Evaluation of Shannon Entropy and Weights of Evidence Models in Landslide Susceptibility Mapping for the Pithoragarh District of Uttarakhand State, India

Abstract

Landslide susceptibility mapping is considered a useful tool for planning, disaster management, and natural hazard mitigation of a region. Although there are different methods for predicting landslide susceptibility, the bivariate statistical analysis method is considered to be simple and popular. In this study, the main aim is to evaluate the performance of Shannon entropy (SE) and weights of evidence (WOE) statistical models in landslide susceptibility mapping of Pithoragarh district of Uttarakhand state, India. For this purpose, ten landslide affecting factors, namely, slope degree, aspect, curvature, elevation, land cover, slope forming materials, geomorphology (landforms), distance to rivers, distance to roads, and overburden depth were used for the development of landslide susceptibility maps using the SE and WOE methods. Data extracted from the Google Earth images, Aster Digital Elevation Model, and Geological Survey of India report were used for the construction and evaluation of landslide susceptibility models and maps. The landslide data of 91 locations were randomly divided into two parts in the ratio of 70 : 30 using GIS software that is 70% data was used for training the models and 30% data was used for testing and validating the models. Performance of the applied models was evaluated using area under the AUC (area under the curve) ROC (receiver operating characteristics) curve. Results indicated that the WOE model is having better accuracy (AUCWOE = 68.75%) than the SE model (AUCSE = 52.17%) in the development of landslide susceptibility maps. Hence, WOE model can be used for the development of accurate landslide susceptibility maps which can provide useful information to decision maker and policy planner in better development of landslide prone areas.

Landslide Susceptibility Mapping Using GIS and Bivariate Statistical Models in Chemoga Watershade, Ethiopia

“…For the purpose of assessment and validation of landslide susceptibility map, the methodology shows in Fig 2 . Table 1: Type of conditioning factors, format and Source landslide locations was created based on Google Earth imagery digitized into points using GIS 10.4 and eld visits. Though there is no speci c rule for de ning how landslide occurrence will be allocated into training and validation data sets [43], usually research work has been done by using 70% of landslides events as training data sets for preparing landslide susceptibility model and the rest 30% have been used for validation of the output model [44][14] [11]. In this study, 118 (70%) of the landslides were used to training landslide susceptibility models and the remaining 51 (30%) of the landslides were used to model validation, shown in g 3.…”

“…The occurrence of landslides is extremely complex phenomenon which depends upon various factors such as geologic structure, lithological association, topography, rainfall, earthquake, and human activity [10]. One of the most widely used approaches to reduce the landslide damages is preparing a landslide susceptibility mapping using suitable models and selecting the effective conditioning factors [11] [12].…”

“…Weights of evidence model [25] [12][26] [27][28] [29],Shannon entropy model [30] [31][32] [11] [33]. Landslide susceptibility models based on the bivariate frequency and Weights of evidence models [34] and frequency ratio and information value models [35][1] [10].…”

GIS-Based Landslide Susceptibility Mapping Using Frequency Ratio and Shannon Entropy Models in Dejen District, Northwestern Ethiopia

“…Te occurrence of landslides is an extremely complex phenomenon which depends upon various factors such as geologic structure, lithological association, topography, rainfall, earthquake, and human activity [10]. One of the most widely used approaches to reduce the landslide damages is preparing a landslide susceptibility mapping using suitable models and selecting the efective conditioning factors [11,12]. Over the last decades, many studies have made contributions in landslide susceptibility maps using qualitative and quantitative methods.…”

“…Some of the methods include the frequency ratio model [2,4,[13][14][15][16][17][18]. A combination of both FR and SE have been applied for landslide susceptibility mapping [19][20][21][22][23][24], weights of evidence model [12,[25][26][27][28][29], and Shannon entropy model [11,[30][31][32][33]. Landslide susceptibility models are based on the bivariate FR and WOE models [34] and frequency ratio and information value models [1,10,35].…”