近年来,随着新理论、新技术得发展,提出了许多新模型和方法应用于滑坡区域危险性评价中。支持向量机(support vector m ach ine,SVM)是新一代的学习算法,已有前人利用SVM应用于滑坡灾害预测中。然而大多只是利用了SVM的两分类算法,得到...近年来,随着新理论、新技术得发展,提出了许多新模型和方法应用于滑坡区域危险性评价中。支持向量机(support vector m ach ine,SVM)是新一代的学习算法,已有前人利用SVM应用于滑坡灾害预测中。然而大多只是利用了SVM的两分类算法,得到的结果只有稳定不稳定两种,这对滑坡区域评价来说是远远不够的。本文尝试利用SVM的多类分类算法进行滑坡危险性区域评价,取得了较好的结果。展开更多
Landslides are recurrent geological phenomena on Earth that cause heavy casualties and property losses annually.In this study,we use the V_(p)-k stacking and nonlinear waveform inversion methods of high-frequency rece...Landslides are recurrent geological phenomena on Earth that cause heavy casualties and property losses annually.In this study,we use the V_(p)-k stacking and nonlinear waveform inversion methods of high-frequency receiver functions extracted from local earthquakes,to sequentially invert Poisson’s ratios and S-wave velocities of the Quaternary Xishancun landslide,which is composed of three segments,i.e.,h1,h2,and h3 from bottom to top.Our results show that Poisson’s ratio values are generally higher than 0.33 and that the S-wave velocities vary from 0.1 to 0.9 km s^(-1).High Poisson’s ratios(>0.44)are mainly distributed in the juncture regions between different segments,as well as the western edge of h2.These zones show significant variation in landslide thickness and are potentially hazardous areas.Low velocities of 0.05–0.2 km s^(-1)with thicknesses of 10–30m are widely observed in the lower layer of the landslide.The high Poisson’s ratios and low-velocity layer may be related to water-rich materials in these areas.Our study suggests that the high-frequency receiver functions from local earthquakes can be used to delineate geotechnical structures,which is valuable for landslide stability analysis and hazard mitigation.展开更多
文摘近年来,随着新理论、新技术得发展,提出了许多新模型和方法应用于滑坡区域危险性评价中。支持向量机(support vector m ach ine,SVM)是新一代的学习算法,已有前人利用SVM应用于滑坡灾害预测中。然而大多只是利用了SVM的两分类算法,得到的结果只有稳定不稳定两种,这对滑坡区域评价来说是远远不够的。本文尝试利用SVM的多类分类算法进行滑坡危险性区域评价,取得了较好的结果。
基金supported by the Strategic Priority Research Program(B)of Chinese Academy of Sciences(Grant No.XDB41000000)the National Natural Science Foundation of China(Grant Nos.41604056,41661164035)。
文摘Landslides are recurrent geological phenomena on Earth that cause heavy casualties and property losses annually.In this study,we use the V_(p)-k stacking and nonlinear waveform inversion methods of high-frequency receiver functions extracted from local earthquakes,to sequentially invert Poisson’s ratios and S-wave velocities of the Quaternary Xishancun landslide,which is composed of three segments,i.e.,h1,h2,and h3 from bottom to top.Our results show that Poisson’s ratio values are generally higher than 0.33 and that the S-wave velocities vary from 0.1 to 0.9 km s^(-1).High Poisson’s ratios(>0.44)are mainly distributed in the juncture regions between different segments,as well as the western edge of h2.These zones show significant variation in landslide thickness and are potentially hazardous areas.Low velocities of 0.05–0.2 km s^(-1)with thicknesses of 10–30m are widely observed in the lower layer of the landslide.The high Poisson’s ratios and low-velocity layer may be related to water-rich materials in these areas.Our study suggests that the high-frequency receiver functions from local earthquakes can be used to delineate geotechnical structures,which is valuable for landslide stability analysis and hazard mitigation.
