Mass movements Modeling and Motion Sensitive Zone Management Using Statistical Algorithms in Ojan Chay Basin

Abstract

Slope instabilities are one of the major natural hazards in mountainous areas that cause significant damage to human activities each year. The purpose of this study was to compare the artificial neural network model with the logistic regression model to evaluate the risk of mass movements and amplitude instability and to identify the effective factors in this phenomenon in Ojan Chay basin. The purpose of the results of the statistical models is to determine the regions with potential of occurrence of instability and finally to prepare a hazard zoning map for the study area. And then the layers are prepared. Distribution map of slope instabilities that occurred in the basin was prepared and integrated with the map of factors affecting the movements and slope distribution map of the slope. Distance from fault, land use, distance from village and road, distance from drainage network were calculated in ArcGIS software environment. ROC, Pseudo R square and Chi Square coefficients were used to evaluate the outputs of the models used. The results showed that the percentages of high risk zones in neural network model and logistic regression were 10.32% and 5.06%, respectively, which mainly include the lithologically restricted zones of these areas. . Also the neural network model with ROC value is 0.89 more efficient than logistic regression for zoning the occurrence of domain instabilities; based on zoning using neural network model, respectively, 40.32, 22.15, 18.32, 8.89,10.32 of the area is classified as very low, low, medium, high and very high risk classes

Keywords

• mass movements
• artificial neural network
• ojan chai basin
• geographic information system
• logistic regression model