[an error occurred while processing this directive] 世界地质 2019, 38(4) 1166-1176 DOI:   10.3969/j.issn.1004-5589.2019.04.028  ISSN: 1004-5589 CN: 22-1111/P
本期目录 | 下期目录 | 过刊浏览 | 高级检索                                                            [打印本页]   [关闭]
经济·环境
扩展功能
本文信息
Supporting info
PDF(4964KB)
[HTML全文]
参考文献[PDF]
参考文献
服务与反馈
把本文推荐给朋友
加入我的书架
加入引用管理器
引用本文
Email Alert
文章反馈
浏览反馈信息
本文关键词相关文章
斜坡地质灾害易发性评价
神经网络
频率比
支持向量机
永吉县
本文作者相关文章
刘飞
秦胜伍
乔双双
窦强
扈秀宇
PubMed
Article by Liu F
Article by Qin S
Article by Qiao S
Article by Dou Q
Article by Hu X
基于神经网络模型的斜坡地质灾害易发性评价:以吉林永吉为例
刘飞, 秦胜伍, 乔双双, 窦强, 扈秀宇
吉林大学 建设工程学院, 长春 130026
摘要： 吉林省永吉县存在大量的斜坡地质灾害，为了给永吉县斜坡地质灾害的防治和预警提供高效直观的分析模型，将吉林省永吉县作为研究区，选取高程、坡度、坡向、剖面曲率、平面曲率、距断层距离、岩性、距河流距离、年均降雨量、地形湿度指数和植被覆盖指数等11个评价因子，利用神经网络模型进行区域斜坡地质灾害易发性分析，再选用频率比、支持向量机模型进行对比。利用ROC曲线对模型的准确性进行验证分析，得出神经网络、频率比和支持向量机模型的成功率分别是91.3%、89.3%、90.2%，预测率分别是87.3%、84.3%、85.6%。结果表明：神经网络模型的精度最高，更适用于永吉县斜坡地质灾害的易发性评价。
关键词： 斜坡地质灾害易发性评价   神经网络   频率比   支持向量机   永吉县  
Slope geological hazards susceptibility evaluation based on neural network model: a case study from Yongji County of Jilin Province
LIU Fei, QIN Sheng-wu, QIAO Shuang-shuang, DOU Qiang, HU Xiu-yu
College of Construction Engineering, Jilin University, Changchun 130026, China
Abstract: There are large number of slope geological hazards in Yongji County of Jilin Province. In order to provide an efficient and intuitive analysis model for the prevention and warning of slope geological hazards, Yongji County of Jilin Province is used as a research area. Eleven evaluation factors including elevation, slope, slope di-rection, profile curvature, plane curvature, distance from faults, lithology, distance from rivers, average annual rainfall, terrain humidity index, and vegetation cover index are selected. Neural network model is used to analyze the susceptibility of regional slope geological hazards, followed by the comparison with frequency ratio and support vector machine models. Finally, the accuracy of the model is verified and analyzed using the ROC curve. The suc-cess rates of the neural network, frequency ratio, and support vector machine models are 91.3%, 89.3% and 90.2%, and the prediction rates are 87.3%, 84.3% and 85.6%, respectively. The results show that the neural network model has the highest accuracy and is more suitable for the assessment of slope geological hazards in Yongji County.
Keywords: slope geological hazards susceptibility evaluation   neural network   frequency ratio   support vector machine   Yongji County  
收稿日期 2019-08-26 修回日期 2019-10-13 网络版发布日期  
DOI: 10.3969/j.issn.1004-5589.2019.04.028
基金项目:

吉林省科技发展计划项目（20190303103SF，20170101001JC）

通讯作者: 秦胜伍(1980),男,教授,主要从事地质工程、地质灾害治理等方面的研究。E-mail:qinsw@jlu.edu.cn
作者简介:
作者Email: qinsw@jlu.edu.cn
参考文献：
[1] 庄卓涵. 基于综合指数法的珠海某地环境地质灾害易发性研究[J], 地下水, 2018, 40(3):110-112, 187. ZHUANG Zhuo-han. Study on the susceptibility of envi-ronmental geological disasters in Zhuhai based on the comprehensive index method[J]. Ground Water, 2018, 40(3):110-112, 187.
[2] Rahmati O, Pourghasemi H R, Zeinivand H. Flood sus-ceptibility mapping using frequency ratio and weights of evidence models in the Golastan Province, Iran[J]. Geocarto International, 2016, 31(1):42-70.
[3] 卢晓仓, 陈泰霖. 信息量模型在区域滑坡灾害危险性分析中的应用[J]. 贵州水力发电, 2010, 24(1):80-83. LU Xiao-cang, CHEN Tai-lin. Application of information quantity model in risk analysis of regional landslide disas-ter[J]. Guizhou Water Power, 2010, 24(1):80-83.
[4] 刘光辉, 刘汉湖, 姚昆, 等. 基于证据权法与确定系数法的滑坡危险区划对比分析:以虹口乡为例[J]. 物探化探计算技术, 2016, 38(6):848-853. LIU Guang-hui, LIU Han-hu, YAO Kun, et al. Based on the weights of evidence method and certainty factor method of landslide danger division comparative analysis:a case study in Hongkou, China[J]. Computing Tech-niques for Geophysical and Geochemical Exploration, 2016, 38(6):848-853.
[5] 邓浩, 张延军, 单坤, 等. 基于神经网络的东北海岸带碎石土地基强夯加固研究[J]. 世界地质, ht-tp://kns. cnki. net/kcms/detail/22.1111. P. 20190925.1525.002. html[2019-10-20] DENG Hao, ZHANG Yan-jun, SHAN Kun, et al. Study on dynamic compaction of gravelly soil foundation in north-east coast based on neural network[J]. Global Geology, http://kns.cnki.net/kcms/detail/22.1111.P.20190925.1525.002.html[2019-10-20]
[6] 黄发明, 殷坤龙, 蒋水华, 等. 基于聚类分析和支持向量机的滑坡易发性评价[J]. 岩石力学与工程学报, 2018, 37(1):156-167. HUANG Fa-ming, YIN Kun-long, JIANG Shui-hua, et al. Landslide susceptibility assessment based on cluste-ring analysis and support vector machine[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37(1):156-167.
[7] 吴赛儿, 陈剑, Zhou W, 等. 基于逻辑回归模型的泥石流易发性评价与检验:以金沙江上游奔子栏-昌波河段为例[J]. 现代地质, 2018, 32(3):611-622. WU Sai-er, CHEN Jian, Zhou W, et al. Debris-flow susceptibility assessment and validation based on logistic regression model:an example from the Benzilan-Changbo segment of the upper Jinshajiang River[J]. Geoscience, 2018, 32(3):611-622.
[8] Kanungo D P, Arora M K, Sarkar S, et al. A compara-tive study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for land-slide susceptibility zonation in Darjeeling Himalayas[J]. Engineering Geology, 2006, 85(3/4):347-366.
[9] 吕江峰. 基于流域单元的永吉县泥石流敏感性分析:硕士学位论文[D]. 长春:吉林大学, 2018. LYU Jiang-feng. Susceptibility analysis of debris flow in Yongji County based on watershed units:master's degree thesis[D]. Changchun:Jilin University, 2018.
[10] 杨根云, 周伟, 方教勇. 基于信息量模型和数据标准化的滑坡易发性评价[J]. 地球信息科学学报, 2018, 20(5):674-683. YANG Gen-yun, ZHOU Wei, FANG Jiao-yong. Assess-ment of landslide susceptibility based on information quantity model and data normalization[J]. Journal of Geoinformation Science, 2018, 20(5):674-683.
[11] 赵帅, 赵洲. 基于信息量模型的地质灾害易发性评价[J]. 水力发电, 2019, 45(3):27-32. ZHAO Shuai, ZHAO Zhou. Geological hazard risk as-sessment based on information quantity model[J]. Wa-ter Power, 2019, 45(3):27-32.
[12] 唐睿旋, 晏鄂川, 唐薇. 基于粗糙集和BP神经网络的滑坡易发性评价[J]. 煤田地质与勘探, 2017, 45(6):129-138. TANG Rui-xuan, YAN E-chuan, TANG Wei. Land-slide susceptibility evaluation based on rough set and back-propagation neural network[J]. Coal Geology & Exploration, 2017, 45(6):129-138.
[13] 牛瑞卿, 彭令, 叶润青, 等. 基于粗糙集的支持向量机滑坡易发性评价[J]. 吉林大学学报(地球科学版), 2012, 42(2):430-439. NIU Rui-qing, PENG Ling, YE Run-qing, et al. Landslide susceptibility assessment based on rough sets and support vector machine[J]. Journal of Jilin Uni-versity (Earth Science Edition), 2012, 42(2):430-439.
[14] 任敬, 范宣梅, 赵程, 等. 贵州省都匀市滑坡易发性评价研究[J]. 水文地质工程地质, 2018, 45(5):165-172. REN Jing, FAN Xuan-mei, ZHAO Cheng, et al. Evalu-ation of the landslide vulnerability in Duyun of Guizhou Province[J]. Hydrogeology & Engineering Geology, 2018, 45(5):165-172.
[15] Cristian V P, Radu P, Adrian G, et al. A comparative analysis of binary logistic regression and analytical hier-archy process for landslide susceptibility assessment in the Dobrovǎt River Basin, Romania[J]. Pedosphere, 2016, 26(3):335-350.
本刊中的类似文章
1．张昭杰, 方石.基于遗传算法优化的支持向量机在岩性识别中的应用[J]. 世界地质, 2019,38(2): 486-491
2．郑泽宇, 赵庆英, 李湜先, 邱士龙.地球化学异常识别的两种机器学习算法之比较[J]. 世界地质, 2018,37(4): 1288-1294
3．王红菲, 江玉龙, 陆哲昆, 王祝文.辽河东部凹陷火成岩测井岩性识别方法与应用[J]. 世界地质, 2016,35(2): 510-525
4．杨晓辉, 王祝文, 王文华, 郑武, 周大鹏.BP 神经网络算法在火成岩泥质含量计算中的应用[J]. 世界地质, 2015,34(4): 1120-1124
5．庄华, 潘保芝, 张丽华.BP 神经网络模型在朝长地区扶杨油层压裂产能预测中的应用[J]. 世界地质, 2012,31(4): 785-790
6．吕琳, 王明君, 范继璋.BP 模型在南海神狐海域天然气水合物储量参数预测中的应用[J]. 世界地质, 2011,30(1): 80-84
7．张振庭, 王忠文, 马艳英, 王淼.支持向量机在地球化学勘查中的应用[J]. 世界地质, 2010,29(1): 78-82
Copyright by 世界地质