Landslide Susceptibility Assessment Based on GIS and MaxEnt Model: Example from Central Districts in Tongchuan City
-
摘要:
铜川市属于中国资源枯竭型城市，近年来过量的开采资源与频繁的工程活动诱发了大量的滑坡，对人民安全与社会发展造成了严重威胁，如何科学合理地对滑坡易发性进行评价具有重大的研究意义。以铜川市滑坡分布较多的王益区、印台区作为研究区，选取坡度、坡向、高程、曲率、距道路的距离、距水系的距离、地形地貌、岩土体类型等8个因子构建评价指标体系，采用MaxEnt模型与ArcGIS平台相结合的方法构建了研究区滑坡易发性评价模型，并进行了易发性评价。评价结果显示，MaxEnt模型AUC值达到0.905，评价能力优秀；Kappa系数为0.76，评价结果与滑坡现状分布十分吻合；距水系的距离、地形地貌为最重要的环境影响因子。高易发和较高易发主要分布在其中部及东部居民集中居住区，分别占研究区总面积的4.36%、5.77%，与实地调查结果相符，MaxEnt模型可在类似区域滑坡易发性评价中进行推广。
Abstract:Tongchuan city is a resource-depleted city in China. In recent years, excessive resource exploitation and frequent engineering activities have induced a large number of landslides, which threaten people’s safety and social development, and it is of great research significance to evaluate landslide susceptibility in a scientific and reasonable way. The study area is Wangyi and Yintai, which are the two districts with more landslide distribution in Tongchuan City, and the evaluation index system is constructed by selecting eight factors, including slope, slope direction, elevation, curvature, distance from road, distance from water system, geomorphology type and geotechnical type, etc. The model and platform are combined to construct the evaluation model of landslide susceptibility in the study area, and the susceptibility evaluation is carried out. The evaluation results show that the model value reaches 0.905, with excellent evaluation ability, and the coefficient is 0.76. The evaluation results are in good agreement with the current distribution of landslides; the distance from water system and geomorphological type are the most important environmental impact factors. The high susceptibility and high susceptibility account for 4.36% and 5.77% of the total area, mainly in the central and eastern residential areas of the study area, which is consistent with the field survey results.
-
Key words:
- susceptibility assessment /
- MaxEnt model /
- ArcGIS /
- landslide
-
-
表 1 AUC值与Kappa值评价标准表
Table 1. Assessment standard of AUC value and kappa value
精确度 极差 较差 一般 较好 优秀 AUC 0.5～0.6 0.6～0.7 0.7～0.8 0.8～0.9 0.9～1 Kappa 0～0.2 0.2～0.4 0.4～0.55 0.55～0.7 0.7～1 
下载: 导出CSV
表 2 AUC均值/SD值与训练比例的关系表
Table 2. Relationship between AUC mean value/SD value and training proportion
训练样本比例 70% 75% 80% 85% 90% AUC平均值 0.902 0.905 0.909 0.904 0.887 标准差 0.0763 0.0661 0.0855 0.0839 0.0565
下载: 导出CSV
-
范亦嵩. 宜君县地质灾害特征及风险评价[D]. 西安: 西北大学硕士学位论文, 2020.
冯杭建, 周爱国, 俞剑君, 等. 浙西梅雨滑坡易发性评价模型对比[J]. 地球科学, 2016, 41(03): 403-415.
FENG Hangjian, ZHOU Aiguo, YU Jianjun, et al. A Comparative Study on Plum-Rain-Triggered Landslide Susceptibility Assessment Models in West Zhejiang Province.Earth Science
冯卫, 唐亚明, 马红娜, 等. 基于层次分析法的咸阳市多灾种自然灾害综合风险评价[J]. 西北地质, 2021, 54(02): 282-288.
FENG Wei, TANG Yaming, MA Hongna, et al. Comprehensive Risk Assessment of Mutti-hazard Natural Disasters in Xianyang City Based on AHP. Northwestern Geology
郭倩怡, 王友林, 谢婉丽, 等. 黄土湿陷性与土体物性指标的相关性研究[J]. 西北地质, 2021, 54(01): 212-221.
GUO Qianyi, WANG Youlin, XIE Wanli, et al. Study on Correlation between Loess Collapsibility and Soil Physical Property Index. Northwestern Geology
李泽群. 基于BP人工神经网络和GIS的湖南省鼎城区滑坡易发性评价[D]. 石家庄: 河北地质大学硕士学位论文, 2020.
林荣福, 刘纪平, 徐胜华, 等. 随机森林赋权信息量的滑坡易发性评价方法[J]. 测绘科学, 2020, 45(12): 131-138.
LIN Rongfu, LIU Jiping, Xu Shenghua, et al. Evaluation method of landslide susceptibility based on random forest weighted information. Science of Surveying and Mapping
刘睿, 施婌娴, 孙德亮, 等. 基于GIS与随机森林的巫山县滑坡易发性区划[J]. 重庆师范大学学报(自然科学版), 2020, 37(03): 86-96.
LIU Rui, SHI Shuxian, SUN Deliang, et al. Based on GIS and Random Forest Model for Landslide Susceptibility Mapping in Wushan County. Journal of Chongqing Normal University (Natural Science)
刘颖莹, 谢婉丽, 朱桦, 等. 陕西泾阳地区黄土固结湿陷试验及预测模型研究[J]. 西北地质, 2018, 51(02): 227-233. doi: 10.3969/j.issn.1009-6248.2018.02.030
LIU Yingying, XIE Wanli, ZHU Hua, et al. Study on Loess Consolidation Collapse Test and Prediction Model in Jingyang District, Shaanxi Province. Northwestern Geology doi: 10.3969/j.issn.1009-6248.2018.02.030
麦鉴锋, 冼宇阳, 刘桂林. 气候变化情景下广东省降雨诱发型滑坡灾害潜在分布及预测[J]. 地球信息科学学报, 2021, 23(11): 2042-2054. doi: 10.12082/dqxxkx.2021.210182
MAI Jianfeng, XIAN Yuyang, LIU Guilin. Predicting potential rainfall-triggered landslides sites in Guangdong Province (China) using Max-Ent model under climate changes scenarios. Journal of Geo-information Science doi: 10.12082/dqxxkx.2021.210182
屈新星, 李道安, 何云玲, 等. 基于MaxEnt模型的滑坡易发性评价——以攀枝花市为例[J]. 水土保持研究, 2021, 28(02): 224-229.
QU Xinxing, LI Daoan, HE Yunling, et al. Evaluation of landslide susceptibility based on MaxEnt model: taking Panzhihua City as an example[J]. Research of Soil and Water Conservation, 2021, 28(02): 224-229.
阮沈勇, 黄润秋. 基于GIS的信息量法模型在地质灾害危险性区划中的应用[J]. 成都理工学院学报, 2001, (01): 89-92.
RUAN Shenyong, HUANG Runqiu. Application of GIS based Information model on assessment of geological hazards risk. Journal of Chengdu University of Technology
唐兴港, 王慧勇, 黄豆, 等. 长江中下游地区滑坡的易发性评价——以江西省为例[J]. 水土保持通报, 2021, 41(03): 166-172.
TANG Xinggang, WANG Huiyong, HUANG Dou, et al. Evaluation of landslide susceptibility in middle and lower reaches of Yangtze River. Bulletin of Soil and Water Conservation
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. doi: 10.12082/dqxxkx.2020.190766
TIAN Naiman, LAN Hengxing, WU Yuming, et al. Performance comparison of BP artificial neural network and CART decision tree model in land-slide susceptibility prediction. Journal of Geo-information Science doi: 10.12082/dqxxkx.2020.190766
屠水云, 张钟远, 付弘流, 等. 基于CF与CF-LR模型的地质灾害易发性评价[J]. 中国地质灾害与防治学报, 2022, 33(02): 96-104. doi: 10.16031/j.cnki.issn.1003-8035.2022.02-12
TU Shuiyun, ZHANG Zhongyuan, FU Hongliu, et al. Geological hazard susceptibility evaluation based on CF and CF-LR model. The Chinese Journal of Geological Hazard and Control doi: 10.16031/j.cnki.issn.1003-8035.2022.02-12
王高峰, 郭宁, 邓兵, 等. 不同组合模型区域滑坡易发性及精度分析[J]. 西北地质, 2021, 54(02): 259-272.
WANG Gaofeng, GUO Ning, DENG Bing, et al. Analysis of Landslide Susceptibility and Accuracy in Different Combination Models. Northwestern Geology
王倩, 薛云, 张维, 等. 基于支持向量机的滑坡易发性评价[J]. 湖南城市学院学报(自然科学版), 2021, 30(01): 22-28.
WANG Qian, XUE Yun, ZHANG Wei, et al. Landslide susceptibility mapping based on support vector machine models. Journal of Hunan City University (Natural Science)
王念秦, 郭有金, 刘铁铭, 等. 基于支持向量机模型的滑坡危险性评价[J]. 科学技术与工程, 2019, 19(35): 70-78. doi: 10.3969/j.issn.1671-1815.2019.35.010
WANG Nianqin, GUO Youjin, LIU Tieming, et al. Landslide susceptibility assessment based on support vector machine model. Science Technology and Engineering doi: 10.3969/j.issn.1671-1815.2019.35.010
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(01): 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. Earth Science
谢婉丽, 葛瑞华, 郭倩怡, 等. 灌溉作用下黄土宏观力学响应及微观结构特性研究[J]. 水文地质工程地质, 2017, 44(02): 82-89.
XIE Wanli, GE Ruihua, GUO Qianyi, et al. A study of macro mechanical response and microstructure characteristics of loess under irrigation mechanism. Hydrogeology & Engineering Geology
谢婉丽, 滕宏泉, 杜蕾, 等. 大西安地区滑坡分类及其特征分析[J]. 地球环境学报, 2018a, 9(01): 79-88. doi: 10.7515/JEE182006
XIE Wanli, TENG Hongquan, DU Lei, et al. An analysis of landslide classifications and characteristics in Xi’an[J].Journal of Earth Environment, 2018a, 9(1):79-88. doi: 10.7515/JEE182006
谢婉丽, 滕宏泉, 杜蕾, 等. 基于GIS结合模糊信息方法在灾害危险性区划中的应用——以大西安地区崩滑地质灾害为例[J]. 灾害学, 2018b, 33(03): 111-116. doi: 10.3969/j.issn.1000-811X.2018.03.021
XIE Wanli, TENG Hongquan, DU Lei, et al. The Application of Evaluation Method Combing Fuzzy Information with GIS to Mapping Susceptibility and Risk of Geological Disasters of Landslide and Collapse in Greater Xi’an Region. Journal of Catastrophology doi: 10.3969/j.issn.1000-811X.2018.03.021
杨华阳, 许向宁, 杨鸿发. 基于证据权法的九寨沟地震滑坡危险性评价[J]. 中国地质灾害与防治学报, 2020, 31(03): 20-29.
YANG Huayang, XU Xiangning, YANG Hongfa. The Jiuzhaigou co-eismic landslide hazard assessment based on weight of evidence method. The Chinese Journal of Geological Hazard and Control
杨永刚, 殷坤龙, 赵海燕, 等. 基于C5.0决策树-快速聚类模型的万州区库岸段乡镇滑坡易发性区划[J]. 地质科技情报, 2019, 38(06): 189-197.
YANG Yonggang, YIN Kunlong, ZHAO Haiyan, et al. Landslide Susceptibility Evaluation for Township Units of Bank Section in Wanzhou District Based on C5. 0 Decision Tree and K Means Cluster Model. Geological Science and Technology Information
赵冬梅, 角媛梅, 邱应美, 等. 基于MaxEnt模型的哈尼梯田核心区滑坡易发性评价[J]. 水土保持研究, 2020, 27(04): 392-399+407.
ZHAO Dongmei, JIAO Yuanhai, QIU Yingmei, et al. Assessment on Landslide Susceptibility of the Core Area of Hani Race Terraces Heritage Site Maximum Entropy Model. Research of Soil and Water Conservation
赵铮, 陈建华, 甘先霞, 等. 基于信息量法和支持向量机的芦山县滑坡危险性评价[J]. 物探化探计算技术, 2022, 44(01): 96-101. doi: 10.3969/j.issn.1001-1749.2022.01.12
ZHAO Zheng, CHEN Jianhua, GAN Xianxia, et al. Risk assessment of landslides in Lushan county method and support vector based on information value machine. Computing Techniques for Geophysical and Geochemical Exploration doi: 10.3969/j.issn.1001-1749.2022.01.12
Dickson M E, Perry G. Identfying the controls on coastal cliff landslides using machine-learning approaches [J]. Environmental Modelling and Software, 2016, 76(4): 117-127.
Felicisimo, Cuartero, Remondo, et al. Mapping landslide susceptibility with logistic regression, multiple adaptive regression splines, classification and regression trees, and maximum entropy methods: a comparative study[J]. Landslides, 2013, 10(2): 175-189. doi: 10.1007/s10346-012-0320-1
Kornejady, Aiding, Ownegh, et al. Landslide susceptibility assessment using maximum entropy model with two different data sampling methods[J]. Catena, 2017, 152: 144-162. doi: 10.1016/j.catena.2017.01.010
LIU Handong, LIU Jing jing, CHEN Jiaxing, et al. Tilt deformation and instability of the slope for predicting rainfall-induced landslide[J]. Arabian Journal of Geosciences, 2022, 15(3): 257-271. doi: 10.1007/s12517-021-09338-8
Maryam Mokhtari, Sahar Abedian. Spatial prediction of landslide susceptibility in Taleghan basin, Iran[J]. Stochastic Environmental Research and Risk Assessment, 2019, 33(7): 1297-1325. doi: 10.1007/s00477-019-01696-w
Shrestha S, Kang T S. Assessment of seismically-induced landslide susceptibility after the 2015 Gorkha earthquake, Nepal[J]. Bulletin of Engineering Geology and the Environment, 2019, 78(3): 1829-1842. doi: 10.1007/s10064-017-1191-4
Suchita Shrestha, Tae-Seob Kang. Earthquake induced landslide susceptibility mapping by comparing MaxEnt and Random Forest models: a case study from Nepal Himalaya[J]. 대한지질학회 학술대회, 2016, 10: 261.
-
图(6)
表(2)
计量
- 文章访问数: 2518
- PDF下载数: 146
- 施引文献: 0