[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):542-556.[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,(4):542-556.[doi:10.16089/j.cnki.1008-2786.000692]
点击复制

基于斜坡单元自动划分的滑坡易发性评价
分享到：

《山地学报》[ISSN:1008-2186/CN:51-1516]

卷:
期数:
2022年第4期
页码:
542-556
栏目:
山地灾害
出版日期:
2022-07-25

文章信息/Info

Title:
Evaluation of Landslide Susceptibility Based on Automatic Slope Unit Division
文章编号:
1008-2786-(2022)4-542-15
作者:
吴先谭a; 邓 辉a; b*; 张文江a; 卓文浩a
成都理工大学 a. 地球科学学院; b. 地质灾害防治与地质环境保护国家重点实验室,四川 成都 610059
Author(s):
WU Xiantana;  DENG Huia; b*;  ZHANG Wenjianga;  ZHUO Wenhaoa
a. College of Earth Sciences; b. State Key Laboratory of Geohazard Prevention and Geoenvironment Protection, Chengdu University of Technology, Chengdu 610059
关键词:
滑坡易发性;  斜坡单元;  频率比模型;  机器学习模型;  毛尔盖水库
Keywords:
landslide susceptibility;  slope unit;  frequency ratio;  machine learning model;  Maergai Reservoir
分类号:
P642.22
DOI:
10.16089/j.cnki.1008-2786.000692
文献标志码:
A
摘要:
将斜坡单元与机器学习模型相结合,对比分析不同机器学习模型在斜坡单元中滑坡易发性评价的差异性,有助于优化预测的精确性和结果的稳定性,为滑坡的预测提供科学依据。本文以四川省黑水县毛尔盖水库地区为研究区,利用r.slopeunits方法自动划分斜坡单元,采用地理探测器(GeoDetector)方法优化滑坡易发性评价指标体系,以斜坡单元为基础分别应用频率比(FR)、频率比-随机森林(FR-RF)、频率比-支持向量机(FR-SVM)、频率比-人工神经网络(FR-ANN)耦合模型对滑坡易发性进行空间预测,并对比分析不同模型在滑坡易发性评价中的性能差异。结果表明:(1)r.slopeunits方法提取的斜坡单元内部坡向均一性较好,满足滑坡稳定性分析方法中计算单元均一性假设;(2)地理探测器筛选的12个评价因子相关性分析表明,没有冗余的评价因子被输入到机器学习模型,保证了模型的可靠性和预测能力;(3)Kappa系数、准确率(Accuracy)、AUC值联合表明预测能力由大到小依次为FR-RF模型、FR-SVM模型、FR-ANN模型、FR,相较于其他模型,FR-RF模型的预测结果中极高和高易发区的滑坡面积占比最高,达到86.89%。研究成果表明FR-RF耦合模型更适用于以斜坡单元为基础的滑坡易发性评价,可为西南深切河谷区域滑坡易发性评价提供理论指导。
Abstract:
Comparing and analyzing the difference of landslide susceptibility results evaluated by different machine learning models based on slope unit, the accuracy and the stability of prediction results can be optimized, which can provide a scientific basis for landslide prediction. In this paper, slopes in the Maurge Reservoir of Heishui county, Sichuan, China was selected for case study. The r.slopeunits tool was introduced to automatically extract slope units in a model of landslide susceptibility evaluation, and the GeoDetector method was used to optimize its index system. Then it took four models, Frequency Ratio(FR), Frequency Ratio-Random Forest(FR-RF), Frequency Ratio-Support Vector Machine(FR-SVM), and Frequency Ratio-Artificial Neural Network(FR-ANN)to delineate areas prone to landslides, and their performances were evaluated. The following results are listed:(1)Slope units extracted by the r.slopeunits tool had good internal aspect homogeneity satisfying the assumption of calculating unit uniformity in a landslide stability analysis;(2)The correlation analysis of 12 evaluation factors collected by GeoDetector showed that no redundant evaluation factors were input into the machine learning model, which ensured the reliability and prediction ability of the models;(3)The Kappa coefficient, Accuracy(Accuracy), and AUC values suggested that the order of prediction ability was FR-RF, FR-SVM, FR-ANN, and FR. Compared to other models, the FR-RF model predicted 86.89% of the landslide area in extremely high and high susceptibility zones, the greatest proportion among all models. In a word, with the coupled FR-RF model, our proposed approach is more suitable for evaluating landslide susceptibility based on auto-division of slope units in a model of landslide stability analysis. This study provides a theoretical guidance for predicting landslide hazards in deep river valleys in southwest China.

参考文献/References:

[1] 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
[2] MERGHADI A, YUNUS A P, DOU Jie, et al. Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance [J]. Earth-Science Reviews, 2020, 207:103225. DOI: 10.1016/j.earscirev.2020.103225
[3] 郑师谊,张绪教,杨艳,等. 层次分析法在滇西怒江河谷潞江盆地段崩塌与滑坡地质灾害危险性评价中的应用[J]. 地质通报,2012,31(2/3):356-365. [ZHENG Shiyi, ZHANG Xujiao, YANG Yan, et al. The application of analytic hierarchy process to the danger evaluation of collapse and slide in Lujiang basin segment of Nujiang valley, western Yunnan province [J]. Geological Bulletin of China, 2012, 31(2/3):356-365]
[4] 张玘恺,凌斯祥,李晓宁,等. 九寨沟县滑坡灾害易发性快速评估模型对比研究[J]. 岩石力学与工程学报,2020,39(8):1595-1610. [ZHANG Qikai, LING Sixiang, LI Xiaoning, et al. Comparison of landslide susceptibility mapping rapid assessment models in Jiuzhaigou county, Sichuan province, China [J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(8):1595-1610] DOI: 10.13722/j.cnki.jrme.2020.0029
[5] 管家琳,黄炎和,林金石,等. 基于信息量模型与随机森林模型的崩岗风险对比评估[J]. 山地学报,2021,39(4):539-551. [GUAN Jialin, HUANG Yanhe, LIN Jinshi, et al. Comparisons between Benggang risk assessments based on information model and random forest model [J]. Mountain Research, 2021, 39(4):539-551] DOI: 10.16089/j.cnki.1008-2786.000618
[6] 李文彦,王喜乐. 频率比与信息量模型在黄土沟壑区滑坡易发性评价中的应用与比较[J]. 自然灾害学报,2020,29(4):213-220. [LI Wenyan, WANG Xile. Application and comparison of frequency ratio and information value model for evaluating landslide susceptibility of loess gully region [J]. Journal of Natural Disasters, 2020, 29(4):213-220] DOI: 10.13577/j.jnd.2020.0422
[7] 黄发明,殷坤龙,蒋水华,等. 基于聚类分析和支持向量机的滑坡易发性评价[J]. 岩石力学与工程学报,2018,37(1):156-167. [HUANG Faming, YIN Kunlong, JIANG Shuihua, et al. Landslide susceptibility assessment based on clustering analysis and support vector machine [J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37(1):156-167] DOI: 10.13722/j.cnki.jrme.2017.0824
[8] 田乃满,兰恒星,伍宇明,等. 人工神经网络和决策树模型在滑坡易发性分析中的性能对比[J]. 地球信息科学学报,2020,22(12):2304-2316. [TIAN Naiman, LAN Hengxing, WU Yuming, et al. Performance comparison of BP artificial neural network and CART decision tree model in landslide susceptibility prediction [J]. Journal of Geo-information Science, 2020, 22(12):2304-2316] DOI: 10.12082/dqxxkx.2020.190766
[9] 吴润泽,胡旭东,梅红波,等. 基于随机森林的滑坡空间易发性评价:以三峡库区湖北段为例[J]. 地球科学,2021,46(1):321-330. [WU Runze, HU Xudong, MEI Hongbo, et al. Spatial susceptibility assessment of landslides based on random forest: A case study from Hubei section in the Three Gorges Reservoir area [J]. Earth Science, 2021, 46(1):321-330] DOI: 10.3799/dqkx.2020.032
[10] 陈飞,蔡超,李小双,等. 基于信息量与神经网络模型的滑坡易发性评价[J]. 岩石力学与工程学报,2020,39(S1):2859-2870. [CHEN Fei, CAI Chao, LI Xiaoshuang, et al. Evaluation of landslide susceptibility based on information volume and neural network model [J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(S1):2859-2870] DOI: 10.13722/j.cnki.jrme.2019.1094
[11] 薛强,张茂省,李林. 基于斜坡单元与信息量法结合的宝塔区黄土滑坡易发性评价[J].地质通报,2015,34(11):2108-2115. [XUE Qiang, ZHANG Maosheng, LI Lin. Loess landslide susceptibility evaluation based on slope unit and information value method in Baota district, Yan'an [J]. Geological Bulletin of China, 2015, 34(11):2108-2115]
[12] 唐川,马国超. 基于地貌单元的小区域地质灾害易发性分区方法研究[J]. 地理科学,2015,35(1):91-98. [TANG Chuan, MA Guochao. Small regional geohazards susceptibility mapping based on geomorphic unit [J]. Scientia Geographica Sinica, 2015, 35(1):91-98] DOI: 10.13249/j.cnki.sgs.2015.01.011
[13] 王凯,张少杰,韦方强. 斜坡单元提取方法研究进展和展望[J]. 长江科学院院报,2020,37(6):85-93. [WANG Kai, ZHANG Shaojie, WEI Fangqiang. Advances and prospects in the slope unit extraction method [J]. Journal of Yangtze River Scientific Research Institute, 2020, 37(6):85-93] DOI: 10.11988/ckyyb.20190210
[14] ZHAO Yu, WANG Rui, JIANG Yuanjun, et al. GIS-based logistic regression for rainfall-induced landslide susceptibility mapping under different grid sizes in Yueqing, southeastern China [J]. Engineering Geology, 2019, 259:105147. DOI: 10.1016/j.enggeo.2019.105147
[15] SCHLOGEL R, MARCHESINI I, ALVIOLI M, et al. Optimizing landslide susceptibility zonation: Effects of DEM spatial resolution and slope unit delineation on logistic regression models [J]. Geomorphology, 2018, 301:10-20. DOI: 10.1016/j.geomorph.2017.10.018
[16] ALVIOLI M, MARCHESINI I, REICHENBACH P, et al. Automatic delineation of geomorphological slope units with r.slopeunits v1.0 and their optimization for landslide susceptibility modeling [J]. Geoscientific Model Development, 2016, 9(11):3975-3991. DOI: 10.5194/gmd-9-3975-2016
[17] HAKAN T, LUIGI L. Completeness index for earthquake-induced landslide inventories [J]. Engineering Geology, 2020, 264: 105331. DOI: 10.1016/j.enggeo.2019.105331
[18] 许强,董秀军,李为乐. 基于天-空-地一体化的重大地质灾害隐患早期识别与监测预警[J]. 武汉大学学报(信息科学版),2019,44(7):957-966. [XU Qiang, DONG Xiujun, LI Weile. Integrated space-air-ground early detection, monitoring and warning system for potential catastrophic geohazards [J]. Geomatics and Information Science of Wuhan University, 2019, 44(7):957-966] DOI: 10.13203/j.whugis20190088
[19] BREIMAN L. Random forests [J]. Machine Learning, 2001, 45(1):5-32. DOI: 10.1023/A:1010933404324
[20] CORTES C, VAPNIK V. Support-vector networks [J]. Machine Learning, 1995, 20(3):273-297. DOI: 10.1007/BF00994018
[21] ZHOU Xinzhi, WEN Haijia, ZHANG Yalan, et al. Landslide susceptibility mapping using hybrid random forest with GeoDetector and RFE for factor optimization [J]. Geoscience Frontiers, 2021, 12(5):101211. DOI: 10.1016/j.gsf.2021.101211
[22] 张建廷,张立民,徐涛. 遥感图像的异质性测度分割效果评价[J]. 测绘科学技术学报,2015,32(5):479-482+488. [ZHANG Jianting, ZHANG Limin, XU Tao. Heterogeneity measure based segmentation performance evaluation for remote sensing image [J]. Journal of Geomatics Science and Technology, 2015, 32(5):479-482+488] DOI: 10.3969/j.issn.1673-6338.2015.05.009
[23] 罗路广,裴向军,崔圣华,等. 九寨沟地震滑坡易发性评价因子组合选取研究[J]. 岩石力学与工程学报,2021,40(11):2306-2319. [LUO Luguang, PEI Xiangjun, CUI Shenghua, et al. Combined selection of causative factors for Jiuzhaigou earthquake-induced landslide susceptibility assessment [J]. Chinese Journal of Rock Mechanics and Engineering, 2021, 40(11):2306-2319] DOI: 10.13722/j.cnki.jrme.2021.0198
[24] DOU J, YUNUS A P, TIEN B D, et al. Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan [J]. Science of The Total Environment, 2019, 662:332-346. DOI: 10.1016/j.scitotenv.2019.01.221
[25] 中华人民共和国国家质量监督检验检疫总局和中国国家标准化管理委员会. 中国地震动参数区划图:GB 18306-2015[S]. 北京:中国标准出版社,2015-05-15. [General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China and Standardization Administration of China. Seismic ground motion parameters zonation map of China: GB 18306-2015[S]. Beijing: Standards Press of China, 2015-05-15]
[26] 王劲峰,徐成东. 地理探测器:原理与展望[J]. 地理学报,2017,72(1):116-134. [WANG Jinfeng, XU Chengdong. Geodetector: Principle and prospective [J]. Acta Geographica Sinica, 2017, 72(1):116-134] DOI: 10.11821/dlxb201701010
[27] 罗路广,裴向军,黄润秋. 强震山区地震滑坡发生概率研究—以九寨沟国家地质公园为例[J]. 岩石力学与工程学报,2020,39(10):2079-2093. [LUO Luguang, PEI Xiangjun, HUANG Runqiu. Earthquake-triggered landslide occurrence probability in strong seismically mountainous area: A case study of Jiuzhaigou National Geopark [J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(10):2079-2093] DOI: 10.13722/j.cnki.jrme.2020.0298
[28] 颜阁,梁收运,赵红亮. 基于GIS的斜坡单元划分方法改进与实现[J]. 地理科学,2017,37(11):1764-1770. [YAN Ge, LIANG Shouyun, ZHAO Hongliang. An approach to improving slope unit division using GIS technique [J]. Scientia Geographica Sinica, 2017, 37(11):1764-1770] DOI: 10.13249/j.cnki.sgs.2017.11.019
[29] MANDAL K, SAHA S, MANDAL S. Applying deep learning and benchmark machine learning algorithms for landslide susceptibility modelling in Rorachu river basin of Sikkim Himalaya, India [J]. Geoscience Frontiers, 2021, 12(5):101203. DOI: 10.1016/j.gsf.2021.101203
[30] HUANG Faming, YIN Kunlong, HUANG Jinsong, et al. Landslide susceptibility mapping based on self-organizing-map network and extreme learning machine [J]. Engineering Geology, 2017, 223:11-22. DOI: 10.1016/j.enggeo.2017.04.013

相似文献/References:

[1]付 圣,陈丽霞*,黎丰收,等.鄂西南山区小区域大比例尺滑坡灾害易发性及其精度评价[J].山地学报,2017,(04):517.[doi:10.16089/j.cnki.1008-2786.000249]
　FU Sheng,CHEN Lixia*,LI Fengshou,et al.Large Scale Landslides Susceptibility and Accuracy Assessment in Mountainous Counties[J].Mountain Research,2017,(4):517.[doi:10.16089/j.cnki.1008-2786.000249]
[2]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.[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,(4):280.[doi:10.16089/j.cnki.1008-2786.000748]

备注/Memo

备注/Memo:
收稿日期(Received date):2021-12-07; 改回日期(Accepted date): 2022-08-14
基金项目(Foundation item):西藏自治区科学技术厅重点研发计划(XZ202001ZY0056G); 四川省地质灾害隐患遥感识别监测项目(510201202076888); 四川矿产资源研究中心科研项目(SCKCZY2017-YB08)。[Key Research and Development Program of Science and Technology Department of Tibet(XZ202001ZY0056G); Remote Sensing Identification and Monitoring Project of Hidden Geological Hazards in Sichuan Province(510201202076888); Sichuan Mineral Resources Research Center's Scientific Research Project(SCKCZY2017-YB08)]
作者简介(Biography):吴先谭(1996-),男,四川达州人,硕士研究生,主要研究方向:滑坡灾害早期识别和风险评价。 [WU Xiantan(1996-), male, born in Dazhou, Sichuan province, M.Sc. candidate, research on landslide hazard early identification and risk evaluation] E-mail: wuxiantan@stu.cdut.edu.cn
*通讯作者(Corresponding author):邓辉(1984-),男,湖南醴陵市人,博士,讲师,主要研究方向:滑坡灾害早期识别和风险评价。 [DEN Hui(1984-), male, born in Liling, Hunan province, Ph.D., lecturer, research on landslide hazard early identification and risk evaluation] E-mail: dengh@cdut.edu.cn
更新日期/Last Update: 2022-08-30