Maximum Entropy-Based Model of High-Threat Landslide Disaster Distribution in Zhaoqing, China

• DOI: 10.2991/jrarc.2017.7.3.2
• Publication Date: 2017-12-27T13:30:24Z
• Authors: Shaoxiong Yuan; Guangqing Huang; Haixian Xiong; Qinghua Gong; Jun Wang; Jun Chen
• Keywords: Lithology

Landslide disaster that threatened over 100 people in Zhaoqing, China, were taken as samples.Sixteen environmental factors selected, including altitude, slope degree, aspect, lithology, soil texture, normalized differential vegetation index (NDVI), average annual rainfall, distance to developed land, and roads.The Maximum Entropy model was employed for simulation analysis of landslides.The results suggest that: NDVI, rivers, roads, rainfall variance, altitude are the leading affect landslide disasters.Of into consideration, land contributes much 43.6% AUC (area under curve) value distribution model.In fact, this factor became absolute variable even indicating high-threat disasters study area highly correlated with human activities.The closer location more likely a occur.Using MaxEnt model, highthreat Zhaoqing can be favourably simulated.The model's prediction precision reached 0.769 without land; whereas, 0.845 account.