长江科学院院报 ›› 2016, Vol. 33 ›› Issue (8): 47-51.DOI: 10.11988/ckyyb.20150311

• 工程安全与灾害防治 • 上一篇    下一篇

信息量支持下SVM模型滑坡灾害易发性评价

安凯强1,牛瑞卿2   

  1. 1.武汉大学 测绘遥感信息工程国家重点实验室,武汉 430079;
    2.中国地质大学武汉 地球物理与空间信息学院,武汉 430074
  • 收稿日期:2015-04-15 修回日期:2015-05-11 出版日期:2016-07-25 发布日期:2016-07-25
  • 通讯作者: 牛瑞卿(1969-),男,河南南阳人,教授,博士,从事3S与地质灾害研究,(电话)027-67883425(电子信箱)rqniu@163.com。
  • 作者简介:安凯强(1992-),男,河北石家庄人,硕士研究生,研究方向为灾害遥感变化检测与评估,(电话)027-68778880(电子信箱)kaiqiaAN@163.com。
  • 基金资助:
    国家高技术研究发展计划(863)项目(2012AA121303)

Landslide Susceptibility Assessment Using Support Vector Machine Based on Weighted-information Model

AN Kai-qiang1, NIU Rui-qing2   

  1. 1.State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing,Wuhan University, Wuhan 430079, China;
    2.Institute of Geophysics and Geomatics,China University of Geosciences, Wuhan 430074, China
  • Received:2015-04-15 Revised:2015-05-11 Online:2016-07-25 Published:2016-07-25

摘要: 三峡库区是我国滑坡灾害广泛发育的地区之一,滑坡灾害易发性评价对库区的防灾减灾有重要意义。在滑坡灾害易发性指标信息量的基础上,构建了信息量支持下的SVM模型,并对滑坡灾害易发性进行了评价。该模型根据地层岩性、地质构造、坡度、坡向、坡型结构、土地利用类型、水、归一化植被指数,以及上述指标的总信息量,共9类指标组成的数据集进行SVM训练,得到评价模型;运用该评价模型对研究区全区滑坡灾害易发性进行评价,并以模型决策值的零点和突变点确定易发性等级划分标准。并以三峡库区万州主城区为研究区验证模型,研究表明信息量支持下SVM模型的训练样本精度为81.41%,验证样本精度为91.11%,优于常用的信息量模型,滑坡的高易发区和较高易发区占研究区总面积的47.05%,主要集中在人类工程活动强烈的长江干支流两侧,结果与已知滑坡分布基本一致,表明该模型在研究区具备较好的适用性。

关键词: 滑坡灾害, 信息量, 支持向量机, 易发性评价, 三峡库区

Abstract: Three Gorges Reservoir is one of the landslide disaster-prone areas in China, and it is meaningful to as-sess the landslides susceptibility of Three Gorges Reservoir both for disaster prevention and reduction. The WI (Weighted-Information)-SVM(Support Vector Machine) model was adopted to assess the landslide susceptibility on the basis of entropy and SVM models. The SVM’s training dataset was comprised by the entropy of nine influence factors, including the stratum lithology, the geological structure, the slope gradient, the direction and structure of slope, the land use, the influence of water, and the NDVI (Normalized Difference Vegetation Index), together with the sum of them. The landslide susceptibility of the whole study area was evaluated, and the result of landslide susceptibility was ranked according to the zero value and abrupt change value of the decision value of model. The landslide susceptibility in Wanzhou district was assessed as an example to validate the WI-SVM model. The research result showed that the accuracy of the training dataset was 81.41% and verification dataset 91.11%, superior to commonly used models. Area with high and relatively high susceptibility accounts for 47.05% of the entire area, mainly in the mainstream and tributaries of the Yangtze River with strong human activities. The results are consistent with the distribution of landslides which has been known, indicating that the WI-SVM model has good applicability for the study area.

Key words: landslide hazards, weighted-information, support vector machine, susceptibility assessment, Three Gorges Reservoir area

中图分类号: