[1]缪亚敏,朱阿兴,杨 琳,等.滑坡危险度评价对BCS负样本采样的敏感性[J].山地学报,2016,(04):432-441.[doi:10.16089/j.cnki.1008-2786.000148]
　MIAO Yamin,ZHU Axing,YANG Lin,et al.Sensitivity of BCS for Sampling Landslide Absence Data in Landslide Susceptibility Assessment[J].Mountain Research,2016,(04):432-441.[doi:10.16089/j.cnki.1008-2786.000148]
点击复制

滑坡危险度评价对BCS负样本采样的敏感性()
分享到：

《山地学报》[ISSN:1008-2186/CN:51-1516]

卷:
期数:
2016年04期
页码:
432-441
栏目:
山地灾害
出版日期:
2016-08-01

文章信息/Info

Title:
Sensitivity of BCS for Sampling Landslide Absence Data in Landslide Susceptibility Assessment
文章编号:
1008-2786-(2016)4-432-10
作者:
缪亚敏1;  朱阿兴1; 2; 3;  杨 琳2; 白世彪1; 刘军志1; 邓永翠1
1.虚拟地理环境教育部重点实验室(南京师范大学),江苏省地理环境演化国家重点实验室培育建设点,江苏省地理信息资源开发与利用协同创新中心,江苏 南京 210023;
2.中国科学院地理科学与资源研究所 资源与环境信息系统国家重点实验室,北京 100101;
3.Department of Geography, University of Wisconsin-Madison, Madison, WI 53706, USA
Author(s):
MIAO Yamin1;  ZHU Axing1; 2; 3; YANG Lin2; BAI Shibiao1; LIU Junzhi1; DENG Yongcui1
1.Key Laboratory of Virtual Geographic Environment(Nanjing Normal University), Ministry of Education, State Key Laboratory Cultivation Base of Geographical Environment Evolution(Jiangsu Province), Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China;
2.State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China;
3.Department of Geography, University of Wisconsin-Madison, Madison, WI 53706, USA
关键词:
SVM;  负样本;  缓冲区控制采样;  缓冲区大小;  滑坡危险度制图
Keywords:
SVM;  landslide absence data;  BCS;  buffer;  landslide susceptibility mapping
分类号:
P642.22
DOI:
10.16089/j.cnki.1008-2786.000148
文献标志码:
A
摘要:
滑坡负样本在基于统计方法的滑坡危险度制图中具有重要作用,能够抑制统计方法对滑坡危险度的高估。缓冲区控制采样(Buffer controlled sampling,BCS)是一种广泛使用的负样本采样方法,其原理是认为滑坡点附近一定范围内的地理环境与滑坡点所在的地理环境相似,易发生滑坡,因而应当在灾害点一定缓冲区以外的区域采集负样本。目前缓冲区大小主要是根据专家对研究区的经验知识确定,具有主观性。缓冲区大小对基于统计方法的滑坡危险度制图的影响研究较少。因此,有必要分析缓冲区大小与滑坡危险度制图精度之间的关系,探究适宜的缓冲区大小。以陇南山区的油坊沟流域为研究区,基于BCS负样本采样方法,探究不同缓冲区大小对基于支持向量机(Support vector machine,SVM)的滑坡危险度制图结果的影响。结果表明:缓冲区过小会导致与滑坡点地理环境相似的假的负样本的存在,从而导致滑坡危险度的低估; 缓冲区过大会导致负样本在环境特征空间中太局限,负样本集的全局代表性差,从而导致滑坡危险度的高估。在本研究区基于SVM的滑坡危险度制图中,200～500 m是使用BCS采集负样本的较理想的缓冲区大小。
Abstract:
Landslide absence data plays an important role in data-driven models for landslide susceptibility mapping. It can constrain the overestimation of predicted landslide susceptibility values. Buffer controlled sampling(BCS)is widely used in sampling landslide absence data. It is based on the general principle that the area near the landslide occurrences has similar geo-environment with landslides, resulting it prone to landslides. Thus landslide absence data should be sampled from the areas beyond the buffer zones of the landslide sites. Currently the buffer size is decided subjectively based on the experts' knowledge of the study area. The study of the effect of buffer size on data-driven models for landslide susceptibility mapping is rare. It is important to study the general relationships between buffer size and mapping accuracy and find an appropriate buffer size for an given area. In this study, BCS sampling strategy was used in the Youfang ravine in the south Gansu of China for sampling landslide absence data and Support Vector Machine(SVM)was used to deliniute landslide susceptibility across the study area. Results show that if the buffer size be small, false absence data would be included in the generated absence datasets and result in the underestimation of the predicted landslide susceptibility values. If the buffer size be large, the representativeness of generated landslide absence data for the whole study area is low, resulting in the overestimation of the predicted landslide susceptibility values. In the Youfang ravine, the appropriate range of buffer size in BCS for sampling landslide absence data is from 200 m to 500 m in SVM for landslide susceptibility mapping.

参考文献/References:

[1] 胡新丽,唐辉明. 斜坡工程GIS系统研究与应用[M]. 武汉:中国地质大学出版社,2005:1-136[Hu Xinli, Tang Huiming. Research on the GIS system of slope engineering GIS and its application[M]. Wuhan: China University of Geosciences Press,2005:1-136]
[2] Iswar D, Sashikant Sahoob, Cees van Westena, et al. Landslide susceptibility assessment using logistic regression and its comparison with a rock mass classification system, along a road section in the northern Himalayas(India)[J]. Gepmorphology, 2010, 114(4): 627-637
[3] Bai Shibiao, Wang Jian, Zhang Zhigang, et al. Combined landslide susceptibility mapping after Wenchuan earthquake at the Zhouqu segment in the Bailongjiang Basin, China[J]. Catena, 2012, 99: 18-25
[4] Guzzetti F, Carrara A, Cardinali M, et al. Landslide hazard evaluation: a review of current techniques and their application in a multi-scale study, Central Italy[J]. Geomorphology, 1999, 31: 181–216
[5] Guzzetti F, Reichenbach P, Cardinali M, et al. Probabilistic landslide hazard assessment at the basin scale[J]. Gepmorphology, 2005, 72(1-4): 272-299
[6] Guzzetti F, Reichenbach P, Ardizzone F, et al. Estimating the quality of landslide susceptibility models[J]. Gepmorphology, 2006, 20(1-2): 166-184
[7] Dai Fuchu, Lee Chaofen, Zhang Xiaohui. GIS-based geo-environmental evaluation for urban land-use planning: a case study[J]. Engineering Geology, 2001, 61(4): 257-271
[8] 尹志华. 基于RS和GIS技术对区域滑坡进行高效快速敏感性评价的模型研究——以北川县为例[D]. 成都理工大学,2011.[Yin zhihua. Rapid and efficient regional landslide susceptibility assessment model based GIS and RS technology——a case study in Beichuan County[D]. Chengdu University of Technology,2011.]
[9] Carrara A, Cardinali M, Detti R, et al. GIS techniques and statistical models in evaluating landslide hazard[J]. Earth surface processes and landforms, 1991, 16: 427-445
[10] Süzen M L, Doyuran V. Data driven bivariate landslide susceptibility assessment using geographical information systems: a method and application to Asarsuyu catchment, Turkey[J]. Engineering Geology, 2004,71(3-4): 303-321
[11] Das I, Sahoo S, van Westen C, et al. Landslide susceptibility assessment using logistic regression and its comparison with a rock mass classification system, along a road section in the northern Himalayas(India)[J]. Geomorphology, 2010, 114: 627-637
[12] Yilmaz I. The effect of the sampling strategies on the landslide susceptibility mapping by conditional probability and artificial neural networks[J]. Environmental Earth Sciences, 2010, 60: 505-519
[13] Carrara A, Cardinali M, Guzzetti F, et al. GIS-based techniques for mapping landslide hazard[G]// Carrara A, Guzzetti F.(Eds.). Geographical Information Systems in Assessing Natural Hazards. Kluwer Academic Publishers, Dordrecht, The Netherlands, 1995:135-175
[14] 祁元,刘勇,杨正华,等. 基于GIS的兰州滑坡与泥石流灾害危险性分析[J]. 冰川冻土,2012,34(1):96-104[Qi Yuan, Liu Yong, Yang Zhenghua, et al. GIS-based analysis of landslide and debris flow hazard in Lanzho[J]. Journal of Glaciology and Geocryology,2012,34(1): 96-104]
[15] Guo Qinghua, Maggi K, Catherine H G. Support vector machines for predicting distribution of Sudden Oak Death in California[J]. Ecological Modelling, 2005, 182: 75-90
[16] Xiao Chenchao, Tian Yuan, Shi Wenzhong, et al. A new method of pseudo absence data generation in landslide susceptibility mapping with a case study of Shenzhen[J]. Science China Technological Sciences, 2010, 53(1): 75-84
[17] Yao Xin, Tham L G, Dai Fuchu. Landslide susceptibility mapping based on support vector machine: a case study on natural slopes of Hong Kong, China[J]. Geomorphology, 2008, 101:572-582
[18] 方苗, 张金龙, 徐瑱. 基于GIS和Logistic回归模型的兰州市滑坡灾害敏感性区划研究[J]. 遥感技术与应用,2011,24(6):845-852[Fang Miao, Zhang Jinlong, Xu Zhen. Landslide susceptibility zoning study in Lanzhou city based on GIS and logistic regression model[J]. Remote Sensing Technology and Application,2011,24(6): 845-852]
[19] 谌文武,赵志福,刘高,等. 兰州-海口高速公路甘肃段工程地质问题研究[M]. 兰州:兰州大学出版社,2006:19-22[Chen Wenwu, Zhao Zhifu, Liu Gao, et al. The engineering geological problems study of Gansu section of Lanzhou-Haikou highway[M]. Lanzhou: Lanzhou University Press,2006: 19-22]
[20] 陈耀乾. 甘肃省武都县地质灾害调查与区划报告[R]. 兰州:甘肃省地质环境监测总站,2001.[Chen Yaoqian. Geo-hazard survey and zone report in Wudu country of Gansu province[R]. Lanzhou: General Monitoring Station of Geological Environment of Gansu Province, China,2001.]
[21] 董抗甲. 甘肃省武都县地质灾害调查与区划报告[R]. 甘肃省地质环境监测总站,2003.[Dong Kangjia. Geo-hazard survey and zone report in Zhouqu country of Gansu province[R]. Edited by General Monitoring Station of Geological Environment of Gansu Province, China,2003. ]
[22] Atkinson P M, Massari R. Autologistic modelling of susceptibility to landsliding in the Central Apennines, Italy[J]. Geomorphology, 2011, 130(1-2): 55-64
[23] 陈晓利,叶洪,程菊红. GIS技术在区域地震滑坡危险性预测中的应用——以龙陵地震滑坡为例[J]. 工程地质学报,2006,14(03):333-338[Chen Xiaoli, Ye Hong, Cheng Juhong. Use of GIS in regional risk assessment of earthquake induced landslides—— a case study of earthquake induced landslides in Longling in 1976[J]. Journal of Engineering Geology,2006,14(03): 333-338]
[24] 谭龙, 陈冠, 王思源, 等. 逻辑回归与支持向量机模型在滑坡敏感性评价中的应[J]. 工程地质学报,2014,22(1):56-63[Tan Long, Chen Guan, Wang Siyuan, et al. Landslide susceptibility mapping based on logistic regression and support vector machine[J]. Journal of Engineering Geology,2014,22(1): 56-63]
[25] 齐识,张雅莉,张鹏,等. 白龙江流域滑坡危险性评价指标体系的构建[J]. 长江科学院院报,2014,31(01):23-38[Qi Shi, Zhang Yali, Zhang Peng, et al. An assessment index system for landslide risk in Bailong river basin[J]. Journal of Yangtze river scientific research institute,2014,31(01): 23-38]
[26] 许冲,戴福初,姚鑫,等. 基于GIS的汶川地震滑坡灾害影响因素确定性系数分析[J]. 岩石力学与工程学报,2010,29(01):2372-2381[Xu Chong, Dai Fuchu, Yao Xin, et al. GIS based certainty factor analysis of landslide triggering factors in Wenchuan earthquake[J]. Chinese Journal of rock mechanics and engineering,2010,29(01): 2372-2381]
[27] 白世彪,闾国年,盛业华. GIS 技术在三峡库区滑坡影响因素分析中的应用[G]//中国地理信息系统协会第八届年会论文集,2004.[Bai Shibiao, Lü Guonian, Sheng Yehua. The application of GIS technology in the analysis of the landslide triggering factors in three Gorges reservoir area[G]//The eighth annual meeting proceedings of China association of geographic information system,2004.]
[28] Bai Shibiao, Wang Jian, Lü Guonian, et al. GIS-Based and Data-Driven Bivariate Landslide-Susceptibility Mapping in the Three Gorges Area, China[J]. Pedosphere, 2009, 19: 14-20
[29] 傅文杰. GIS支持下基于支持向量机的滑坡危险性评价[J]. 地理科学,2008,28(6):838-841[Fu Wenjie. Landslide hazard evaluation based on GIS and SVM[J]. Scientia geographica sinica,2008,28(6): 838-841]
[30] 李秀珍,孔纪名,王成华. 多分类支持向量机在滑坡稳定性判识中的应用[J]. 吉林大学学报:地球科学版,2010,40(3):631-637[Li Xiuzhen, Kong Jiming, Wang Chenghua. Application of multi-classification support vector machine in the identifying of landslide stability[J]. Journal of Jilin University:Earth Science Edition,2010,40(3): 631-637]
[31] 姜琪文,许强,何政伟. 基于SVM多类分类的滑坡区域危险性评价方法研究[J]. 地质灾害与环境保护,2005,16(3):328-330[Jiang Qiwen, Xu Qiang, He Zhengwei. Study on landslide hazard zonation based on multi-classification support vector machine[J]. Journal of Geological Hazards and Environment Preservation,2005,16(3): 329-330]
[32] 胡德勇,李京,陈云浩,等. GIS支持下滑坡灾害空间预测方法研究[J]. 遥感学报,2007,11(6):852-859[Hu Deyong, Li Jing, Chen Yunhao, et al. GIS-based landslide spatial prediction methods, a case study in Cameron highland, Malaysia[J]. Journal of Remote Sensing,2007,11(6): 852-859]
[33] Xu Chong, Xu Xiwei, Dai Fuchu. Comparison of different models for susceptibility mapping of earthquake triggered landslides related with the 2008 Wenchuan earthquake in China[J]. Computers & Geosciences, 2012, 46: 317-329
[34] Xu Chong, Dai Fuchu, Xu Xiwei, et al. GIS-based support vector machine modeling of earthquake-triggered landslide susceptibility in the Jianjiang River watershed, China[J]. Geomorphology, 2012, 145: 70-80
[35] Pradhan B. A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS[J]. Computers & Geosciences, 2013, 51: 350-365
[36] Chang Chihchuang, Lin Chihjen. LIBSVM: a library for Support Vector Machines [J]. ACM Transactions on Intelligent Systems and Technology(TIST), 2011, 2(3): 27. Software available at http://www.csie.ntu.edu.tw/ ～ cjlin/libsvm
[37] 刘京,朱阿兴,张淑杰,等. 基于样点个体代表性的大尺度土壤属性制图方法[J]. 土壤学报,2013,50(1):12-20[Liu Jing, Zhu Axing, Zhang Shujie, et al. Large scaled soil attribute mapping method based on individual representativeness of sample sites[J]. Acta Pedologica Sinica,2013,50(1): 12-20]

备注/Memo

备注/Memo:
收稿日期(Received date):2015-11-02; 修回日期(Accepted):2015-11-16。
基金项目(Foundation item):国家自然科学基金项目(41431177,41471178); 江苏省高校自然科学研究重大项目(14KJA170001); 国家重点基础研究发展计划973项目(2015CB954102)。 [This study is supported by the National Natural Science Foundation of China(41431177), the Natural Science Research Program of Jiangsu(14KJA170001)], the National Basic Research Program of China(2015CB954102).]
作者简介(Biography):缪亚敏(1991-),女,江苏泰州,硕士研究生,从事滑坡危险度评价研究。 [Miao Yamin, Female, Master Candidate, Born in Taizhou, Jiangsu, Major in landslide susceptibility mapping.] E-mail:miaopaper@163.com
更新日期/Last Update: 2016-07-30