The spatial prediction of landslide susceptibility applying artificial neural network and logistic regression models: A case study of Inje, Korea

Abstract

Abstract:The aim of this study is to predict landslide susceptibility caused using the spatial analysis by the application of a statistical methodology based on the GIS. Logistic regression models along with arti cial neutral network were applied and validated to analyze landslide susceptibility in Inje, Korea. Landslide occurrence area in the study were identi ed based on interpretations of optical remote sensing data (Aerial photographs) followed by eld surveys. A spatial database considering forest, geophysical, soil and topographic data, was built on the study area using the Geographical Information System (GIS). These factors were analysed using arti cial neural network (ANN) and logistic regression models to generate a landslide susceptibility map. The study validates the landslide susceptibility map by comparing them with landslide occurrence areas. The locations of landslide occurrence were divided randomly into a training set (50%) and a test set (50%). A training set analyse the landslide susceptibility map using the arti cial network along with logistic regression models, and a test set was retained to validate the prediction map. The validation results revealed that the arti cial neural network model (with an accuracy of 80.10%) was better at predicting landslides than the logistic regression model (with an accuracy of 77.05%). Of the weights used in the arti cial neural network model, 'slope' yielded the highest weight value (1.330), and 'aspect' yielded the lowest value (1.000). This research applied two statistical analysis methods in a GIS and compared their results. Based on the ndings, we were able to derive a more e ective method for analyzing landslide susceptibility.

Análisis espacial de susceptibilidad de erosión en una cuenca hidrográfica del trópico húmedo de Costa Rica

“…Estos resultados difieren de otros estudios que utilizaron la misma metodología. Para Ayalew y Yamagishi (2004) el parámetro más relevante en su modelo es la distancia a las carreteras; para Lee (2005) es la pendiente; para Pineda et al (2011) es la morfología de pendientes o tipo de relieve; para Akbari et al (2014) es la pendiente seguida de la distancia a carreteras; para Lee et al (2016) es la pendiente seguida del drenaje del suelo. A diferencia de los estudios anteriores que se focalizan en inventariar exclusivamente los deslizamientos, el presente trabajo incluye todas las posibles formas de erosión y, como consecuencia, los factores intrínsecos del terreno poseen una influencia relativa más baja.…”

“…Comparativamente en el estudio de Dai y Lee (2002) es del 85 %, en Lee (2005) ese mismo cálculo es del 78,6 % y del 80,01 % en Lee et al (2016). Aplicando el método de validación ROC, este es del 76,5 %, siendo en el estudio de Ayalew y Yamagishi, (2004) de un 83,58 %.…”

“…(Enero-Junio, 2018 multivariada (Carrara et al, 1991;Chung et al, 1995), 3) regresión logística binaria (Chung y Fabbri, 1999;Dai y Lee, 2002;Lee, 2005;Ayalew y Yamagishi, 2005;Pineda et al, 2011;Akbari et al, 2014;Lee et al, 2016), 4) probabilidad condicional conjunta mediante el teorema de Bayes (Chung y Fabbri, 1999). Más recientemente se han introducido nuevos enfoques como la evaluación multicriterio espacial (Castellanos y Van Westen, 2007;Pourgashemi et al, 2012;Shahabi y Hashim, 2015), las redes neuronales (Pradhan y Lee, 2010), y la lógica difusa (fuzzy logic) (Pradhan, 2010).…”

Assessment of Landslide-Prone Areas and Their Zonation Using Logistic Regression, LogitBoost, and NaïveBayes Machine-Learning Algorithms

“…Different methods were applied for the landslide location identification such as inventory reports, high-resolution satellite images, and extensive field surveys. In this study, 17 landslide effective factors are used based on the literature review and data availability [6,22,26,[39][40][41][42][43]. These factors include aspect, slope, altitude, maximum curvature, profile curvature, topographic wetness index (TWI), topographic positioning index (TPI), distance from fault, convexity, forest type, forest diameter, forest density, land use and land cover (LULC), lithology, soil, flow accumulation, and mid slope position.…”

A landslide susceptibility map based on spatial scale segmentation: A case study at Zigui-Badong in the Three Gorges Reservoir Area, China

“…Aditian, Kubota and Shinohara used three methods, FR, LR, and ANN, in a study of landslides triggered by heavy rains in the Ambon region of Indonesia: the study showed that the ANN had the best results among these three methods, and was the best method for interpreting the relationship between landslide and LSM factors [3]. Saro et al used two methods, LR and ANN, for the construction of an LSM in Inje City, South Korea, with the results indicating that the accuracy of the ANN was higher than that of the LR model [4]. Hong et al compared the effects of four support vector machine (SVM) models based on different kernel functions in the LSM by taking Luxi City, Jiangxi Province, as a study area.…”