节点文献
基于GIS的Logistic回归在区域滑坡空间预测中的应用
Applicatioh of GIS-Based Logistic Regression Modal on Spatial Prognosis Studying of Landslide
【摘要】 巫山新址西区作为试验区,选取地形地貌、岩性特征、地质构造等区域斜坡稳定性影响因子,以MAPGIS地理信息系统为技术支撑,将全区按10m×10m方格划分为14450个单元,每个格网单元作为一个样本,建立Logistic回归模型,进行区域滑坡空间预测。结果表明:以滑坡发生概率0.163为判据,试验区内发生滑坡地段的判对率为72.08%,不发生滑坡地段的判对率为81.44%。根据计算结果可以得到区域斜坡稳定性分区以及进一步的地质灾害风险评价。
【Abstract】 The west area in new Wushan was taken as an experimental region to make spatial prognosis of landslide based on the logistic regression model and GIS, in which the landform, physiognomy, lithological and geological structure are selected as slope stability influence factors. In calculation, the area was compartmentalized into 14450 elements at the size of 10m×10m. Compared with the actual landslide occurrence, the predict accuracy of landslide occurrence is 72.08% and non-occurrence is 81.44%with the criterion of landslide occurrence probability is 0.163. According to the calculated results, the stability of the slope can be identified, and the risk of gnological disasters can be predicted.
【Key words】 GIS; Logistic regression; Landslide; Spatial prognosis;
- 【文献出处】 公路交通科技 ,Journal of Highway and Transportation Research and Development , 编辑部邮箱 ,2005年S1期
- 【分类号】P642.22
- 【被引频次】55
- 【下载频次】724