基于GIS与ANN模型的地震滑坡易发性区划
|
摘要
基于遥感数据、地理信息系统(GIS)技术和人工神经网络(ANN)模型,开展地震滑坡易发性区划研究。2010年4月14日玉树地震后,基于航片与卫星影像目视解译,并辅以野外调查的方法,在地震区圈定了2036处地震诱发滑坡。选择高程、坡度、坡向、斜坡曲率、坡位、与水系距离、地层岩性、与断裂距离、与公路距离、归一化植被指数(NDVI)、与同震地表破裂距离、地震动峰值加速度(PGA)共12个因子作为地震滑坡易发性评价因子。这些因子均是应用GIS技术与遥感影像处理技术,基于地形数据、地质数据、遥感数据得到。训练样本中的滑动样本有两组,一组是滑坡区整个单滑坡体的质心位置,另一组是滑坡滑源区滑前的坡体高程最高的位置。应用这12个影响因子,分别采用这两组评价样本,基于ANN模型建立地震滑坡易发性索引图,基于GIS工具建立地震滑坡易发性分级图。分别应用训练样本中滑坡分布的点数据去检验各自的结果正确率,正确率分别为81.53%与81.29%,表明ANN模型是一种高效科学的地震滑坡易发性区划模型。
The aim of this study was to carry out earthquake triggered landslide susceptibility zonation using remote sensing data,GIS technology,and artificial neural network(ANN) model.Landslides triggered by the 2010 Yushu earthquake were delineated in the study area from interpretation of aerial photographs and satellite images,verified by selected field checking.Twelve factors,including elevation,slope angle,slope aspect,slope curvature,slope position,drainages,lithology,faults,roads,normalized difference vegetation index(NDVI),co-seismic main surface fault-ruptures,and peak ground acceleration(PGA) were selected as earthquake triggered landslide susceptibility factors.These factors were obtained from topographical and geological data and satellite images using GIS technology and image processing.Two types of landslide locations were selected as landsliding training samples.One was the centroid location of each landslide.The other was the top location of each landslide.These factors and the two types of training samples were used with ANN model to analyze landslides susceptibility index.Two landslide susceptibility zonation maps were created by using GIS tools.The landslide locations were used to verify results of the landslide susceptibility maps respectively and to compare them.The success rates of the two results were 81.53% and 81.29% respectively.This showed the ANN model was an effective tool for earthquake triggered landslide susceptibility zonation.
The aim of this study was to carry out earthquake triggered landslide susceptibility zonation using remote sensing data,GIS technology,and artificial neural network(ANN) model.Landslides triggered by the 2010 Yushu earthquake were delineated in the study area from interpretation of aerial photographs and satellite images,verified by selected field checking.Twelve factors,including elevation,slope angle,slope aspect,slope curvature,slope position,drainages,lithology,faults,roads,normalized difference vegetation index(NDVI),co-seismic main surface fault-ruptures,and peak ground acceleration(PGA) were selected as earthquake triggered landslide susceptibility factors.These factors were obtained from topographical and geological data and satellite images using GIS technology and image processing.Two types of landslide locations were selected as landsliding training samples.One was the centroid location of each landslide.The other was the top location of each landslide.These factors and the two types of training samples were used with ANN model to analyze landslides susceptibility index.Two landslide susceptibility zonation maps were created by using GIS tools.The landslide locations were used to verify results of the landslide susceptibility maps respectively and to compare them.The success rates of the two results were 81.53% and 81.29% respectively.This showed the ANN model was an effective tool for earthquake triggered landslide susceptibility zonation.
引文
[1]殷跃平,张永双,马寅生,等.青海玉树Ms7.1级地震地质灾害主要特征[J].工程地质学报,2010,18(3):289-296.
[2]殷跃平,田廷山,李文渊,等.青海玉树地震地质灾害调查[EB/OL].2010,http://www.gcdz.org/CN/article/downloa-dArticleFile.do?attachType=PDF&id=8550.
[3]赵家绪,李玉军,张力征,等.青海玉树“4.14”地震灾区地质灾害应急排查报告[R].西宁:青海省国土资源厅,2010.
[4]许冲,徐锡伟,于贵华.玉树地震滑坡特征、机制、分布调查[J].地震地质,2011,32(4):1-10.
[5]许冲,徐锡伟,戴福初,等.玉树地震滑坡特征控制变量统计分析[J].工程地质学报,2011,19(4):505-510.
[6]Arora M K,Das Gupta A S,Gupta R P.An artificial neuralnetwork approach for landslide hazard zonation in the Bhagi-rathi(Ganga)Valley,Himalayas[J].International Journal ofRemote Sensing,2004,25(3):559-572.
[7]Caniani D,Pascale S,Sdao F,et al.Neural networks andlandslide susceptibility:A case study of the urban area of Po-tenza[J].Natural Hazards,2008,45(1):55-72.
[8]Chauhan S,Sharma M,Arora M K,et al.Landslide suscepti-bility zonation through ratings derived from artificial neuralNetwork[J].International Journal of Applied Earth Observa-tion and Geoinformation,2010,12(5):340-350.
[9]Choi J,Oh H J,Won J S,et al.Validation of an artificial neu-ral network model for landslide susceptibility mapping[J].Environmental Earth Sciences,2010,60(3):473-483.
[10]Ercanoglu M.Landslide susceptibility assessment of SE Bartin(West Black Sea region,Turkey)by artificial neural networks[J].Natural Hazards and Earth System Sciences,2005,5(6):979-992.
[11]Lee C F,Ye H,Yeung M R,et al.AIGIS-based methodologyfor natural terrain landslide susceptibility mapping in HongKong[J].Episodes,2001,24(3):150-160.
[12]Pavel M,Fannin R J,Nelson J D.Replication of a terrain sta-bility mapping using an artificial neural network[J].Geomor-phology,2008,97(3/4):356-373.
[13]Pradhan B,Lee S.Landslide risk analysis using artificial neu-ral network model focussing on different training sites[J].In-ternational Journal of Physical Sciences,2009,4(1):1-15.
[14]Wang H B,Sassa K.Rainfall-induced landslide hazard assess-ment using artificial neural networks[J].Earth SurfaceProcesses and Landforms,2006,31(2):235-247.
[15]Wu Q,Ye S Y,Wu X,et al.Risk assessment of earth frac-tures by constructing an intrinsic vulnerability map,a specificvulnerability map,and a hazard map,using Yuci City,Shanxi,China as an example[J].Environmental Geology,2004,46(1):104-112.
[16]Yesilnacar E,Topal T.Landslide susceptibility mapping:Acomparison of logistic regression and neural networks methodsin a medium scale study,Hendek region(Turkey)[J].Engi-neering Geology,2005,79(3/4):251-266.
[17]Yilmaz I.Comparison of landslide susceptibility mappingmethodologies for Koyulhisar,Turkey:Conditional probabili-ty,logistic regression,artificial neural networks,and supportvector machine[J].Environmental Earth Sciences,2010,61(4):821-836.
[18]Lee S,Evangelista D G.Earthquake-induced landslide-suscep-tibility mapping using an artificial neural network[J].NaturalHazards and Earth System Sciences,2006,6(5):687-695.
[19]Lee C T.Methodology for estimation of earthquake-inducedlandslide probability and result evaluation[C]∥Anon.Geo-physical Research Abstracts.[S.l.]:[s.n.],2006,8:05759.
[20]陈晓利,赵健,叶洪.应用径向基概率神经网络研究地震滑坡[J].地震地质,2006,28(3):430-440.
[21]USGS.Magnitude 6.9:Southern Qinghai,China,2010April13 23:49:38UTC[EB/OL].2010,http://earthquake.usgs.gov/earthquakes/eqinthenews/2010/us2010vacp/.
[22]Xu X W,Yu G H,Sun X Z.Yushu earthquake slip:Implica-tion of great earthquake migration along boundary fault systemof Bayan Har block,Tibetan Plateau[C]∥American Geophys-ical Union.Fall Meeting 2010.2010,abstract#T22A-04.
[23]Pan J,Li H,Xu Z,et al.Surface rupture characteristics andrupture mechanics of the Yushu earthquake(Ms7.1),14/04/2010[C].American Geophysical Union,Fall Meeting 2010,2010,abstract#T54B-08.
[24]张军龙,陈长云,胡朝忠,等.玉树Ms7.1地震地表破裂带及其同震位移分布[J].地震,2010,30(3):1-12.
[25]孙鑫喆,徐锡伟,陈立春,等.青海玉树Ms7.1地震两个典型地点的地表破裂特征[J].地震地质,2010,32(2):338-344.
[26]陈立春,王虎,冉勇康,等.玉树Ms7.1级地震地表破裂与历史大地震[J].科学通报,2010,55(13):1200-1205.
[27]刘云华,单新建,屈春燕,等.青海玉树Ms7.1级地震地表形变场特征研究[J].中国科学:D辑,2010,40(10):1310-1320.
[28]马寅生,张永双,胡道功,等.玉树地震地表破裂与宏观震中[J].地质力学学报,2010,16(2):115-128.
[29]石峰,何宏林,张英.青海玉树Ms7.1级地震地表破裂带的遥感影像解译[J].震灾防御技术,2010,5(2):220-227.
[30]Weiss A D.Topographic position and landforms analysis[C]∥Anon.Environmental systems research institute.Inc.Interna-tional user Conference,Sqn Diego,CA,USA,9-13,July 2001.
[2]殷跃平,田廷山,李文渊,等.青海玉树地震地质灾害调查[EB/OL].2010,http://www.gcdz.org/CN/article/downloa-dArticleFile.do?attachType=PDF&id=8550.
[3]赵家绪,李玉军,张力征,等.青海玉树“4.14”地震灾区地质灾害应急排查报告[R].西宁:青海省国土资源厅,2010.
[4]许冲,徐锡伟,于贵华.玉树地震滑坡特征、机制、分布调查[J].地震地质,2011,32(4):1-10.
[5]许冲,徐锡伟,戴福初,等.玉树地震滑坡特征控制变量统计分析[J].工程地质学报,2011,19(4):505-510.
[6]Arora M K,Das Gupta A S,Gupta R P.An artificial neuralnetwork approach for landslide hazard zonation in the Bhagi-rathi(Ganga)Valley,Himalayas[J].International Journal ofRemote Sensing,2004,25(3):559-572.
[7]Caniani D,Pascale S,Sdao F,et al.Neural networks andlandslide susceptibility:A case study of the urban area of Po-tenza[J].Natural Hazards,2008,45(1):55-72.
[8]Chauhan S,Sharma M,Arora M K,et al.Landslide suscepti-bility zonation through ratings derived from artificial neuralNetwork[J].International Journal of Applied Earth Observa-tion and Geoinformation,2010,12(5):340-350.
[9]Choi J,Oh H J,Won J S,et al.Validation of an artificial neu-ral network model for landslide susceptibility mapping[J].Environmental Earth Sciences,2010,60(3):473-483.
[10]Ercanoglu M.Landslide susceptibility assessment of SE Bartin(West Black Sea region,Turkey)by artificial neural networks[J].Natural Hazards and Earth System Sciences,2005,5(6):979-992.
[11]Lee C F,Ye H,Yeung M R,et al.AIGIS-based methodologyfor natural terrain landslide susceptibility mapping in HongKong[J].Episodes,2001,24(3):150-160.
[12]Pavel M,Fannin R J,Nelson J D.Replication of a terrain sta-bility mapping using an artificial neural network[J].Geomor-phology,2008,97(3/4):356-373.
[13]Pradhan B,Lee S.Landslide risk analysis using artificial neu-ral network model focussing on different training sites[J].In-ternational Journal of Physical Sciences,2009,4(1):1-15.
[14]Wang H B,Sassa K.Rainfall-induced landslide hazard assess-ment using artificial neural networks[J].Earth SurfaceProcesses and Landforms,2006,31(2):235-247.
[15]Wu Q,Ye S Y,Wu X,et al.Risk assessment of earth frac-tures by constructing an intrinsic vulnerability map,a specificvulnerability map,and a hazard map,using Yuci City,Shanxi,China as an example[J].Environmental Geology,2004,46(1):104-112.
[16]Yesilnacar E,Topal T.Landslide susceptibility mapping:Acomparison of logistic regression and neural networks methodsin a medium scale study,Hendek region(Turkey)[J].Engi-neering Geology,2005,79(3/4):251-266.
[17]Yilmaz I.Comparison of landslide susceptibility mappingmethodologies for Koyulhisar,Turkey:Conditional probabili-ty,logistic regression,artificial neural networks,and supportvector machine[J].Environmental Earth Sciences,2010,61(4):821-836.
[18]Lee S,Evangelista D G.Earthquake-induced landslide-suscep-tibility mapping using an artificial neural network[J].NaturalHazards and Earth System Sciences,2006,6(5):687-695.
[19]Lee C T.Methodology for estimation of earthquake-inducedlandslide probability and result evaluation[C]∥Anon.Geo-physical Research Abstracts.[S.l.]:[s.n.],2006,8:05759.
[20]陈晓利,赵健,叶洪.应用径向基概率神经网络研究地震滑坡[J].地震地质,2006,28(3):430-440.
[21]USGS.Magnitude 6.9:Southern Qinghai,China,2010April13 23:49:38UTC[EB/OL].2010,http://earthquake.usgs.gov/earthquakes/eqinthenews/2010/us2010vacp/.
[22]Xu X W,Yu G H,Sun X Z.Yushu earthquake slip:Implica-tion of great earthquake migration along boundary fault systemof Bayan Har block,Tibetan Plateau[C]∥American Geophys-ical Union.Fall Meeting 2010.2010,abstract#T22A-04.
[23]Pan J,Li H,Xu Z,et al.Surface rupture characteristics andrupture mechanics of the Yushu earthquake(Ms7.1),14/04/2010[C].American Geophysical Union,Fall Meeting 2010,2010,abstract#T54B-08.
[24]张军龙,陈长云,胡朝忠,等.玉树Ms7.1地震地表破裂带及其同震位移分布[J].地震,2010,30(3):1-12.
[25]孙鑫喆,徐锡伟,陈立春,等.青海玉树Ms7.1地震两个典型地点的地表破裂特征[J].地震地质,2010,32(2):338-344.
[26]陈立春,王虎,冉勇康,等.玉树Ms7.1级地震地表破裂与历史大地震[J].科学通报,2010,55(13):1200-1205.
[27]刘云华,单新建,屈春燕,等.青海玉树Ms7.1级地震地表形变场特征研究[J].中国科学:D辑,2010,40(10):1310-1320.
[28]马寅生,张永双,胡道功,等.玉树地震地表破裂与宏观震中[J].地质力学学报,2010,16(2):115-128.
[29]石峰,何宏林,张英.青海玉树Ms7.1级地震地表破裂带的遥感影像解译[J].震灾防御技术,2010,5(2):220-227.
[30]Weiss A D.Topographic position and landforms analysis[C]∥Anon.Environmental systems research institute.Inc.Interna-tional user Conference,Sqn Diego,CA,USA,9-13,July 2001.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心