Spatial Prediction Modelling of Landslide Susceptibility Assessment Using Statistical Information Value Model—A Case Study of Dharchula, Pithoragarh District Uttarakhand, India

A landslide is a hazardous phenomenon that occurs when the particulate matter of the earth's surface shifts towards the gravitational pull of the earth, which can lead to loss of life and damage to the earth's resources. Therefore, it is crucial to monitor and assess such events to minimize their impact on human life and the environment. The main objective of this paper is to identify and map areas susceptible to landslides in a particular region, using a combination of Elevation and LANDSAT 8 data through the Statistical Information Value Model (SIVM). The classification of the identified zones has been done based on the Natural Jenks algorithm, which categorizes them into five equal classes, namely Very High, High, Moderate, Low, and Very Low. The analysis has been carried out using the ArcGIS-10.3 software. To ensure the accuracy of the results, the landslide signatures extracted from Google Earth have been used in two steps. Firstly, Model Training Areas have been identified for calibration, representing 70% of the total study area. Secondly, Model Testing Areas have been identified for validation, representing the remaining 30% of the study area. This approach helps in improving the accuracy of the landslide susceptibility mapping and ensures that the results are reliable and credible. The study area has been analyzed using various statistical techniques, including correlation analysis and logistic regression analysis. The results have been used to develop a predictive model for identifying areas susceptible to landslides. The model's performance has been evaluated using various metrics, such as accuracy, precision, and recall. The results indicate that the proposed model is effective in identifying areas prone to landslides, and the accuracy of the model is satisfactory. This study has provided valuable insights into identifying and mapping areas susceptible to landslides using a combination of remote sensing and statistical techniques. The proposed model can be used to develop early warning systems and mitigate the impact of landslides on human life and the environment.