In this regard, soil is one of the most important natural resources and human life depends on it. In mountainous regions in the worldwide, landslides are considered as the most costly and damaging natural hazards, causing thousands of deaths every year and property losses billions of dollars (Michel et al. 2014). Landslides are considered to be one of the most widespread geologic hazards in many areas of the world and can be defined as a downslope movement of soil and rock under the influence of gravity (Malamud et al. 2004). Landslide is one of the main natural hazards in Iran that annually makes great economic and personal defect (Pourghasemi et al. 2013). The losses resulting from mass movements until the end of September 2007 have been estimated at 12.7 billion Iranian Rials using 4900 landslide database (Pourghasemi et al. 2012). Iran is one of the countries which in general face with too many landslides. Mountainous features, high tectonic activity, and geological and climatologically varieties make the Iranian plateau capable for the occurrence of various types of landslides, especially in Alborz and Zagros active mountainous belts (Pourghasemi et al. 2012). Due to the heavy losses the landslides and the growing trend of this erosion, landslide susceptibility zonation maps are a reasonable strategy to prevent and control the phenomenon destructive. Landslide …show more content…
2013; Jaffari et al. 2013; Shahabi et al. 2014; Regmi et al. 2014; Youssef et al. 2015; Karimi Sangchini et al. 2015) were applied for LSM. Also, probabilistic models such as Dempster-Shafer, weights-of-evidence, and Certainty Factor (Mohammady et al. 2012; Pourghasemi et al. 2012; Ozdemir & Altural 2013; Devkota et al. 2013; Pourghasemi et al. 2013; Dou et al. 2014; Youssef et al. 2015) were used to map landslide susceptibility in different countries. Recently, in many sciences and engineering investigations, researchers were used some new mathematical approaches such as fuzzy logic (Ercanoglu & Gokceoglu 2002; Kanungo et al. 2008; Pradhan 2010, 2011; Pourghasemi et al. 2012; Regmi et al. 2013; Zhu et al. 2014(, artificial neural networks (Ermini et al. 2005; Kanungo et al. 2006; Melchiorre et al. 2008; Yilmaz 2009, 2010; Pradhan & lee 2010; Poudyal et al. 2010; Pradhan & Buchroithner 2010; Zare et al. 2012; Tien Bui et al. 2012; Salarian et al. 2014; Conforti et al. 2014), support vector machines (Yao et al. 2008; Tien Bui et al. 2012; Pourghasemi et al., 2013; Kavzoglu et al. 2014; Peng et al. 2014; Hong et al. 2015), neuro-fuzzy (Vahidnia et al. 2010; Sezer et al. 2011; Oh & Pradhan. 2011; Pradhan 2012; Tien Bui et al. 2012), and data mining techniques such as random forest, boosted regression tree, classification and regression