泥石流危险性评价:模糊c均值聚类-支持向量机法

doi:10.13278/j.cnki.jjuese.201604203

吉林大学学报(地球科学版) ›› 2016, Vol. 46 ›› Issue (4): 1168-1175.doi: 10.13278/j.cnki.jjuese.201604203

泥石流危险性评价:模糊c均值聚类-支持向量机法

王常明¹, 田书文¹, 王翊虹², 阮云凯¹, 丁桂伶²

1. 吉林大学建设工程学院, 长春 130026;
2. 北京市地质研究所, 北京 100111

收稿日期:2016-03-05 出版日期:2016-07-26 发布日期:2016-07-26
通讯作者: 田书文(1988),男,博士研究生,主要从事地质灾害防治及工程地质方面的研究,E-mail:597758449@qq.com E-mail:597758449@qq.com
作者简介:王常明(1966),男,教授,博士生导师,主要从事土力学及地质灾害方面的研究,E-mail:wangcm@jlu.edu.cn
基金资助:
国家自然科学基金面上项目（41572257，40972171）；北京市科技计划项目（Z141100003614052）

Risk Assessment of Debris Flow: A Method of SVM Based on FCM

Wang Changming¹, Tian Shuwen¹, Wang Yihong², Ruan Yunkai¹, Ding Guiling²

1. College of Construction Engineering, Jilin University, Changchun 130026, China;
2. Beijing Geology Institute, Beijing 100011, Chana

Received:2016-03-05 Online:2016-07-26 Published:2016-07-26
Supported by:
Supported by National Science Foundation of China (41572257, 40972171)and Beijing Science and Technology Project(Z141100003614052)

摘要/Abstract

摘要：

泥石流是一种能够造成灾难性后果的严重自然灾害，准确可靠的泥石流危险性评价对于其预警及防治工作来说至关重要。泥石流的危险性评价方法有很多，模糊c均值聚类（FCM）方法是其中一种应用广泛的分类方法；相比其他方法而言，其无需主观确定边界，并且能以各级隶属度矩阵为输出结果，方便应用。支持向量机（SVM）是基于结构风险最小化为目标的机器学习理论，以支持向量为算法支撑，具有一定的鲁棒性，并且适合在小样本条件下进行分类。本文选用FCM和SVM联合的方法，开展泥石流危险性的评价；对北京房山区南窖沟泥石流危险性进行分析，并对比其他评价方法所得结果，证明本文提出的评价方法具有较好的效果。

关键词: 泥石流, 危险性分类, 模糊c均值聚类, 支持向量机

Abstract:

Debris flow is a kind of nature hazard which can produce serious consequences, and the accuracy of debris flow risk classification is important for the early warning and disaster prevention.Now there are a lot of algorithms used to evaluate the risk of debris flow. Fuzzy c means (FCM) algorithm is one of the widely used algorithms. Compared with general classification method, FCM does not need to determine risk boundaries artificially, and it outputs membership degree matrix for each risk degree. Support vector machine (SVM) is a machine algorithm based on structure risk minimization. It establishes classification model by support vectors and has better Robustness. It is well applied to small samples. In this paper, the SVM method based on FCM is used for debris flow risk evaluation, which gets a good classification performance.

Key words: debris-flow, risk classification, FCM, SVM

中图分类号:

P642.23

王常明, 田书文, 王翊虹, 阮云凯, 丁桂伶. 泥石流危险性评价:模糊c均值聚类-支持向量机法[J]. 吉林大学学报(地球科学版), 2016, 46(4): 1168-1175.

Wang Changming, Tian Shuwen, Wang Yihong, Ruan Yunkai, Ding Guiling. Risk Assessment of Debris Flow: A Method of SVM Based on FCM[J]. Journal of Jilin University(Earth Science Edition), 2016, 46(4): 1168-1175.

参考文献

[1] 牛岑岑. 泥石流危险度评价指标的提取与等级划分[D]. 长春:吉林大学,2013. Niu Cencen,Index Selection and Rating for Debris Flow Hazard Assessment[D]. Changchun:Jilin University,2013.

[2] 陈宁生,周海波,卢阳,等.西南山区泥石流防治工程效益浅析[J].成都理工大学学报(自然科学版),2013,40(1):50-58. Chen Ningsheng,Zhou Haibo,Lu Yang,et al. Analysis of Benefits of Debris Flow Control Projects in Southwest Mountain Areas of China[J]. Journal of Chengdu University of Technology(Science Technology Edition),2013,40(1):50-58.

[3] 韦方强,胡凯衡,崔鹏,等. 山区城镇泥石流减灾决策支持系统[J].自然灾害学报,2002,11(2):31-36. Wei Fangqiang,Hu Kaiheng,Cui Peng,et al. Decision Support System of Debris Flow Mitigation for Mountain Towns[J]. Journal of Natural Disasters, 2002,11(2):31-36.

[4] 康志成,李悼芬,马蔼乃,等.中国泥石流研究[M].北京:科学出版社,2004. Kang Zhicheng,Li Daofen,Ma Ainai,et al. Research on Debris Flow in China[M]. Beijing:Science Press,2004.

[5] 常鸣. 基于遥感及数值模拟的强震区泥石流定量风险评价研究[D]. 成都:成都理工大学,2014. Chang Ming. Quantitative Risk Assessment of Debris Flow in Coseismic Area Based on Remote Sensing and Numerical Simulation[D]. Chengdu :Chengdu University of Technology,2014.

[6] Hollingsworth R,Kovacs G S. Soil Slumps and Debris Flows Prediction and Protection[J]. Bulletin of the Association of Engineering Geologists 1981,38(1):17-28.

[7] Wadge G. The Potential of GIS Modeling of Gravity Flows and Slope Instability[J]. Int J Geographical Information System,1994,2(2):143-152.

[8] 李阔,唐川. 泥石流危险性评价研究进展[J]. 灾害学,2007,22(1):106-111. Li Kuo, Tang Chuan. Progress in Research on Debris Flow Hazard Assessment[J]. Journal of Catastrophology,2007,22(1):106-111.

[9] Xu L M,Chen J P,Wang Q,et al. Fuzzy C-Means Cluster Analysis Based on Mutative Scale Chaos Optimization Alagorithm for the Grouping of Discontinuity Sets[J]. Rock Mechanics and Rock Engineering,2013,46:189-198.

[10] 徐黎明,王清,陈剑平,等. 基于BP神经网络的泥石流平均流速预测[J]. 吉林大学学报(地球科学版),2013,43(1): 167-172. Xu Liming,Wang Qing,Chen Jianping,et al. Forcast for Average Velocity of Debris Flow Based on BP Neural Network[J]. Journal of Jilin University(Earth Science Edition),2013, 43(1):167-172.

[11] 铁永波,唐川. 层次分析法在单沟泥石流危险度评价中的应用[J]. 中国地质灾害与防治学报,2006,17(4):79-84. Tie Yongbo,Tang Chuan. Application of AHP in Single Debris Flow Risk Assessment[J]. The Chinese Journal of Geological Hazard and Control,2006,17(4):79-84.

[12] 谷复光,王清,张晨. 基于投影寻踪与可拓学方法的泥石流危险度评价[J].吉林大学学报(地球科学版),2010,40(2): 373-377. Gu Fuguang,Wang Qing,Zhang Chen. Debris Flow Risk Assessment by PPC and Extenics[J]. Journal of Jilin University(Earth Science Edition),2010,40(2):373-377.

[13] 王晓朋,潘懋,任群智. 基于流域系统地貌信息熵的泥石流危险性定量评价[J]. 北京大学学报(自然科学版),2007,43(2):211-215. Wang Xiaopeng,Pan Mao,Ren Qunzhi. Hazard Assessment of Debris Flow Based on Geomorphic Information Entropy in Catchment[J]. Acta Scientiarum Naturalium Universitatis Pekinensis,2007,43(2):211-215.

[14] Hirata T,Satoh T,Ito K. Fractal Structure of Spatial Distribution of Micro Fracturing in Rock[J]. Geophys J R Astr Soc,1987,90:369-374.

[15] 李欣杰. 大东沟泥石流风险性评价研究[D]. 长春:吉林大学,2014. Li Xinjie.Study of the Risk Evaluation for Dadonggou Debris Flow Basin[D]. Changchun:Jilin University,2014.

[16] 丁丽宏. 基于改进的灰关联分析和层次分析法的边坡稳定性研究[J]. 岩土力学,2011,32(11):3437-3441. Ding Lihong. Research on Estimation of Slope Stability Based on Improved Grey Correlation Analysis and Analytic Hierarchy Process[J]. Rock and Soil Mechanics,2011,32(11):3437-3441.

[17] 铁永波,唐川,周春花. 基于信息熵理论的泥石流沟谷危险度评价[J]. 灾害学,2005,20(4):43-46. Tie Yongbo,Tang Chuan,Zhou chunhua. Information Entropy-Based Hazard Assessment of Debris Flow Gully[J]. Journal of Catastrophology,2005,20(4):43-46.

[18] 黄双,陈剑平,潘玉珍,等. 分形理论在泥石流危险度评价中的应用[J]. 吉林大学学报(地球科学版),2012,42(3):214-219. Huang Shuang,Chen Jianping,Pan Yuzhen,et al. Application of Fractal Theory in Debris Flow Risk Evaluation[J]. Journal of Jilin University(Earth Science Edition),2012,42(3):214-219.

[19] Bezdek J C, Ehrlich R, Full W. FCM: The Fuzzy C-Means Clustering Algorithm[J] .Computers & Geosciences,1984,10(2/3):191-203.

[20] 张文,陈剑平,秦胜伍,等. 基于主成分分析的FCM法在泥石流分类中的应用[J]. 吉林大学学报(地球科学版),2010,40(2):368-372. Zhang Wen,Chen Jianping,Qin Shengwu,et al. Application of FCM Based on Principal Components Analysis in Debris Flow Classification[J]. Journal of Jilin University(Earth Science Edition),2010,40(2):368-372.

[21] 马志民,张军,钟亮.基于层次聚类的改进FCM算法[J].山东交通学院学报,2005, 13(2):67-69. Ma Zhimin,Zhang Jun,Zhong Liang. The Improvement of FCM Algorithm Based on Hierarchical Cluster[J]. Journal of Shandong Jiaotong University,2005,13(2): 67-69.

[22] 李宁,王李管,贾明涛,等. 改进遗传算法和支持向量机的岩体结构面聚类分析[J]. 岩土力学,2014,35(增刊2):405-411. Li Ning,Wang Liguan,Jia Mingtao,et al. Application of Improved Genetic Algorithm and Support Vector Machine to Clustering Analysis of Rock Mass Structural Plane[J]. Rock and Soil Mechanics,2014,35(Sup.2):405-411.

[23] 刘希林,唐川. 泥石流危险度评价[M]. 北京:科学出版社,1995. Liu Xilin,Tang Chuan. Debris Flow Hazard Degree Evaluations[M]. Beijing: Science Press,1995.

[24] 王英杰. 基于最小熵的金沙江上游区域泥石流危险度评价[D]. 长春:吉林大学,2014. Wang Yingjie.Evaluation the Hazard Degree of the Landslide of the Jinsha River Upstream Area Based on Minimum Entropy[D]. Changchun:Jilin University, 2014.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

泥石流危险性评价:模糊c均值聚类-支持向量机法

Risk Assessment of Debris Flow: A Method of SVM Based on FCM

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	杨兰, 王运, 邹勇军, 胡宝群, 李满根, 张安, 朱满怀. 基于机器学习的富硒土壤预测模型的构建与比较——以江西省信丰县油山地区为例[J]. 吉林大学学报(地球科学版), 2025, 55(5): 1629-1643.
[2]	文海家, 胡吉威, 张辉, 向学坤, 黄勤. 泥石流危险范围Laharz修正模型及其应用[J]. 吉林大学学报(地球科学版), 2024, 54(3): 905-918.
[3]	徐兴华, 肖双粟, 冯杭建, 吕庆. 低频性沟谷型泥石流水动力学冲蚀启动机制及动态监控[J]. 吉林大学学报(地球科学版), 2024, 54(3): 919-932.
[4]	管耀, 王清辉, 冯进, 杨清, 石磊. 基于机器学习的蚀变火成岩测录井综合岩性识别——以南海北部珠江口盆地惠州26-6井区为例#br#[J]. 吉林大学学报(地球科学版), 2024, 54(1): 345-358.
[5]	王常明, 刘辛磊, 王飞. 品字形桩林防护结构对泥石流冲击桥墩作用的影响[J]. 吉林大学学报(地球科学版), 2023, 53(6): 1773-1784.
[6]	刘鑫, 张文, 李根, 刘波. 高位远程崩滑碎屑流-泥石流灾害链的演变过程与影响范围预测：以“4·5”四川洪雅县铁匠湾地质灾害链为例[J]. 吉林大学学报(地球科学版), 2023, 53(6): 1799-1811.
[7]	李猛猛, 刘敬党, 梁天意, 谭亮, 王刚, 朱玺. 基于支持向量机算法的岩浆硫化物矿床硫元素预测模型 [J]. 吉林大学学报(地球科学版), 2022, 52(3): 866-878.
[8]	王博帅, 蒲东川, 李婷婷, 牛雪峰. 基于多源遥感影像的长春市城市建成区提取[J]. 吉林大学学报(地球科学版), 2021, 51(4): 1284-1294.
[9]	牟丹, 张丽春, 徐长玲. 3种经典机器学习算法在火山岩测井岩性识别中的对比[J]. 吉林大学学报(地球科学版), 2021, 51(3): 951-956.
[10]	刘云鹏, 郭春影, 秦明宽, 吴玉, 裴柳宁. 基于PCA-SVM算法对稀土元素与稀土判别指标耦合数据集的铀矿床分类[J]. 吉林大学学报(地球科学版), 2021, 51(3): 723-733.
[11]	王常明, 李桐, 田书文, 李硕. 基于LAHARZ的泥石流堆积范围预测模型的建立及应用[J]. 吉林大学学报(地球科学版), 2019, 49(6): 1672-1679.
[12]	尹超, 周爱红, 袁颖, 王帅伟. 基于邻域粗糙集和支持向量机的固结系数预测[J]. 吉林大学学报(地球科学版), 2019, 49(3): 746-754.
[13]	韩启迪, 张小桐, 申维. 基于决策树特征提取的支持向量机在岩性分类中的应用[J]. 吉林大学学报(地球科学版), 2019, 49(2): 611-620.
[14]	徐守余, 路研, 王亚. 基于支持向量机的浊积扇低渗透储层流动单元研究[J]. 吉林大学学报(地球科学版), 2018, 48(5): 1330-1341.
[15]	王明常, 张馨月, 张旭晴, 王凤艳, 牛雪峰, 王红. 基于极限学习机的GF-2影像分类[J]. 吉林大学学报(地球科学版), 2018, 48(2): 373-378.