management practices.     

Landslide occurrence and its relation with terrain factors in the Siwalik Hills,Nepal: case study of susceptibility assessment in three basins

Landslides in the three studied basins of the Siwalik Hills are not random in distribution; they tend to cluster in certain areas implying the control of certain in situ factors or their combination. Landslide controlling in situ factors were reviewed and analyzed from maps, aerial photos and imageries using GIS. Chi square analysis was carried out to test the significance of landslide distribution vis-à-vis in situ factors. Slope gradient and relative relief were consistently significant in landslide distribution. Geology, dip-topography relation, land use and land cover, and vegetation conditions appeared important in landslide occurrence in all three basins either in terms of area or count in any two basins. Slope aspect and altitude tested significant for landslide occurrence in at least two basins. However, upslope flow contributing area, drainage density and distance to lineament were found insignificant in all three basins. In situ factors that tested significant in any two basins were used for landslide susceptibility analysis using a bivariate statistical approach. The distribution of landslides strongly correlates with susceptibility indices. With in situ factors, landslide susceptibility had good correlation with slope gradient and relative relief. Incorporating calculated factor weight values from one basin to the other two basins, proxy susceptibility index maps were also prepared. A moderate to good positive correlation appeared between them implying certain range of confidence for replicating the result for whole of the Siwalik Hills. Slope gradient and relative relief can be used as proxy indicators of landslide susceptible areas in the Siwalik Hills.