基于逻辑回归模型的汶川地震滑坡危险性评价与检验

Application of logistic regression model on the Wenchuan earthquake triggered landslide hazard mapping and its validation

以2008年5月12日汶川地震区为研究区,基于高分辨率航片与卫星影像开展地震滑坡目视解译,制作了汶川地震滑坡编录图。选择坡度、坡向、高程、与水系距离、与公路距离、与映秀—北川断裂距离、地震烈度、岩性共8个影响因子开展地震滑坡危险性评价工作。滑坡样本采用前期48007处滑坡编录点数据,不滑样本为在基于证据权重模型的滑坡危险性评价结果的低危险区与极低危险区随机选择的48000个点。基于这8个影响因子与逻辑回归模型,建立了汶川地震滑坡危险性索引图。采用这48007个滑坡样本点与汶川地震滑坡最新编录的增加滑坡,分别进行模型的成功率与预测率检验。结果表明,模型成功率为81.739%,预测率达到86.278%。

The main purpose of this paper is to present the use of remote sensing images,GIS technology and Logistic Regression(LR) model for earthquake triggered landslide hazard mapping related to the 2008 Wenchuan earthquake.Landslide polygons were delineated in the study area from interpretation of aerial photographs and satellite images in high resolution,and the inventory of landslides triggered by the earthquake was constructed.Eight factors,including slope angle,slope aspect,elevation,distance from drainages,distance from roads,distance from main faults,seismic intensity and lithology were selected as controlling factors for earthquake triggered landslide hazard mapping.Both landsliding and non-landsliding samples were needed as training data for the LR model.Centroids of the 48007 initial landslide polygons were extracted for landsliding samples and a similar number of 48000 points were selected randomly from the regions of the high and the very high landslide hazard areas using weigh of evidence model as non-landsliding samples.Based on the eight landslide controlling factors,48007+48000 training samples and the LR model and landslide qualitative hazard probability index map were constructed using map overlaying techniques.The validation results show that a success rate of 81.739% exists between the hazard probability index map and the location of the initial 48007 landsliding samples.The predictive rate of 86.278% was obtained from comparison of the additional landslide polygons and the landslides hazard probability index map.