[1]文海家,李洋,薛靖元,等.基于大数据挖掘的山区公路沿线滑坡易发性小区划[J].自然灾害学报,2018,(04):159-165.[doi:10.13577/j.jnd.2018.0421]
 WEN Haijia,LI Yang,XUE Jingyuan,et al.Landslides susceptibility microzoning along highway in mountainous region based on mining the big data[J].,2018,(04):159-165.[doi:10.13577/j.jnd.2018.0421]
点击复制

基于大数据挖掘的山区公路沿线滑坡易发性小区划
分享到:

《自然灾害学报》[ISSN:/CN:23-1324/X]

卷:
期数:
2018年04期
页码:
159-165
栏目:
出版日期:
2018-09-28

文章信息/Info

Title:
Landslides susceptibility microzoning along highway in mountainous region based on mining the big data
作者:
文海家123 李洋1 薛靖元1 谢朋1
1. 山地城镇建设与新技术教育部重点实验室, 重庆 400045;
2. 库区环境地质灾害防治国家地方联合工程研究中心, 重庆 400044;
3. 重庆大学 土木工程学院, 重庆 400045
Author(s):
WEN Haijia123 LI Yang1 XUE Jingyuan1 XIE Peng1
1. Key Laboratory of New Technology for Construction of Cities in Mountain Area(Chongqing University), Ministry of Education, Chongqing 400045, China;
2. National Joint Engineering Research Center of Geohazards Prevention in the Reservoir Areas, Chongqing 400044, China;
3. School of Civil Engineering, Chongqing University, Chongqing 400045, China
关键词:
山区公路沿线滑坡小区划地理空间数据大数据挖掘逻辑回归模型
Keywords:
along highway in mountainous regionlandslide microzoninggeo-spatial databasemining the big dataLR model
分类号:
U41;X43;X9
DOI:
10.13577/j.jnd.2018.0421
摘要:
本文目的是基于滑坡灾害因子地理空间数据、历史滑坡大数据分析,构建山区公路沿线滑坡易发性精细化评价的逻辑回归模型。选取高程、坡度、坡向、坡位、微地貌、曲率、顺逆向坡、归一化植被指数、岩性、距水系距离、距断层距离、距道路距离、多年平均降雨13个因子作为滑坡易发性影响因子,以30 m精度栅格建立影响因子地理空间数据库。在研究区域441个历史滑坡数据的基础上,将地理空间分划分为滑坡区与非滑坡区,分别随机选取70%的滑坡区域与非滑坡区作为训练数据集,剩下的30%作为验证数据集。通过样本数据集的训练,建立逻辑回归分析模型。利用训练好的逻辑回归模型,对整个研究区滑坡易发性进行仿真预测。结果显示,滑坡极低、低、中、高、极高易发区面积分别占42.24%、18.42%、17.57%、16.37%、5.41%,高、极高易发区与历史滑坡位置吻合度高;训练数据集、验证数据集以及区域仿真的ROC曲线AUC值分别为0.89、0.83、0.87,评价模型具有较高的稳定性与可靠性;新近发生的3个典型滑坡均处于高或极高易发区,模型具有良好的预测功能。
Abstract:
The purpose of this paper is to construct a LR model for evaluating landslide susceptibility refinement along mountainous highways based on landslide hazard geospatial data and historic landslide big data. The chosen landslide-conditioning factors were altitude, slope angle, slope aspect, slop position, micro-landform, slope curvature, consequent-reverse slop, normalized differential vegetation index(NDVI), lithology, distance to drainage, distance to faults, distance to highway and annual rainfall. Based on the data of 441 historical landslides in the study area, the geographical space is divided into landslide areas and non-landslide areas. 70% of landslide areas and non-landslide areas are randomly selected as training data sets, and the remaining 30% are used as verification data sets. Using the model trained by sample data to simulate the landslide susceptibility in the study area. The susceptibility map was divided into five classes, that is, very low susceptibility, low susceptibility, moderate susceptibility, high susceptibility and very high susceptibility region which represent 42.24%, 18.42%, 17.57%, 16.37% and 5.41%, high susceptibility and very high susceptibility region have a high degree of coincidence with historical landslides. The receiver operating characteristic curve showed that the prediction accuracy of training dataset, validation dataset and whole dataset were 0.89, 0.87 and 0.83 which indicates the model has high stability and reliability; Three recent typical landslides are located in high or very high susceptibility region which indicates the model has good prediction function.

参考文献/References:

[1] 参考消息. 国土资源部:茂县共有地质灾害隐患点538处[EB/OL]. (2017-06-24)[2017-6-29]. http://www.cankaoxiaoxi.com/china/20170624/2145354.shtml. Reference News. Ministry of Land and Resources:There are 538 hidden danger points of geological disasters in Mao County[EB/OL]. (2017-06-24)[2017-6-29]. http://www.cankaoxiaoxi.com/china/20170624/2145354.shtml. (in Chinese)
[2] 百度百科. 6·24茂县山体滑坡[EB/OL]. (2017-06-28)[2017-06-29]. https://baike.baidu.com/item/6%C2%B724%E8%8C%82%E5%8E%BF%E5%B1%B1%E4%BD%93%E6%BB%91%E5%9D%A1/21496563?fr=aladdin. Baidu Encyclopedia. Maoxian mountain landslide in June 24th[EB/OL]. (2017-06-28)[2017-06-29]. https://baike.baidu.com/item/6%C2%B724%E8%8C%82%E5%8E%BF%E5%B1%B1%E4%BD%93%E6%BB%91%E5%9D%A1/21496563?fr=aladdin. (in Chinese)
[3] Krishna A P. Landslide hazard assessment along a mountain highway in the Indian Himalayan Region (IHR) using remote sensing and computational models[C]//2013:6480-6484.
[4] 刘洋洋, 李永强, 李有鹏, 等. 基于AHP-模糊综合评价法的山区丘陵公路灾害易损性研究——以河南省修武县为例[J]. 灾害学, 2017, 32(2):32-38. LIU Yangyang, LI Yongqiang, LI Youpeng, et al. Research of highway diaster vulnerablity based on AHP-Fuzzy comperhensive evaluation method:a case study of Xiuwy County in Henan Province[J]. Journal of Catastrophology, 2017, 32(2):32-38. (in Chinese)
[5] Shou K J, Lin J F. Multi-scale landslide susceptibility analysis along a mountain highway in Central Taiwan[J]. Engineering Geology, 2016, 212:120-135.
[6] 文海家, 胡东萍, 王桂林. 汶川县地震滑坡易发性LR与NN评价比较研究[J]. 土木工程学报, 2014, 47(S1):17-23. WEN Haijia, HU Dongping, WANG Guilin. A comparative study on the susceptibility mapping of earthquake triggered landslide by neural network and logistic regression model, Wenchuan County[J]. China Civil Engineering Journal, 2014, 47(S1):17-23. (in Chinese)
[7] JIANG W, RAO P, CAO R, 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.
[8] Abedini M, Ghasemyan B, Mogaddam M H R. Landslide susceptibility mapping in Bijar city, Kurdistan Province, Iran:a comparative study by logistic regression and AHP models[J]. Environmental Earth Sciences, 2017, 76(8):308.
[9] Youssef A M. Landslide susceptibility delineation in the Ar-Rayth area, Jizan, Kingdom of Saudi Arabia, using analytical hierarchy process, frequency ratio, and logistic regression models[J]. Environmental Earth Sciences, 2015, 73(12):8499-8518.
[10] WEN H, XIE P, XIAO P, et al. Rapid susceptibility mapping of earthquake-triggered slope geohazards in Lushan County by combining remote sensing with the AHP model developed for the Wenchuan earthquake[J]. Bulletin of Engineering Geology & the Environment, 2016, 76(3):909-921.
[11] WEN H. A susceptibility mapping model of earthquake-triggered slope geohazards based on geo-spatial data in mountainous regions[J]. Georisk:Assessment and Management of Risk for Engineered Systems and Geohazards, 2015, 9(1):25-36.
[12] 谢朋, 文海家, 胡东萍. 山区公路沿线地震滑坡易发性区划研究[J]. 中国公路学报, 2018, 31(2):106-114. XIE Peng, WEN Haijia, HU Dongping. Research on susceptibility mapping of earthquake-induced landslides along highway in mountainous region[J]. China Journal of Highway and Transport, 2018, 31(2):106-114. (in Chinese)
[13] WANG L J, GUO M, SAWADA K, et al. A comparative study of landslide susceptibility maps using logistic regression, frequency ratio, decision tree, weights of evidence and artificial neural network[J]. Geosciences Journal, 2016, 20(1):117-136.
[14] Tsangaratos P, Ilia I, Hong H, et al. Applying information theory and GIS-based quantitative methods to produce landslide susceptibility maps in Nancheng County, China[J]. Landslides, 2017, 14(3):1091-1111.
[15] Peng Xie, Haijia Wen, Chaochao Ma, Laurie G. Baise & Jialan Zhang. Application and comparison of logistic regressionmodel and neural network model in earthquake-induced landslides susceptibility mapping at mountainous region, China[J]. Geomatics, Natural Hazards and Risk, 20189(1):501-523.
[16] Yi Lmaz I. Comparison of landslide susceptibility mapping methodologies for Koyulhisar, Turkey:conditional probability, logistic regression, artificial neural networks, and support vector machine[J].Environmental Earth Sciences, 2010, 61(4):821-836.
[17] 张建强, 苏凤环, 范建容. "4·20"芦山地震崩塌滑坡与公路危险性评价——以宝兴县省道S210沿线为例[J]. 山地学报, 2013, 31(5):616-623. ZHANG Jianqing, SU Fenghuan, FAN Jianrong. Distribution of landslides and collapses induced by 2013"4·20"Lushan earthquake and hazards assessment:a case study of S210 highway[J]. Journal of Mountain Science, 2013, 31(5):616-623. (in Chinese)
[18] Netra Prakash Bhandary, Ryuichi Yatabe, Ranjan Kumar Dahal, et al. Areal distribution of large-scale landslides along highway corridors in central Nepal[J]. Georisk:Assessment and Management of Risk for Engineered Systems and Geohazards, 2013, 7(1):1-20.

备注/Memo

备注/Memo:
收稿日期:2018-05-30;改回日期:2018-06-19。
基金项目:教育部留学回国人员科研启动基金项目([2015]1098);重庆市发展和改革委员会2016年高技术产业技术开发专项项目([2016]1270);重庆市留学回国人员创业创新支持项目(CX2017125);重庆市科技计划技术创新与应用示范项目(cstc2018jscx-msybX0310);中央高校基本科研业务费专项(2018CDPTCG0001/38)
作者简介:文海家(1971-),男,教授,博士,主要从事岩土工程大数据防灾减灾研究.E-mail:jhw@cqu.edu.cn
更新日期/Last Update: 1900-01-01