论文部分内容阅读
针对斜坡单元大小直接影响地震滑坡敏感性区划结果,论文利用河网密度优选出集水面积阈值,在此基础上生成最优斜坡单元。构建了基于遗传算法的支持向量机敏感性分区预测模型,并实现了宝盛乡地震滑坡敏感性分区。结果显示,在优选出的斜坡单元基础上完成的地震滑坡敏感性分析的精度达到了98.72%。利用优选斜坡单元结合基于遗传算法的支持向量机构建的地震滑坡预测模型是滑坡预测的有效工具,可为防灾减灾提供决策支持。
In view of the fact that the slope unit size directly affects the sensitivity of seismic landslide results, this paper uses the density of river network to optimize the catchment area threshold, and then generates the optimal slope unit. The model of SVM sensitivity partitioning based on genetic algorithm is constructed, and the sensitivity partition of Bao Sheng Xiang earthquake landslide is realized. The results show that the accuracy of the seismic sensitivity analysis of landslides completed based on the preferred slope units reaches 98.72%. The landslide prediction model constructed by using the optimal slope unit and the support vector machine based on genetic algorithm is an effective tool for landslide prediction, which can provide decision support for disaster prevention and mitigation.