论文部分内容阅读
由于引起滑坡的诱发因素(降雨)值无法准确获取,应用概率统计思想,刻画雨量值;依据延安黄土滑坡成灾机理研究,确定坡高、坡度、坡向、坡型、岩土体结构和植被覆盖为滑坡成灾基本因素;提出了不确定贝叶斯分类挖掘技术构建区域滑坡危险性评价模型方法,达到提高区域滑坡危险性预测精度的目的.以延安市宝塔区为例,验证了运用该方法进行区域滑坡危险评价的可行性.结果表明:采用不确定贝叶斯分类模型对研究区进行危险性划分,评价结果和实际滑坡发育情况吻合,合理地反映区内滑坡灾害发育的总体特征;不确定贝叶斯分类方法的零阶矩曲线下面积值比朴素贝叶斯方法有所提高,证明该方法科学合理.
Due to the inaccessibility of the induced factors (rainfall) caused by the landslide, the probability value statistics is used to characterize the rainfall value. According to the research on the disaster mechanism of the loess landslide in Yan’an, the slope height, slope, aspect, slope structure, rock and soil structure and vegetation Covering the landslide disaster as the basic factor; proposed an uncertain Bayesian classification mining technology to build regional landslide risk assessment model method, to improve the accuracy of regional landslide risk prediction purposes.Taking Yancheng Baota District as an example, the use of the Method is applied to evaluate the landslide danger.The results show that the Bayesian classification model is used to divide the risk of the study area and the evaluation results are consistent with the actual landslide development and reasonably reflect the overall characteristics of the landslide hazard development in the area. The area under the zero-order moment curve of the uncertain Bayesian classification method is higher than the naive Bayesian method, which proves that the method is scientific and reasonable.