考虑变形状态动态切换的阶跃型滑坡位移区间预测方法

Displacement interval prediction method for step-like landslides considering deformation state dynamic switching

为解决传统阶跃型滑坡位移预测模型研究中存在的突变状态预测结果滞后和结果可靠性不明确等典型问题,提出一种新型滑坡位移区间预测改进方法。首先,采用SOM网络和K均值聚类相结合的方法,将阶跃型滑坡的变形状态划分为变形稳定状态与变形突变状态两类。然后,在综合运用工程地质类比法和自适应综合采样算法扩展突变状态样本的基础上,采用随机森林算法建立能够自动识别滑坡变形状态的集合分类器。最终,基于Bootstrap-KELM-BPNN模型,构建考虑滑坡变形状态动态转换的位移区间预测框架,实现滑坡位移的动态区间预测。以三峡库区内典型阶跃型滑坡--白水河滑坡为例,选取XD01监测点在2006年6月~2016年12月期间的数据进行研究,验证该方法的有效性、准确性和可靠性。

To overcome the drawbacks of previous displacement prediction models for step-like landslides such as the hysteresis and the unclear reliability of the prediction results of mutational displacements,a new hybrid prediction method of landslide displacement intervals is proposed.Firstly,the deformation of step-like landslides is divided into steady and mutational states by the combination of SOM network and K-means clustering.Secondly,on the basis of expanding the mutational state samples through the comprehensive application of the engineering geology analogy method and the adaptive synthetic sampling algorithm,an ensemble classifier for recognizing the landslide deformation states automatically is established adopting the random forest algorithm.Finally,an interval prediction framework considering the dynamic switching of landslide deformation states is constructed based on the Bootstrap-KELM-BPNN model.Taking Baishuihe landslide,a typical step-like landslide in the Three Gorges reservoir area,as an example,the dataset of XD01 monitoring point from June,2006 to December,2016 is explored to verify the effectiveness,accuracy and reliability of the proposed method.