Data Mining Approaches for Landslide Susceptibility Mapping in Umyeonsan, Seoul, South Korea

Abstract

The application of data mining models has become increasingly popular in recent years in assessments of a variety of natural hazards such as landslides and floods. Data mining techniques are useful for understanding the relationships between events and their influencing variables. Because landslides are influenced by a combination of factors including geomorphological and meteorological factors, data mining techniques are helpful in elucidating the mechanisms by which these complex factors affect landslide events. In this study, spatial data mining approaches based on data on landslide locations in the geographic information system environment were investigated. The topographical factors of slope, aspect, curvature, topographic wetness index, stream power index, slope length factor, standardized height, valley depth, and downslope distance gradient were determined using topographical maps. Additional soil and forest variables using information obtained from national soil and forest maps were also investigated. A total of 17 variables affecting the frequency of landslide occurrence were selected to construct a spatial database, and support vector machine (SVM) and artificial neural network (ANN) models were applied to predict landslide susceptibility from the selected factors. In the SVM model, linear, polynomial, radial base function, and sigmoid kernels were applied in sequence; the model yielded 72.41%, 72.83%, 77.17% and 72.79% accuracy, respectively. The ANN model yielded a validity accuracy of 78.41%. The results of this study are useful in guiding effective strategies for the prevention and management of landslides in urban areas.

Optimized Conditioning Factors Using Machine Learning Techniques for Groundwater Potential Mapping

“…The Receiver Operating Characteristics (ROC) curve [58] is mainly used for assessing accuracy. It has been widely used in works involving land cover change, disease risk and species distribution studies [59], landslide susceptibility mapping [19,60], groundwater potential mapping [6], and for assessing groundwater vulnerability [61]. In this work, ROC assesses the spatial coincidence between the true event and predicts the probability of the model [59].…”

Editorial for Special Issue: “Application of Artificial Neural Networks in Geoinformatics”

“…The first and second papers, authored by Lee, S., Lee, M., Jung, H. [1] and Oh, H., Lee, S. [2], applied GIS and various machine learning algorithms such as artificial neural networks, support vector machines, and boosted tress to map landslide susceptibility. The third paper, authored by Lee, S., Lee, S., Song, W., Lee, M. [3], applied GIS with artificial neural networks to map potential marten and leopard habitats.…”

The Influence of Different Knowledge-Driven Methods on Landslide Susceptibility Mapping: A Case Study in the Changbai Mountain Area, Northeast China

“…In bivariate statistical analysis, the weights of the landslide conditioning factors are assigned based on landslide density using different methods-including frequency ratio (FR) [13,15,[20][21][22], the information content model (ICM) [23,24], weight of evidence (WoE) [16], certainty factors (CF) [25], favorability functions (FF) [26], and the likelihood ratio model (LRM) [27]. The multivariate statistical methods evaluate the combined relationship between a dependent variable (landslide occurrence) and a series of independent variables (landslide controlling factors), and the most popular methods to analyze the resulting matrix include logistic regression (LR) [6,13,[28][29][30][31][32][33], discriminant analysis (DA) [34,35], random forest (RF) [36][37][38] and active learning statistical analysis, such as the artificial neural networks (ANNs) [3,6,[39][40][41][42].Physically based methods, such as deterministic techniques, are based on mathematical modeling of the physical mechanisms controlling slope failure [43][44][45][46][47][48][49]. However, it is reported that the methods are only applicable over large areas when the geological and geomorphological conditions are fairly homogeneous and the landslide types are simple [17].Moreover, several studies have used two or more models to produce landslide susceptibi...…”