Regional Landslide Susceptibility Mapping Based on Grey Relational Degree Model
-
摘要: 数理统计和机器学习模型如支持向量机（support vector machine，SVM）等，在区域滑坡敏感性评价中得到广泛的应用.但这些模型的建模过程往往较复杂，如在对机器学习进行训练和测试时难以选取合理的非滑坡栅格单元，而且有较多的模型参数需要确定.为提高滑坡敏感性评价建模的效率和精度，提出基于灰色关联度的敏感性评价模型.灰色关联度模型能有效计算各比较样本与参考样本之间的定量的关联度，具有建模过程简洁和评价精度高的优点，该模型目前在区域滑坡敏感性评价中的应用还没有引起研究人员的足够关注且有待进一步拓展.拟将灰色关联度模型用于浙江省飞云江流域南田-雅梅图幅（南田地区）的滑坡敏感性评价，并将得到的评价结果与SVM模型的敏感性评价结果作对比分析.结果显示，灰色关联度模型在高和极高敏感区的滑坡预测精度优于SVM模型，而在中等敏感区的滑坡预测精度略低于SVM模型；整体而言，灰色关联度模型对整个南田地区滑坡敏感性分布的预测精度略高于SVM模型.对两个模型建模过程的对比结果显示，灰色关联度模型建模较简单，具有比SVM模型更高的建模效率，为滑坡敏感性评价提供了一种新思路.Abstract: Statistical and machine learning models, such as support vector machine (SVM), have been widely used to assess the landslide susceptibility. However, the modeling processes of statistical and machine learning model are generally complex.For example, it is difficult to select reasonable non-landslide grid cells when the machine learning models are trained and tested, and many model parameters need to be determined.In order to improve the efficiency and accuracy of the model used for landslide susceptibility assessment, the grey relational degree (GRD) model is proposed. The GRD model can efficiently calculate the quantitative relational degrees between the comparative samples and the reference sample, and it has the advantages of simple modeling process and accurate assessment results.However, few studies have been done on the GRD model.In this study, the GRD model is used to assess the landslide susceptibility in the Nantian and Yamei maps (Nantian area) in the Feiyunjiang River basin, Zhejiang Province of China, and the assessment results of the GRD model are compared with those of the SVM model. The results show that the GRD model has higher prediction rate than the SVM model in the high and very high susceptibility areas, and has slightly lower prediction rate than the SVM in the moderate susceptibility area. On the whole, the GRD model has slightly higher prediction rate than the SVM for landslide susceptibility assessment in Nantian area. Meanwhile, the results also show that the model process of GRD is simple, it has higher efficiency than the SVM. The GRD model provides a novel idea for landslide susceptibility assessment.
-
Key words:
- landslide /
- susceptibility assessment /
- grey relational degree /
- support vector machine
-
图 3 南田地区距离水系的距离(a)，岩土类型(b)
Fig. 3. Distance to river (a) and Lithology map (b) in Nantian area
图 5 基于灰色关联度(a)和SVM (b)模型的南田地区滑坡敏感性分布图
Fig. 5. Landslide susceptibility maps produced by GRD (a) and SVM (b) models
图 6 灰色关联度和SVM模型计算的滑坡敏感性预测率曲线
Fig. 6. Prediction rate curves of landslide susceptibility indexes calculated respectively using GRD and SVM models
表 1 各基础环境因子频率比值
Table 1. Frequency ratios of all environmental factors
基础环境因子 变量值 类型 全区栅格数 栅格(%) 滑坡内栅格数 坡内栅格比例(%) 频率比 高程(m) 135.827~276.951 连续型 106 014 10.464 13 1.641 0.157 276.951~428.184 159 816 15.775 232 29.293 1.857 428.184~569.335 176 959 17.467 191 24.116 1.381 569.335~695.363 217 641 21.482 244 30.808 1.434 695.363~816.350 143 389 14.153 77 9.722 0.687 816.350~947.419 105 862 10.449 24 3.030 0.290 947.419~1 098.652 71 959 7.103 11 1.389 0.196 1 098.652~1 421.283 31 473 3.107 0 0 0 坡度(°) 0~7.680 0 连续型 97 058 9.580 25 3.157 0.329 7.680 0~15.360 5 148 727 14.680 152 19.192 1.307 15.360 5~22.187 4 165 790 16.364 205 25.884 1.582 22.187 4~28.445 4 169 427 16.723 179 22.601 1.351 28.445 4~34.703 4 172 848 17.061 151 19.066 1.117 34.703 4~40.961 4 137 680 13.590 66 8.333 0.613 40.961 4~48.357 2 87 069 8.594 13 1.641 0.191 48.357 2~72.535 8 34 514 3.407 1 0.126 0.037 坡向(°) -1 连续型 15 700 1.550 0 0 0 0~22.5, 337.5~360.0 118 694 11.716 32 4.040 0.345 22.5~67.5 123 105 12.152 35 4.419 0.364 67.5~112.5 131 161 12.946 61 7.702 0.595 112.5~157.5 130 196 12.851 107 13.510 1.051 157.5~202.5 137 048 13.527 222 28.030 2.072 202.5~247.5 130 046 12.836 181 22.854 1.780 247.5~292.5 119 843 11.829 94 11.869 1.003 292.5~337.5 107 320 10.593 60 7.576 0.715 剖面曲率(m-1) 0~4.067 连续型 174 629 17.237 130 16.414 0.952 4.067~7.579 242 442 23.930 235 29.672 1.240 7.579~10.906 206 702 20.403 194 24.495 1.201 10.906~14.418 160 004 15.793 112 14.141 0.895 14.418~18.115 107 668 10.627 73 9.217 0.867 18.115~22.552 70 726 6.981 33 4.167 0.597 22.552~28.467 37 984 3.749 14 1.768 0.471 28.467~47.136 12 958 1.279 1 0.126 0.099 平面曲率(m-1) 0~11.182 连续型 83 192 8.212 103 13.005 1.584 11.182~21.086 133 628 13.190 126 15.909 1.206 21.086~30.67 136 335 13.457 161 20.328 1.511 30.670~40.574 134 844 13.310 139 17.551 1.319 40.574~50.478 126 936 12.529 107 13.510 1.078 50.478~60.702 126 433 12.480 59 7.449 0.597 60.702~70.925 120 128 11.857 54 6.818 0.575 70.925~81.468 151 617 14.965 43 5.429 0.363 地形起伏度(m) 0~93.107 连续型 108 223 10.682 58 7.323 0.686 93.107~152.791 149 609 14.767 146 18.434 1.248 152.791~202.926 180 942 17.860 188 23.737 1.329 202.926~250.673 198 057 19.549 214 27.020 1.382 250.673~296.033 166 547 16.439 128 16.162 0.983 296.033~343.780 120 824 11.926 48 6.060 0.508 343.780 0~408.238 8 68 576 6.769 10 1.262 0.187 408.238 8~608.777 2 20 335 2.007 0 0 0 距离水系的距离(m) 450~ 离散型 244 402 24.124 69 8.712 0.361 300~450 175 748 17.347 90 11.363 0.655 150~300 255 541 25.223 244 30.808 1.221 0~150 337 422 33.305 389 49.116 1.475 地层岩性 火山沉积岩 离散型 413 637 40.828 496 62.626 1.534 火山碎屑岩，火山熔岩 505 243 49.870 238 30.051 0.603 侵入岩，潜火山岩 94 233 9.301 58 7.323 0.787 建筑物指数 0~31 连续型 118 670 11.713 35 4.419 0.377 31~60 193 816 19.131 63 7.955 0.416 60~86 217 602 21.479 71 8.965 0.417 86~113 183 300 18.093 115 14.520 0.803 113~145 114 893 11.341 142 17.929 1.581 145~182 72 815 7.187 153 19.318 2.688 182~224 59 704 5.893 111 14.015 2.378 224~255 52 313 5.164 102 12.879 2.494 植被覆盖度 0~30 连续型 26 080 2.574 0 0 0 30~70 108 691 10.728 42 5.303 0.494 70~102 122 355 12.077 104 13.131 1.087 102~132 148 526 14.660 156 19.697 1.344 132~162 163 354 16.124 188 23.737 1.472 162~192 165 830 16.368 163 20.581 1.257 192~224 160 443 15.837 102 12.879 0.813 224~255 117 834 11.631 37 4.672 0.402 
下载: 导出CSV
表 2 灰色关联度模型评价滑坡敏感性等级的频率比值
Table 2. Frequency ratios of the five susceptibility classes assessed by GRD model
敏感性等级 研究区栅格 栅格比例(%) 滑坡内栅格数 滑坡内栅格比例(%) 频率比值 极高 81 829 8.077 308 38.889 4.815 高 207 359 20.468 258 32.576 1.592 中等 300 839 29.695 164 20.707 0.697 低 284 925 28.124 56 7.071 0.251 极低 138 161 13.637 6 0.758 0.056
下载: 导出CSV
表 3 南田地区SVM模型评价滑坡敏感性等级的频率比值
Table 3. Frequency ratios of the five susceptibility classes assessed by SVM model in Nantian area
敏感性等级 研究区栅格 栅格比例(%) 滑坡内栅格数 滑坡内栅格比例(%) 频率比值 极高 107 736 10.634 310 39.141 3.681 高 234 520 23.149 303 38.258 1.653 中等 293 221 28.943 127 16.035 0.554 低 252 450 24.918 47 5.934 0.238 极低 125 186 12.357 5 0.631 0.051
下载: 导出CSV
-
Bui D., Pradhan B., Lofman O., et al.2012a.Landslide Susceptibility Assessment in the Hoa Binh Province of Vietnam:A Comparison of the Levenberg-Marquardt and Bayesian Regularized Neural Networks.Geomorphology, 171-172:12-29. https://doi.org/10.1016/j.geomorph.2012.04.023 Bui D., Pradhan B., Lofman O., et al.2012b.Spatial Prediction of Landslide Hazards in Hoa Binh Province (Vietnam):A Comparative Assessment of the Efficacy of Evidential Belief Functions and Fuzzy Logic Models.Catena, 96:28-40. https://doi.org/10.1016/j.catena.2012.04.001 Chung C.J., Fabbri A.G..2008.Predicting Landslides for Risk Analysis-Spatial Models Tested by a Cross-Validation Technique.Geomorphology, 94(3-4):438-452. https://doi.org/10.1016/j.geomorph.2006.12.036 Deng J.L..1989.Introduction to Grey System Theory.Journal of Grey System, 1(1):1-24. doi: 10.1017-S1727719100002847/ Feng H.J., Zhou A.G., Yu J.J., et al.2016.A Comparative Study on Plum-Rain-Triggered Landslide Susceptibility Assessment Models in West Zhejiang Province.Earth Science, 41(3):403-415(in Chinese with English abstract). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dqkx201603007 Hong H.Y., Pradhan B., Xu C., et al.2015.Spatial Prediction of Landslide Hazard at the Yihuang Area (China) Using Two-Class Kernel Logistic Regression, Alternating Decision Tree and Support Vector Machines.Catena, 133:266-281. https://doi.org/10.1016/j.catena.2015.05.019 Huang F.M., Huang J.S., Jiang S.H., et al.2017a.Landslide Displacement Prediction Based on Multivariate Chaotic Model and Extreme Learning Machine.Engineering Geology, 218:173-186. https://doi.org/10.1016/j.enggeo.2017.01.016 Huang F.M., Yin K.L., Huang J.S., et al.2017b.Landslide Susceptibility Mapping Based on Self-Organizing-Map Network and Extreme Learning Machine.Engineering Geology, 223:11-22. https://doi.org/10.1016/j.enggeo.2017.04.013 Huang F.M., Yin K.L., Tao H., et al.2016a.Influencing Factor Analysis and Displacement Prediction in Reservoir Landslides-A Case Study of Three Gorges Reservoir (China).Tehnickivjesnik-Technical Gazette, 23(2):617-626. https://doi.org/10.17559/tv-20150314105216 Huang F.M., Yin K.L., Zhang G.R., et al.2016b.Landslide Displacement Prediction Using Discrete Wavelet Transform and Extreme Learning Machine Based on Chaos Theory.Environmental Earth Sciences, 75(20):1376. https://doi.org/10.1007/s12665-016-6133-0 Huang F.M., Yin K.L., Zhang G.R., et al.2015.Landslide Groundwater Level Time Series Prediction Based on Phase Space Reconstruction and Wavelet Analysis-Support Vector Machine Optimized by PSO Algorithm.Earth Science, 40(7):1254-1265(in Chinese with English abstract). http://d.old.wanfangdata.com.cn/Periodical/dqkx201507013 Huang W.D., Yang J.S., Chen J.C., et al.2010.Grey Relational Analysis of Physico-Chemical Variables and Water Body Reflectance of a Chi-Chi Earthquake Landslide-Dammed Lake Monitored by Spot Satellite.Journal of Grey System, 22(4):297-308. Kavzoglu T., Sahin E.K., Colkesen I..2014.Landslide Susceptibility Mapping Using GIS-Based Multi-Criteria Decision Analysis, Support Vector Machines, and Logistic Regression.Landslides, 11(3):425-439. https://doi.org/10.1007/s10346-013-0391-7 Lee S., Ryu J.H., Kim I.S..2007.Landslide Susceptibility Analysis and Its Verification Using Likelihood Ratio, Logistic Regression, and Artificial Neural Network Models:Case Study of Youngin, Korea.Landslides, 4(4):327-338. https://doi.org/10.1007/s10346-007-0088-x Li J.L., Ma D.H., Wang W..2016.Assessment of Potential Seismic Landslide Hazard Based on Evidence Theory and Entropy Weight Grey Incidence.Journal of Central South University(Science and Technology), 47(5):1730-1736(in Chinese with English abstract). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zngydxxb201605036 Li X.Z., Wang C.H., Deng H.Y..2010.Application of Grey Relation Analysis and Distance Discrimination Analysis Methods in Discriminating Potential Landslides of Xiluodu Reservoir Area.The Chinese Journal of Geological Hazard and Control, 21(4):77-81(in Chinese with English abstract). http://en.cnki.com.cn/Article_en/CJFDTOTAL-ZGDH201004016.htm Li Y.Y., Huang J.S., Jiang S.H., et al.2017.A Web-Based GPS System for Displacement Monitoring and Failure Mechanism Analysis of Reservoir Landslide.Scientific Reports, 7(1). https://doi.org/10.1038/s41598-017-17507-7 Liu Y.L., Huang X.L., Duan J., et al.2017.The Assessment of Traffic Accident Risk Based on Grey Relational Analysis and Fuzzy Comprehensive Evaluation Method.Natural Hazards, 88(3):1409-1422. https://doi.org/10.1007/s11069-017-2923-2 Liu S.F., Cai H., Yang Y.J., et al.2013.Advance in Grey Incidence Analysis Modelling.Systems Engineering-Theory & Practice, 33(8):2041-2046(in Chinese with English abstract). http://ieeeexplore.com/xpl/articleDetails.jsp?tp=&arnumber=6083947 Lu X.C., Gong M., Tang L.S., et al.2006.Improved Grey Association Analysis Method Based on T-S Fuzzy Neural Network Model-Application in Evaluating of Landslide Hazards in Guangdong Province.The Chinese Journal of Geological Hazard and Control, 17(3):143-146(in Chinese with English abstract). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zgdzzhyfzxb200603034 MarjanovićM., Kovaevi M., Bajat B., et al.2011.Landslide Susceptibility Assessment Using SVM Machine Learning Algorithm.Engineering Geology, 123(3):225-234. https://doi.org/10.1016/j.enggeo.2011.09.006 Peng L., Niu R.Q., Huang B., et al.2014.Landslide Susceptibility Mapping Based on Rough Set Theory and Support Vector Machines:A Case of the Three Gorges Area, China.Geomorphology, 204:287-301. https://doi.org/10.1016/j.geomorph.2013.08.013 Pham B.T., Tien Bui D., Prakash I., et al.2017.Hybrid Integration of Multilayer Perceptron Neural Networks and Machine Learning Ensembles for Landslide Susceptibility Assessment at Himalayan Area (India) Using GIS.Catena, 149:52-63. https://doi.org/10.1016/j.catena.2016.09.007 Pradhan B..2013.A Comparative Study on the Predictive Ability of the Decision Tree, Support Vector Machine and Neuro-Fuzzy Models in Landslide Susceptibility Mapping Using GIS.Computers & Geosciences, 51:350-365. https://doi.org/10.1016/j.cageo.2012.08.023 Yao X., Tham L.G., Dai F.C..2008.Landslide Susceptibility Mapping Based on Support Vector Machine:A Case Study on Natural Slopes of Hong Kong, China.Geomorphology, 101(4):572-582. https://doi.org/10.1016/j.geomorph.2008.02.011 Tsangaratos P., Benardos A..2014.Estimating Landslide Susceptibility through a Artificial Neural Network Classifier.Natural Hazards, 74(3):1489-1516. https://doi.org/10.1007/s11069-014-1245-x Wang J., Guo J., Wang W.D., et al.2012.Application and Comparison of Weighted Linear Combination Model and Logistic Regression Model in Landslide Susceptibility Mapping.Journal of Central South University(Science and Technology), 43(5):1932-1939(in Chinese with English abstract). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zngydxxb201205050 Wang J.J., Yin K.L., Xiao L.L..2014.Landslide Susceptibility Assessment Based on GIS and Weighted Information Value:A Case Study of Wanzhou District, three Gorges Reservoir.Chinese Journal of Rock Mechanics and Engineering, 33(4):797-808(in Chinese with English abstract). http://en.cnki.com.cn/Article_en/CJFDTotal-YSLX201404018.htm Wu Y.P., Chen L.X., Cheng C., et al.2017.GIS-Based Landslide Hazard Predicting System and Its Real-Time Test during a Typhoon, Zhejiang Province, Southeast China.Engineering Geology, 175:9-21. https://doi.org/10.1016/j.enggeo.2014.03.005 Wu Y.P., Zhang Q.X., Tang H.M., et al.2014.Landslide Hazard Warning Based on Effective Rainfall Intensity.Earth Science, 39(7):889-895(in Chinese with English abstract). Xu X.H., Shang Y.Q..2009.Integrated Zonation of Landslide Stability.Chinese Journal of Geotechnical Engineering, 31(5):669-674(in Chinese with English abstract). http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=yslxygcxb201405016 Yu J.M., Zhang X.N., Xiong C.L..2017.A Methodology for Evaluating Micro-Surfacing Treatment on Asphalt Pavement Based on Grey System Models and Grey Rational Degree Theory.Construction and Building Materials, 150:214-226. https://doi.org/10.13039/501100005015 Zhu L., Lu Y.M., Luo J.P..2013.Regional Landslide Susceptibility Model Based on Gray and Elman Neural Networks.Journal of Natural Disasters, 22(5):120-126(in Chinese with English abstract). http://en.cnki.com.cn/Article_en/CJFDTOTAL-ZRZH201305017.htm Zhu X.X., Wang Y.M., Gong X.F..2013.Assessment of the Landslide Hazards in Wencheng County of Zhejiang Province.The Chinese Journal of Geological Hazard and Control, 24(3):13-18(in Chinese with English abstract). http://d.old.wanfangdata.com.cn/Periodical/zgdzzhyfzxb201303003 冯杭建, 周爱国, 俞剑君, 等.2016.浙西梅雨滑坡易发性评价模型对比.地球科学, 41(3):403-415. http://earth-science.net/WebPage/Article.aspx?id=3259 黄发明, 殷坤龙, 张桂荣, 等.2015.基于相空间重构和小波分析-粒子群向量机的滑坡地下水位预测.地球科学, 40(7):1254-1265. http://earth-science.net/WebPage/Article.aspx?id=3113 李嘉良, 马东辉, 王威.2016.基于证据理论和熵权灰色关联的潜在地震滑坡危险性评价.中南大学学报(自然科学版), 47(5):1730-1736. http://d.old.wanfangdata.com.cn/Periodical/zngydxxb201605036 李秀珍, 王成华, 邓宏艳.2010.灰色关联度法和距离判别分析法在溪洛渡库区潜在滑坡判识中的应用.中国地质灾害与防治学报, 21(4):77-81. doi: 10.3969/j.issn.1003-8035.2010.04.014 刘思峰, 蔡华, 杨英杰, 等.2013.灰色关联分析模型研究进展.系统工程理论与实践, 33(8):2041-2046. doi: 10.3969/j.issn.1000-6788.2013.08.018 陆显超, 龚民, 汤连生, 等.2006.基于T-S模糊神经系统的灰色关联分析方法——以广东省滑坡危险性评价为例.中国地质灾害与防治学报, 17(3):143-146. doi: 10.3969/j.issn.1003-8035.2006.03.034 王佳佳, 殷坤龙, 肖莉丽.2014.基于GIS和信息量的滑坡灾害易发性评价——以三峡库区万州区为例.岩石力学与工程学报, 33(4):797-808. http://d.old.wanfangdata.com.cn/Periodical/yslxygcxb201404018 王进, 郭靖, 王卫东, 等.2012.权重线性组合与逻辑回归模型在滑坡易发性区划中的应用与比较.中南大学学报(自然科学版), 43(5):1932-1939. http://d.old.wanfangdata.com.cn/Periodical/zngydxxb201205050 吴益平, 张秋霞, 唐辉明, 等.2014.基于有效降雨强度的滑坡灾害危险性预警.地球科学, 39(7):889-895. http://earth-science.net/WebPage/Article.aspx?id=2892 徐兴华, 尚岳全.2009.滑坡稳定性综合区划研究.岩土工程学报, 31(5):669-674. doi: 10.3321/j.issn:1000-4548.2009.05.004 朱莉, 卢毅敏, 罗建平.2013.基于灰色-Elman神经网络的区域滑坡易发性模型.自然灾害学报, 22(5):120-126. http://www.cnki.com.cn/Article/CJFDTotal-ZRZH201305017.htm 朱晓曦, 王一鸣, 龚新法.2013.浙江省文成县滑坡灾害危险性评价.中国地质灾害与防治学报, 24(3):13-18. http://d.old.wanfangdata.com.cn/Periodical/zgdzzhyfzxb201303003 -
点击查看大图
图(6) / 表(3)
计量
- 文章访问数: 4638
- HTML全文浏览量: 2147
- PDF下载量: 62
- 被引次数: 0
