基于支持向量机模型的四川省滑坡灾害易发性区划
|
摘要
以四川省为研究区,结合野外调查情况和主成分分析法,选择与构造线距离、高程、与河流距离、地貌类型、岩性、年均降雨量和坡度等7个滑坡致灾因子,并基于频率比模型构建滑坡致灾因子评价体系,引入支持向量机模型编制研究区滑坡易发性区划图。研究结果表明:四川省被划分为低易发区、中易发区、高易发区和极高易发区4个区域,各区面积占研究区比例分别为41.77%,31.19%,17.20%和10.84%,高易发区和极高易发区主要位于四川省的南部和中东部,且发生滑坡数量占总数的79.14%。研究成果不仅为基础设施建设、防灾减灾工作提供科学依据,还为其他地区滑坡易发性评价提供参考。
Taking Sichuan Province as the research area, combining the field investigation and principal component analysis(PCA) method, distance from the construction line, elevation, distance from the river,landform types, lithology, annual average rainfall and slope are selected as landslide causal factors with the frequency ratio model, and support vector machine(SVM) is used to created landslide susceptibility zoning map of research area. The results show that the research area could be classified into four categories, i.e., low susceptibility zone, moderate susceptibility zone, high susceptibility zone, and extremely high susceptibility zone,taking an area proportion of 41.77%, 31.19%, 17.20%, 10.84%, respectively. The number of landslides in high-susceptibility areas and extremely high-susceptibility areas accounted for 79.14% of the total, mainly in the southern and central eastern parts of Sichuan Province. The research results not only provide a scientific basis for infrastructure construction, disaster prevention, and mitigation work but also provide a reference for landslide susceptibility evaluation in other regions.
Taking Sichuan Province as the research area, combining the field investigation and principal component analysis(PCA) method, distance from the construction line, elevation, distance from the river,landform types, lithology, annual average rainfall and slope are selected as landslide causal factors with the frequency ratio model, and support vector machine(SVM) is used to created landslide susceptibility zoning map of research area. The results show that the research area could be classified into four categories, i.e., low susceptibility zone, moderate susceptibility zone, high susceptibility zone, and extremely high susceptibility zone,taking an area proportion of 41.77%, 31.19%, 17.20%, 10.84%, respectively. The number of landslides in high-susceptibility areas and extremely high-susceptibility areas accounted for 79.14% of the total, mainly in the southern and central eastern parts of Sichuan Province. The research results not only provide a scientific basis for infrastructure construction, disaster prevention, and mitigation work but also provide a reference for landslide susceptibility evaluation in other regions.
引文
[1]陈香,王瑞.福建省滑坡灾害风险管理决策系统构建[J].灾害学,2016,31(2):47-52.CHEN Xiang,WANG Rui.Construction of landslide disaster risk management decision system in Fujian province[J].Disaster science,2016,31(2):47-52.
[2]Mandal B,Mandal S.Analytical hierarchy process(AHP)based landslide susceptibility mapping of Lish river basin of eastern Darjeeling Himalaya[J].Advances in Space Research,2018,62(11):3114-3132.
[3]Giovanni L,Rocco P,Francis C.Landslide susceptibility mapping using a fuzzy approach[J].Procedia Engineering,2016,161:380-387.
[4]Luigi L,Martin M P.Presenting logistic regression-based landslide susceptibility results[J].Engineering Geology,2018,244:14-24.
[5]YANG Jintao,SONG Chao,YANG Yang.New method for landslide susceptibility mapping supported by spatial logistic regression and GeoDetector:A case study of Duwen Highway Basin,Sichuan Province[J].Geomorphology,2019,324:62-71.
[6]Aditian A,Kubota T,Shinohara Y.Comparison of GIS-based landslide susceptibility models using frequency ratio,logistic regression,and artificial neural network in a tertiary region of Ambon,Indonesia[J].Geomorphology,2018,318:101-111.
[7]Binh T P,Ataollah S,Dieu T B.A hybrid machine learning ensemble approach based on a Radial Basis Function neural network and Rotation Forest for landslide susceptibility modeling:A case study in the Himalayan area,India[J].International Journal of Sediment Research,2018,33(2):157-170.
[8]HUANG Yu,ZHAO Lu.Review on landslide susceptibility mapping using support vector machines[J].Catena,2018,165:520-529.
[9]王卫东,陈燕平,钟晟.应用CF和Logistic回归模型编制滑坡危险性区划图[J].中南大学学报(自然科学版),2009(4):1127-1132.WANG Weidong,CHEN Yanping,ZHONG Sheng.Landslide susceptibility mapped with CF and Logistic regression model[J].Journal of Central South University(Science and Technology),2009(4):1127-1132.
[10]黄发明,殷坤龙,蒋水华.基于聚类分析和支持向量机的滑坡易发性评价[J].岩土力学与工程学报,2018,37(1):156-167.HUANG Faming,YIN Kunlong,JIANG Shuihua.Landslide susceptibility evaluation based on cluster analysis and support vector machine[J].Chinese Journal of Rock Mechanics and Engineering,2018,37(1):156-167.
[11]雷鹏,蒋廷耀.基于PCA和SVM算法的滑坡稳定性分析研究[J].科技视界,2015,14(6):92-97.LEI Peng,JIANG Tingyao.Analysis of landslide stability based on PCA and SVM algorithms[J].Science&Technology,Vision,2015,14(6):92-97.
[12]齐信,黄波林,刘广宁,等.基于GIS技术和频率比模型的三峡地区秭归向斜盆地滑坡敏感性评价[J].地质力学学报,2017,23(1):97-104.QI Xin,HUANG Bolin,LIU Guangning,et al.Sensitivity evaluation of landslides in the Zigui inclined basin in the Three gorges area based on gis technology and frequency ratio model[J].Journal of Geomechanics,2017,23(1):97-104.
[13]陈冰梅,樊晓平,周志明,等.支持向量机原理及展望[J].制造业自动化,2010,32(12):136-138.CHEN Bingmei,FAN Xiaoping,ZHOU Zhiming,et al.The principle and prospect of support vector machine[J].Manufacturing Automation,2010,32(12):136-138.
[14]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 susceptibility evaluation based on support vector machine with GIS support[J].Scientia Geographica Sinica,2008,28(6):838-841.
[15]Edson D,Jacques W.Empirical comparison of crossvalidation and internal metrics for tuning SVMhyperparameters[J].Pattern Recognition Letters,2017,88:6-11.
[16]Eslami M,Shadfar S,Mohammadi-Torkashvand A.Assessment of density area and LNRF models in landslide hazard zonation(Case study:Alamout watershed,Qazvin Province,Iran)[J].Acta Ecologica Sinica,2018,19:1-8.
[2]Mandal B,Mandal S.Analytical hierarchy process(AHP)based landslide susceptibility mapping of Lish river basin of eastern Darjeeling Himalaya[J].Advances in Space Research,2018,62(11):3114-3132.
[3]Giovanni L,Rocco P,Francis C.Landslide susceptibility mapping using a fuzzy approach[J].Procedia Engineering,2016,161:380-387.
[4]Luigi L,Martin M P.Presenting logistic regression-based landslide susceptibility results[J].Engineering Geology,2018,244:14-24.
[5]YANG Jintao,SONG Chao,YANG Yang.New method for landslide susceptibility mapping supported by spatial logistic regression and GeoDetector:A case study of Duwen Highway Basin,Sichuan Province[J].Geomorphology,2019,324:62-71.
[6]Aditian A,Kubota T,Shinohara Y.Comparison of GIS-based landslide susceptibility models using frequency ratio,logistic regression,and artificial neural network in a tertiary region of Ambon,Indonesia[J].Geomorphology,2018,318:101-111.
[7]Binh T P,Ataollah S,Dieu T B.A hybrid machine learning ensemble approach based on a Radial Basis Function neural network and Rotation Forest for landslide susceptibility modeling:A case study in the Himalayan area,India[J].International Journal of Sediment Research,2018,33(2):157-170.
[8]HUANG Yu,ZHAO Lu.Review on landslide susceptibility mapping using support vector machines[J].Catena,2018,165:520-529.
[9]王卫东,陈燕平,钟晟.应用CF和Logistic回归模型编制滑坡危险性区划图[J].中南大学学报(自然科学版),2009(4):1127-1132.WANG Weidong,CHEN Yanping,ZHONG Sheng.Landslide susceptibility mapped with CF and Logistic regression model[J].Journal of Central South University(Science and Technology),2009(4):1127-1132.
[10]黄发明,殷坤龙,蒋水华.基于聚类分析和支持向量机的滑坡易发性评价[J].岩土力学与工程学报,2018,37(1):156-167.HUANG Faming,YIN Kunlong,JIANG Shuihua.Landslide susceptibility evaluation based on cluster analysis and support vector machine[J].Chinese Journal of Rock Mechanics and Engineering,2018,37(1):156-167.
[11]雷鹏,蒋廷耀.基于PCA和SVM算法的滑坡稳定性分析研究[J].科技视界,2015,14(6):92-97.LEI Peng,JIANG Tingyao.Analysis of landslide stability based on PCA and SVM algorithms[J].Science&Technology,Vision,2015,14(6):92-97.
[12]齐信,黄波林,刘广宁,等.基于GIS技术和频率比模型的三峡地区秭归向斜盆地滑坡敏感性评价[J].地质力学学报,2017,23(1):97-104.QI Xin,HUANG Bolin,LIU Guangning,et al.Sensitivity evaluation of landslides in the Zigui inclined basin in the Three gorges area based on gis technology and frequency ratio model[J].Journal of Geomechanics,2017,23(1):97-104.
[13]陈冰梅,樊晓平,周志明,等.支持向量机原理及展望[J].制造业自动化,2010,32(12):136-138.CHEN Bingmei,FAN Xiaoping,ZHOU Zhiming,et al.The principle and prospect of support vector machine[J].Manufacturing Automation,2010,32(12):136-138.
[14]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 susceptibility evaluation based on support vector machine with GIS support[J].Scientia Geographica Sinica,2008,28(6):838-841.
[15]Edson D,Jacques W.Empirical comparison of crossvalidation and internal metrics for tuning SVMhyperparameters[J].Pattern Recognition Letters,2017,88:6-11.
[16]Eslami M,Shadfar S,Mohammadi-Torkashvand A.Assessment of density area and LNRF models in landslide hazard zonation(Case study:Alamout watershed,Qazvin Province,Iran)[J].Acta Ecologica Sinica,2018,19:1-8.