[1]曾 营,张迎宾*,张钟远,等.基于X-多层感知器耦合模型的滑坡易发性评价——以贵州省松桃自治县为例[J].山地学报,2023,(2):280-294.[doi:10.16089/j.cnki.1008-2786.000748]
　ZENG Ying,ZHANG Yingbin*,ZHANG Zhongyuan,et al.Landslide Susceptibility Evaluation Based on Coupled X-Multilayer Perceptron Model—a Case Study of Songtao Autonomous County of Guizhou Province, China[J].Mountain Research,2023,(2):280-294.[doi:10.16089/j.cnki.1008-2786.000748]
点击复制

基于X-多层感知器耦合模型的滑坡易发性评价——以贵州省松桃自治县为例
分享到：

《山地学报》[ISSN:1008-2186/CN:51-1516]

卷:
期数:
2023年第2期
页码:
280-294
栏目:
山地技术
出版日期:
2023-03-25

文章信息/Info

Title:
Landslide Susceptibility Evaluation Based on Coupled X-Multilayer Perceptron Model—a Case Study of Songtao Autonomous County of Guizhou Province, China
文章编号:
1008-2786-(2023)2-280-15
作者:
曾 营1; 张迎宾1*; 张钟远2; 柳 静1; 朱 辉1
(1.西南交通大学 土木工程学院,成都 610031; 2.哈尔滨工业大学 重庆研究院,重庆 400020)
Author(s):
ZENG Ying1; ZHANG Yingbin1*; ZHANG Zhongyuan2; LIU Jing1; ZHU Hui1
(1. School of Civil Engineering, Southwest Jiaotong University, Chengdu 610031, China; 2. Chongqing Re-search Institute of Harbin Institute of Technology, Chongqing 400020, China )
关键词:
滑坡易发性;  多层感知器;  NFR模型;  I模型;  模型耦合;  贵州省松桃县
Keywords:
landslide susceptibility;  multiple perceptron;  Normalized Frequency Ratio model;  Information Value model;  coupled model;  Songtao County;  Guizhou province
分类号:
P642.4
DOI:
10.16089/j.cnki.1008-2786.000748
文献标志码:
A
摘要:
滑坡易发性评价是区域滑坡灾害风险评估的基础。当前主要滑坡易发性评价方法主要采用单一数据驱动模型,在实际应用中易出现漏报、误报问题。本文针对单一数据驱动模型的弊端,提出结合多层感知器(Multi-Layer Perceptron,MLP)构建耦合模型进行滑坡预测分析; 选取贵州省松桃苗族自治县作为研究区,借助ArcGIS软件平台,将高程、坡度、坡向与起伏度等12个因子作为评价指标因子; 采用归一化频率比(NFR)模型与信息量(I)模型对研究区进行易发性评价,再分别与MLP模型结合成为NFR-MLP、I-MLP耦合模型并开展滑坡区预测分析; 将得到的易发性结果分为高、较高、中等、较低、低易发区五类; 结合区划结果频率比、接受者操作特征曲线(ROC)线下面积AUC值以及新典型滑坡实例,检验模型的精确度与可靠性。结果表明:(1)精确度大小为:I-MLP耦合模型>I模型>NFR-MLP耦合模型>NFR模型。因MLP模型具备高度的容错性和鲁棒性,致使X-MLP耦合模型更加适应复杂多变的环境因素;(2)I-MLP耦合模型预测性能较为出众,相较于单一模型精度提升5.7%。本研究结果可为研究区地质灾害防治提供一定指导建议。
Abstract:
Landslide susceptibility evaluation is a prerequisite for regional geo-hazard risk mapping. Most past inves-tigation into landslide susceptibility tried to use a single data-driven model, which were prone to underreporting and misreporting in practical prewarning.In this study, a typical geohazard-prone area, Songtao Miao Autonomous County, Guizhou province, China was chosen to conduct a case study. A Coupled Multilayer Perceptron(MLP)model for landslide prediction was introduced to solve the drawback of a single data-driven model. It took twelve evaluation index factors including elevation, slope, aspect, and topographic relief into GIS software. A Normalized Frequency Ratio(NFR)model and an Information Value(I)model were separately used to draw a primitive delineation of susceptibility of the study area, and then they were combined with MLP model to create NFR-MLP and I-MLP coupled model to further analysis. The research area was divided into five zones: high, relatively high, medium, relatively low, and low suscep-tibility zones according to the evaluation. The accuracy and reliability of the two models were justified by combining frequency ratios of zoning results with AUC values under the receiver operating characteristic curve(ROC)line along with new typical landslide examples.We have the following findings:(1)All models could be ranked in order of accuracy: I-MLP coupled model > I model > NFR-MLP coupled model > NFR model. Because the MLP model had advantages in fault tolerance and robustness, making the X-MLP coupled model more suitable for evaluating complex and changeable geo-environment.(2)I-MLP coupled model had outstanding predictive performance, with 5.7% accuracy im-provement as compared with those from some single data-driven models. This susceptibility zoning results can pro-vide guidance for prevention and control of geological disasters in research areas.

参考文献/References:

[1] 黄润秋. 20世纪以来中国的大型滑坡及其发生机制[J]. 岩石力学与工程学报, 2007, 26(3): 433-454. [HUANG Runqiu. Large-scale landslides and their sliding mechanism in China since the 20th century [J]. Chinese Journal of Rock Mechanics and Engineering, 2007, 26(3): 433-454]
[2] 石菊松, 张永双, 董诚, 等. 基于GIS技术的巴东新城区滑坡灾害危险性区划[J]. 地球学报, 2005, 26(3): 275-282. [SHI Jusong, ZHANG Yongshuang, DONG Cheng, et al. GIS-based landslide hazard zonation of the new Badong county site [J]. Acta Geoscientica Sinica, 2005, 26(3): 275-282] DOI: 10.3321/j.issn:1006-3021.2005.03.014
[3] 张俊, 殷坤龙, 王佳佳, 等. 三峡库区万州区滑坡灾害易发性评价研究[J]. 岩石力学与工程学报, 2016, 35(2): 284-296. [ZHANG Jun, YIN Kunlong, WANG Jiajia, et al. Evaluation of landslide susceptibility for Wanzhou district of Three Gorges Reservoir [J]. Chinese Journal of Rock Mechanics and Engineering, 2016, 35(2): 284-296] DOI: 10.13722/J. CNKI. JRME. 2015.0318
[4] JIANG Weiguo, RAO Pingzeng, CAO Ran, et al. Comparative evaluation of geological disaster susceptibility using multi-regression methods and spatial accuracy validation [J]. Journal of Geographical Sciences, 2017, 27(4): 439-462. DOI: 10.1007/s11442-017-1386-4
[5] PATRICHE C V, PIRNAU R, GROZAVU A, et al. A comparative analysis of binary logistic regression and analytical hierarchy process for landslide susceptibility assessment in the Dobrovat River Basin, Romania [J]. Pedosphere, 2016, 26(3): 335-350. DOI: 10.1016/S1002-0160(15)60047-9
[6] 余淙蔚, 柳侃, 殷杰, 等. 一种适用于逻辑回归模型评价浅层滑坡易发性的网格尺度划分方法——以2019年福建省三明市群发浅层滑坡为例[J]. 山地学报, 2022, 40(1): 106-119. [YU Congwei, LUI Kan, YIN Jie, et al. A grid-scale division method applicable to logistc regrsion models for evaluating the susceptibility of shallow landslides—taking the 2019 cluster of shallow landslides in Sanming, Fujian as example [J]. Mountain Research, 2022, 40(1): 106-119] DOI: 10.16089/j.cnki.1008-2786.000659
[7] LIU R, LI L, PIRASTEH S, et al. The performance quality of LR, SVM, and RF for earthquake-induced landslides susceptibility mapping incorporating remote sensing imagery [J]. Arabian Journal of Geosciences, 2021, 14(4): 259. DOI: 10.1007/s12517-021-06573-x
[8] 刘永垚, 第宝锋, 詹宇, 等. 基于随机森林模型的泥石流易发性评价——以汶川地震重灾区为例[J]. 山地学报, 2018, 36(5): 765-773. [LIU Yongyao, DI Baofeng, ZHAN Yu, et al. Debris flows susceptibility assessment in Wenchuan earthquake areas based on random forest algorithm model [J]. Mountain Research, 2018, 36(5): 765-773] DOI: 10.16089/j.cnki.1008-2786.000372
[9] 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, 145-146: 70-80. DOI: 10.1016/j.geomorph.2011.12.040
[10] YU Chenglong, CHEN Jianping. Landslide susceptibility mapping using the slope unit for southeastern Helong city, Jilin province, China: A comparison of ANN and SVM [J]. Symmetry, 2020, 12(6): 1047. DOI: 10.3390/sym12061047
[11] 郭子正, 殷坤龙, 付圣, 等. 基于GIS与WOE-BP模型的滑坡易发性评价[J]. 地球科学, 2019, 44(12): 4299-4312. [GUO Zizheng, YIN Kunlong, FU Sheng, et al. Evaluation of landslide susceptibility based on GIS and WOE-BP model [J]. Earth Sciences, 2019, 44(12): 4299-4312] DOI: 10.3799/dqkx.2018.555
[12] XU Jin, ZHAO Yanna. Stability analysis of geotechnical landslide based on GA-BP neural network model [J]. Computational and Mathematical Methods in Medicine, 2022, 2022: 3958985. DOI: 10.1155/2022/3958985
[13] 张钟远, 邓明国, 徐世光, 等. 镇康县滑坡易发性评价模型对比研究[J]. 岩石力学与工程学报, 2022, 41(1): 157-171. [ZHANG Zhongyuan, DENG Mingguo, XU Shiguang, et al. Comparison of landslide susceptibility assessment models in Zhenkang county, Yunnan province, China [J]. Chinese Journal of Rock Mechanics and Engineering, 2022, 41(1): 157-171] DOI: 10.13722/j. cnki. jrme. 2021.0360
[14] 吴常润, 角媛梅, 王金亮, 等. 基于频率比—逻辑回归耦合模型的双柏县滑坡易发性评价[J]. 自然灾害学报, 2021, 30(4): 213-224. [WU Changrun, JIAO Yuanmei, WANG Jinliang, et al. Frequency ratio and logistic regression models based coupling analysis for susceptibility of landslide in Shuangbai county [J]. Journal of Natural Disasters, 2021, 30(4): 213-224] DOI: 10.13577/j. jnd. 2021.0423
[15] 邓念东, 崔阳阳, 郭有金. 基于频率比—随机森林模型的滑坡易发性评价[J]. 科学技术与工程, 2020, 20(34): 13990-13996. [DENG Niandong, CUI Yangyang, GUO Youjin. Frequency ratio-random forest-model-based landslide susceptibility assessment [J]. Science Technology and Engineering, 2020, 20(34): 13990-13996]
[16] 周晓亭, 黄发明, 吴伟成, 等. 基于耦合信息量法选择负样本的区域滑坡易发性预测[J]. 工程科学与技术, 2022, 54(3): 25-35. [ZHOU Xiaoting, HUANG Faming, WU Weicheng, et al. Regional landslide susceptibility prediction based on negative sample selected by coupling information value method [J]. Advanced Engineering Sciences, 2022, 54(3): 25-35] DOI: 10.15961/j. jsuese. 202100808
[17] HUANG Faming, CAO Zhongshan, JIANG Shuihua, et al. Landslide susceptibility prediction based on a semi-supervised multiple-layer perceptron model [J]. Landslides, 2020, 17(12): 2919-2930. DOI: 10.1007/s10346-020-01473-9
[18] BUI D T, PRADHAN B, REVHAUG I, et al. A comparative assessment between the application of fuzzy unordered rules induction algorithm and J48 decision tree models in spatial prediction of shallow landslides at Lang Son city, Vietnam [G]// SRIVASTAVA P K, GUPTA S M M, ISLAM T. Remote Sensing Applications in Environmental Research. New York: Springer, 2014: 87-111. DOI: 10.1007/978-3-319-05906-8-6
[19] 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 and Geosciences, 2013, 51: 350-365. DOI: 10.1016/j.cageo.2012.08.023
[20] JEBUR M N, PRADHAN B, TEHRANY M S. Optimization of landslide conditioning factors using very high-resolution airborne laser scanning(LiDAR)data at catchment scale [J]. Remote Sensing of Environment, 2014, 152: 150-165. DOI: 10.1016/j.rse.2014.05.013
[21] POURGHASEMI H R, PRADHAN B, GOKCEOGLU C. Application of fuzzy logic and analytical hierarchy process(AHP)to landslide susceptibility mapping at Haraz watershed, Iran [J]. Natural Hazards, 2012, 63: 965-996. DOI: 10.1007/s11069-012-0217-2
[22] PHAM B T, BUI D T, PRAKASH I, et al. Hybrid integration of multilayer perceptron neural networks and machine learning ensembles for landslide susceptibility assessment at Himalayan area(India)using GIS [J]. Catena, 2017, 149: 52-63. DOI: 10.1016/j.catena.2016.09.007
[23] ZHU Li, HUANG Lianghao, FAN Linyu, et al. Landslide susceptibility prediction modeling based on remote sensing and a novel deep learning algorithm of a cascade-parallel recurrent neural network [J]. Sensors, 2020, 20(6): 1576. DOI: 10.3390/s20061576
[24] MILOEVIC' D, MANCˇEV D, CˇERBA D, et al. The potential of chironomid larvae-based metrics in the bioassessment of non-wadeable rivers [J]. Science of the Total Environment, 2017, 616-617: 472-479. DOI: 10.1016/j.scitotenv.2017.10.262
[25] 杨光, 徐佩华, 曹琛, 等. 基于确定性系数组合模型的区域滑坡敏感性评价[J]. 工程地质学报, 2019, 27(5): 1153-1163. [YANG Guang, XU Peihua, CAO Chen, et al. Assessment of regional landslide susceptibility based on combined model of certainty factor method [J]. Journal of Engineering Geology, 2019, 27(5): 1153-1163] DOI: 10.13544/J. CNKI. Jeg. 2019018
[26] 松桃苗族自治县人民政府. 铜仁市松桃苗族自治县县情简介[EB/OL].(2021-11.01)[2022-07-31]. http://www.songtao.gov.cn/zjst/stjj/202008/t20200807_62284287.html [Songtao Miao Autonomous County People's Government. County Profile of Tongren Songtao Miao Autonomous County [EB/OL].(2021-11.01)[2022-07-31]. http://www.songtao.gov.cn/zjst/stjj/202008/t20200807_62284287.html]
[27] SUN Xiaohui, CHEN Jianping, HAN Xudong, et al. Landslide susceptibility mapping along the upper Jinsha River, south-western China: A comparison of hydrological and curvature watershed methods for slope unit classification [J]. Bulletin of Engineering Geology and the Environment, 2020, 79(9): 4657-4670. DOI: 10.1007/s10064-020-01849-0
[28] REHMAN A, SONG J, HAQ F, et al. Multi-hazard susceptibility assessment using the analytical hierarchy process and frequency ratio techniques in the northwest Himalayas, Pakistan [J]. Remote Sensing, 2022, 14(3): 554. DOI: 10.3390/rs14030554
[29] 仉义星, 兰恒星, 李郎平, 等. 综合统计模型和物理模型的地质灾害精细评估——以福建省龙山社区为例[J]. 工程地质学报, 2019, 27(3): 608-622. [ZHANG Yixing, LAN Hengxing, LI Langping, et al. Combining statistical model and physical model for refined assessment of geological disaster: A case study of Longshan community in Fujian province [J]. Journal of Engineering Geology, 2019, 27(3): 608-622] DOI: 10.13544/j. cnki. jeg. 2018-270
[30] 罗鸿东, 李瑞冬, 张勃, 等. 基于信息量法的地质灾害气象风险预警模型:以甘肃省陇南地区为例[J]. 地学前缘, 2019, 26(6): 289-297. [LUO Hongdong, LI Ruidong, ZHANG Bo, et al. An early warning model system for predicting eteorological risk associated with geological disasters in the Longnan area,Gansu province based on the information value method [J]. Earth Science Frontiers, 2019, 26(6): 289-297] DOI: 10.13745/j. esf. sf.2019.11.1
[31] 张向营, 张春山, 孟华君, 等. 基于GIS和信息量模型的京张高铁滑坡易发性评价[J]. 地质力学学报, 2018, 24(1): 96-105. [ZHANG Xiangying, ZHNAG Chunshan, MENG Huajun, et al. Landslide susceptibility assessment of new Jing-Zhang high-speed railway based on GIS and information value model [J]. Journal of Geomechanics, 2018, 24(1): 96-105] DOI: 10.12090/j.issn.1006-6616.2018.24.01.011
[32] SAITO H, NAKAYAMA D, MATSUYAMA H. Comparison of landslide susceptibility based on a decision-tree model and actual landslide occurrence: The Akaishi Mountains, Japan [J]. Geomorphology, 2009, 109(3): 108-121. DOI: 10.1016/j.geomorph.2009.02.026
[33] 骆剑承, 周成虎, 杨艳. 人工神经网络遥感影像分类模型及其与知识集成方法研究[J]. 遥感学报, 2001, 5(2): 122-129. [LUO Jiancheng, ZHOU Chenghu, YANG Yan. ANN remote sensing classification model and its integration approach with Geo-knowledge [J]. Journal of Remote Sensing, 2001, 5(2): 122-129] DOI: 10.3321/j.issn:1007-4619.2001.02.010
[34] LOMBARDO L, TANYAS H. Chrono-validation of near-real-time landslide susceptibility models via plug-in statistical simulations [J]. Engineering Geology, 2020, 278: 105818. DOI: 10.1016/j.enggeo.2020.105818
[35] 刘艺梁, 殷坤龙, 刘斌. 逻辑回归和人工神经网络模型在滑坡灾害空间预测中的应用[J]. 水文地质工程地质, 2010, 37(5): 92-96. [LIU Yiliang, YIN Kunlong, LIU Bin. Application of logistic regression and artificial neural network model in spatial assessment of landslide hazards [J]. Hydrogeology and Engineering Geology, 2010, 37(5): 92-96] DOI: 10.16030/j. cnki. issn.1000-3665.2010.05.015
[36] DORMANN C F, ELITH J, BACHER S, et al. Collinearity: A review of methods to deal with it and a simulation study evaluating their performance [J]. Ecography, 2013, 36(1): 27-46. DOI: 10.1111/j.1600-0587.2012.07348.x
[37] BUI D T, TUAN T A, KLENPE H, et al. Spatial prediction models for shallow landslide hazards: A comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree [J]. Landslides, 2016, 13(2): 361-378. DOI: 10.1007/s10346-015-0557-6
[38] DE MELLO R B, MARCON R. Unpacking firm effects: Modeling political alliances in variance decomposition of firm performance in turbulent environments [J]. 2005, 2(1): 21-37. DOI: 10.1590/S1807-76922005000100003
[39] LIAO D, VALLIANT R. Variance inflation factors in the analysis of complex survey data [J]. Survey Methodology, 2012, 38(1): 53-62.
[40] CHEN Wei, ZHANG Shuai, LI Renwei, et al. Performance evaluation of the GIS-based data mining techniques of best-first decision tree, random forest, and na?ve Bayes tree for landslide susceptibility modeling [J]. Science of the Total Environment, 2018, 644: 1006-1018. DOI: 10.1016/i.scitotenv.2018.06.389
[41] BUI D T, LOFMAN O, REVHAUG I, et al. Landslide susceptibility analysis in the Hoa Binh province of Vietnam using statistical index and logistic regression [J]. Natural Hazards, 2011, 59: 1413-1444. DOI: 10.1007/s11069-011-9844-2
[42] HAIR J F. Multivariate data analysis: An overview [M]. Heidelberg: Springer, 2011: 904-907. DOI: 10.1007/978-3-642-04898-2_395
[43] 胡涛. 贵州省思南县地质灾害危险性评价研究[D]. 武汉: 中国地质大学, 2020: 46-47, 55-46. [HU Tao. Study of geological disasters hazard assessment in Sinan county of Guizhou province [D]. Wuhan: China University of Geosciences, 2020: 46-47, 55-46 ] DOI: 10.27492/d. cnki. gzdzu 2020.000065
[44] VAN WESTEN C J, CASTELLANOS E, KURIAKOSE S L. Spatial data for landslide susceptibility, hazard, and vulnerability assessment: An overview [J]. Engineering Geology, 2008, 102(3): 112-131. DOI: 10.1016/j.enggeo.2008.03.010
[45] 周超, 殷坤龙, 曹颖, 等. 基于集成学习与径向基神经网络耦合模型的三峡库区滑坡易发性评价[J]. 地球科学, 2020, 45(6): 1865-1876. [ZHOU Chao, YIN Kunlong, CAO Ying, et al. Landslide susceptibility assessment by applying the coupling method of radial basis neural network and adaboost: A case study from the Three Gorges Reservoir area [J]. Earth Sciences, 2020, 45(6): 1865-1876] DOI: 10.3799/dqkx.2020.071
[46] CHUNG C J, FABBRI A G. Predicting landslides for risk analysis - spatial models tested by a cross-validation technique [J]. Geomorphology, 2008, 94(3-4): 438-452. DOI: 10.1016/j.geomorph.2006.12.036

相似文献/References:

[1]吴先谭a,邓 辉a,b*,等.基于斜坡单元自动划分的滑坡易发性评价[J].山地学报,2022,(4):542.[doi:10.16089/j.cnki.1008-2786.000692]
　WU Xiantana,DENG Huia,b*,et al.Evaluation of Landslide Susceptibility Based on Automatic Slope Unit Division[J].Mountain Research,2022,(2):542.[doi:10.16089/j.cnki.1008-2786.000692]

备注/Memo

备注/Memo:
收稿日期(Received date): 2022-11-15; 改回日期(Accepted data):2023-04-02
基金项目(Foundation item): 国家自然科学基金(41977213); 中央高校基本科研业务费专项资金(XJ2021KJZK039); 四川省交通运输科技项目(2021-A-03); 中铁四川生态城投资有限公司委托项目(R110121H01092)。[National Natural Science Foundation of China(41977213); Fundamental Research Funds for the Central Universities(XJ2021KJZK039); Sichuan Provincial Transportation Science and Technology Project(2021-A-03); Project of China Railway Sichuan Eco-City Investment Co.,LTD(R110121H01092)]
作者简介(Biography): 曾营(1997-),男,福建宁德人,博士研究生,研究方向:地质灾害风险评估。[ZENG Ying(1997-), male, born in Ningde, Fujian province, Ph.D. candidate, research on geological hazard risk assessment] E-mail:zengying@my.swjtu.edu.cn
*通讯作者(Corresponding author): 张迎宾(1983-),男,教授,博士,研究方向:岩土地震工程。[ZHANG Yingbin(1983-), male, professor, Ph.D., research on geotechnical earthquake engineering ] E-mail:yingbinz719@swjtu.edu.cn
更新日期/Last Update: 2023-03-30