基于粗糙集理论的滑坡易发性评价——以三峡库区秭归县境内为例

Landslide susceptibility assessment based on rough set theory: Taking Zigui County territory in Three Gorges Reservoir for example

以滑坡灾害突出的三峡库区秭归县境内为研究区,利用粗糙集理论将20个初始评价因子进行属性约简至12个核心评价因子,并对其组成的决策表进行知识挖掘获得滑坡与评价因子之间的规则集合。利用知识规则集合对决策表进行分类,得到以斜坡单元为基础的滑坡易发性图。研究结果表明:滑坡易发区面积占研究区总面积的21.7%,主要分布在斜坡结构为顺向坡,地层岩性为软岩、软硬相间岩,以及靠近水系及公路开挖的区域。粗糙集方法的预测精度为87%,其预测能力较KNN算法和Logistic模型的优。粗糙集理论是一种行之有效的区域滑坡易发性评价方法。

To analyze the landslide susceptibility,the rough set theory was used to reduce the redundant information of 20 initial factors to 12 representative factors in Zigui County of the Three Gorges Reservoir.Then the factors were used to extract rules to describe the relationships between landslide conditioning factors and landslide events.Finally,all knowledge rules were used for classification,and landslide susceptibility maps based on slope units were produced.The results show that the susceptibility zone is 21.7%of the total study area,which is primary distributed in the slope structure for consequential slope and lithology of soft rock,and close to water and highway excavation.Compared with validation of landslides,the accuracy of the rough set method is 87%,and so it is superior to KNN method and the Logistic model.The rough set theory provides the effective way for the landslide susceptibility assessment.