A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS

The aim of this study is to evaluate the landslide hazards at Selangor area, Malaysia, using Geographic Information System (GIS) and Remote Sensing. Landslide locations of the study area were identified from aerial photograph interpretation and field survey. Topographical maps, geological data, and satellite images were collected, processed, and constructed into a spatial database in a GIS platform. The factors chosen that influence landslide occurrence were: slope, aspect, curvature, distance from drainage, lithology, distance from lineaments, land cover, vegetation index, and precipitation distribution. Landslide hazardous areas were analyzed and mapped using the landslide-occurrence factors by frequency ratio and logistic regression models. The results of the analysis were verified using the landslide location data and compared with probability model. The comparison results showed that the frequency ratio model (accuracy is 93.04%) is better in prediction than logistic regression (accuracy is 90.34%) model.

Landslide hazard mapping at Selangor, Malaysia using frequency ratio and logistic regression models

This paper presents recommended methodologies for the quantitative analysis of landslide hazard, vulnerability and risk at different spatial scales (site-specific, local, regional and national), as well as for the verification and validation of the results. The methodologies described focus on the evaluation of the probabilities of occurrence of different landslide types with certain characteristics. Methods used to determine the spatial distribution of landslide intensity, the characterisation of the elements at risk, the assessment of the potential degree of damage and the quantification of the vulnerability of the elements at risk, and those used to perform the quantitative risk analysis are also described. The paper is intended for use by scientists and practising engineers, geologists and other landslide experts.

/pdf/recommendations-for-the-quantitative-analysis-of-landslide-1culjw5db2.pdf

Recommendations for the quantitative analysis of landslide risk

Data collection for landslide susceptibility modeling is often an inhibitive activity. This is one reason why for quite some time landslides have been described and modelled on the basis of spatially distributed values of landslide-related attributes. This paper presents landslide susceptibility analysis in the Klang Valley area, Malaysia, using back-propagation artificial neural network model. A landslide inventory map with a total of 398 landslide locations was constructed using the data from various sources. Out of 398 landslide locations, 318 (80%) of the data taken before the year 2004 was used for training the neural network model and the remaining 80 (20%) locations (post-2004 events) were used for the accuracy assessment purpose. Topographical, geological data and satellite images were collected, processed, and constructed into a spatial database using GIS and image processing. Eleven landslide occurrence related factors were selected as: slope angle, slope aspect, curvature, altitude, distance to roads, distance to rivers, lithology, distance to faults, soil type, landcover and the normalized difference vegetation index value. For calculating the weight of the relative importance of each factor to the landslide occurrence, an artificial neural network method was developed. Each thematic layer's weight was determined by the back-propagation training method and landslide susceptibility indices (LSI) were calculated using the trained back-propagation weights. To assess the factor effects, the weights were calculated three times, using all 11 factors in the first case, then recalculating after removal of those 4 factors that had the smallest weights, and thirdly after removal of the remaining 3 least influential factors. The effect of weights in landslide susceptibility was verified using the landslide location data. It is revealed that all factors have relatively positive effects on the landslide susceptibility maps in the study. The validation results showed sufficient agreement between the computed susceptibility maps and the existing data on landslide areas. The distribution of landslide susceptibility zones derived from ANN shows similar trends as those obtained by applying in GIS-based susceptibility procedures by the same authors (using the frequency ratio and logistic regression method) and indicates that ANN results are better than the earlier method. Among the three cases, the best accuracy (94%) was obtained in the case of the 7 factors weight, whereas 11 factors based weight showed the worst accuracy (91%).

Landslide susceptibility assessment and factor effect analysis: backpropagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling

Landslide susceptibility mapping using frequency ratio, logistic regression, artificial neural networks and their comparison: A case study from Kat landslides (Tokat-Turkey)

Determination and application of the weights for landslide susceptibility mapping using an artificial neural network

This study compares the landslide susceptibility maps from four application models, namely, (1) the bivariate model of the Dempster–Shafer based evidential belief function (EBF); (2) integration of the EBF in the knowledge-based analytical hierarchy process (AHP) as a pairwise comparison model processed by using all available causative factors; (3) integration of the EBF in the knowledge-based AHP as a pairwise comparison model by using high nominated causative factor weights only; and (4) integrated EBF in the logistic regression (LR) as a multivariate model by using nominated causative factor weights only. These models were tested in Pohang and Gyeongju Cities (South Korea) by using the geographic information system GIS platform. In the first step, a landslide inventory map consisting of 296 landslide locations were prepared from various data sources. Then, a total of 15 landslide causative factors (slope angle, slope aspect, curvature, surface roughness, altitude, distance from drainages, stream power index, topographic wetness index, wood age, wood diameter, wood type, forest density, soil thickness, soil texture, and soil drainage) were extracted from the database and then converted into a raster. Final susceptibility maps exhibit close results from the two models. Models 1 and 3 predicted 82.3% and 80% of testing data during the analysis, respectively. Thus, Models 1 and 3 show better performance than LR. These resultant maps can be used to extend the capability of bivariate statistical based model, by finding the relationship between each single conditioning factor and landslide locations, moreover, the proposed ensemble model can be used to show the inter-relationships importance between each conditioning factors, without the need to refer to the multivariate statistic. The research outcome may provide powerful tools for natural hazard assessment and land use planning.

A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process and multivariate statistical logistic regression for landslide susceptibility mapping

Landslide is one of the repeated geological hazards during rainy season, which causes fatalities, damage to property and economic losses in Korea. Landslides are responsible for at least 17% of all fatalities from natural hazards worldwide, and nearly 25% of annual casualties caused by natural hazards in Korea. Due to global climate change, the frequency of landslide occurrence has been increased and subsequently, the losses and damages associated with landslides also have been increased. Therefore, accurate prediction of landslide occurrence, and monitoring and early warning for ground movements are very important tasks to reduce the damages and losses caused by landslides. Various studies on landslide prediction and reduction in landslide damage have been performed and consequently, much of the recent progress has been in these areas. In particular, the application of information and geospatial technologies such as remote sensing and geographic information systems (GIS) has greatly contributed to landslide hazard assessment studies over recent years. In this paper, the recent advances and the state-of-the-art in the essential components of the landslide hazard assessment, such as landslide susceptibility analysis, runout modeling, landslide monitoring and early warning, were reviewed. Especially, this paper focused on the evaluation of the landslide susceptibility using probabilistic approach and physically based method, runout evaluation using volume based model and dynamic model, in situ ground based monitoring techniques, remote sensing techniques for landslide monitoring, and landslide early warning using rainfall and physical thresholds.

Hyuck-Jin Park

Papers

Determination and application of the weights for landslide susceptibility mapping using an artificial neural network

A novel ensemble bivariate statistical evidential belief function with knowledge-based analytical hierarchy process and multivariate statistical logistic regression for landslide susceptibility mapping

Landslide prediction, monitoring and early warning: a concise review of state-of-the-art

Probabilistic analysis of rock slope stability and random properties of discontinuity parameters, Interstate Highway 40, Western North Carolina, USA

Development of a probabilistic approach for rock wedge failure