[1]温亚楠,张志华,慕号伟,等.动态多源数据驱动模式下的滑坡灾害空间预测[J].自然灾害学报,2021,30(03):083-92.[doi:10.13577/j.jnd.2021.0310]
 WEN Yanan,ZHANG Zhihua,MU Haowei,et al.Landslide disaster spatial prediction under dynamic multi-source data-driven model[J].,2021,30(03):083-92.[doi:10.13577/j.jnd.2021.0310]
点击复制

动态多源数据驱动模式下的滑坡灾害空间预测
分享到:

《自然灾害学报》[ISSN:/CN:23-1324/X]

卷:
30
期数:
2021年03期
页码:
083-92
栏目:
出版日期:
2021-06-28

文章信息/Info

Title:
Landslide disaster spatial prediction under dynamic multi-source data-driven model
作者:
温亚楠123 张志华123 慕号伟123 田德宇4 王筱宇123
1. 兰州交通大学 测绘与地理信息学院, 甘肃 兰州 730070;
2. 地理国情监测技术应用国家地方联合工程研究中心, 甘肃 兰州 730070;
3. 甘肃省地理国情监测工程实验室, 甘肃 兰州 730070;
4. 中科院西北生态环境资源研究院, 甘肃 兰州 730000
Author(s):
WEN Ya’nan123 ZHANG Zhihua123 MU Haowei123 TIAN Deyu4 WANG Xiaoyu123
1. Faculty of Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, China;
2. National-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring, Lanzhou 730070, China;
3. Gansu Provincial Engineering Laboratory for National Geographic State Monitoring, Lanzhou 730070, China;
4. Northwest Institute of Eco-Environmental Resources, CAS, Lanzhou 730000, China
关键词:
滑坡空间预测机器学习谷歌地球引擎动态多源遥感数据数据驱动
Keywords:
landslide spatial predictionmachine learningGoogle Earth Enginedynamic remote sensing datadata driving
分类号:
TP79;X4
DOI:
10.13577/j.jnd.2021.0310
摘要:
滑坡作为危害程度仅次于地震的地质灾害对人类生命和财产安全造成严重威胁,快速准确的滑坡空间预测对人类可持续发展具有重要意义。该研究基于谷歌地球引擎平台,利用动态多源遥感大数据和机器学习算法对滑坡灾害进行训练和预测。首先对2016-2019年全国发生的滑坡灾害建库,并按照7:3随机划分训练集和验证集,然后在主成分分析和特征递归消除特征优化的基础上采用支持向量机和随机森林分类器进行分类和预测,最后通过受试者工作特征曲线的面积量化值评价预测模型。试验表明:特征递归消除结合随机森林方法(RFE-RF)不仅在训练集上表现出较好的预测性能,而且在验证集上获得了最高的预测精度。因此,基于动态多源遥感数据,RFE-RF模型可以在灾害发生前为滑坡预警提供数据参考,旨在探索一种结合遥感大数据和机器学习的滑坡空间预测新思路。
Abstract:
Landslide, the geological disaster second only to earthquake, led to the serious threat to life and property safety of human. Rapid and accurate landslide prediction has tremendous significance for human sustainable development. Based on Google Earth Engine platform, dynamic multi-source remote sensing big data and machine learning algorithms were utilized to train and predict landslide disasters. Firstly, a database of landslide disasters in the country from 2016-2019 was established,and the training dataset and the validation dataset is divided according to 7:3 randomly. Then, support vector machines classifier and random forest classifier are used for classification and prediction based on feature optimization operation of principal component analysis and feature recursive elimination. Finally, the area quantized value of the receiver operating characteristic curve was employed to evaluate the predictive model. The experiment shows that the feature recursive elimination combined with random forest method (RFE-RF) not only exhibits preferable prediction performance in the training dataset, but also obtains the highest prediction accuracy in the validation dataset. Therefore, based on dynamic multi-source remote sensing data, the RFE-RF model can provide data references for landslide warning before disasters. The research aims to explore a new idea for landslide prediction by combining remote sensing big data and machine learning.

参考文献/References:

[1] Cogan J,Gratchev I. A study on the effect of rainfall and slope characteristics on landslide initiation by means of flume tests[J]. Landslides, 2019, 16(12):2369-2379.
[2] 环境监测院. 2019年全国地质灾害通报[EB/OL]. (2020-03-31). http://cigem.cn/auto/dbfile/file?db=1006&rid=48834&fid=285f. Environmental Monitoring Institute. 2019 National Geological Hazard Bulletin[EB/OL]. (2020-03-31). http://cigem.cn/auto/dbfile/file?db=1006&rid=48834&fid=285f,2020-03-31. (in Chinese)
[3] 陈亚亚,刘传胜,杨瑞霞, 等. 世界自然遗产地突发性地质灾害全球尺度危险性评价[J]. 自然灾害学报, 2020, 29(2):87-96. CHEN Yaya, LIU Chuansheng, YANG Ruixia, et al. Global-scale risk assessment of sudden geological disasters in world natural heritage sites[J]. Journal of Natural Disasters, 2020, 29(2):87-96. (in Chinese)
[4] SAITO M. Failure of soil due to creep[C]//Proceeding 5th International Conference of Soil Mechanics and Foundation Engineering, 1961.
[5] 何满潮. 滑坡地质灾害远程监测预报系统及其工程应用[J]. 岩石力学与工程学报, 2009, 28(6):1081-1090. HE Manchao. Real-Time remote monitoring and forecasting system forgeological disasters of landslides and its engineering application[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2009, 28(6):1081-1090. (in Chinese)
[6] 王志旺,李端有,王湘桂. 区域滑坡空间预测方法研究综述[J]. 长江科学院院报, 2012, 29(5):78-85+94. WANG Zhiwang, LI Duanyou, WANG Xianggui. Review of researches on regional landslide susceptibility mapping model[J]. Journal of Yangtze River Scientific Research Institute, 2012, 29(5):78-85+94. (in Chinese)
[7] 高华喜,殷坤龙. 基于GIS的滑坡灾害风险空间预测[J]. 自然灾害学报, 2011, 20(1):31-36. GAO Huaxi, YIN Kunlong. GIS-based spatial prediction of landslide hazard risk[J]. Journal of Natural Disasters, 2011, 20(1):31-36. (in Chinese)
[8] 方丹,胡卓玮,王志恒. 基于GIS的北川县地震次生滑坡灾害空间预测[J]. 山地学报, 2012, 30(2):230-238. FANG Dan, HU Zhuowei, WANG Zhiheng. Spatial prediction of earthquake-induced secondary landslide disaster in Beichuan County based on GIS[J]. Mountain Research, 2012, 30(2):230-238. (in Chinese)
[9] 武雪玲,任福,牛瑞卿. 多源数据支持下的三峡库区滑坡灾害空间智能预测[J]. 武汉大学学报(信息科学版), 2013, 38(8):963-968. WU Xueling, REN Fu, NIU Ruiqing. Spatial intelligent prediction of landslide hazard based on multi-source data in three gorges reservoir area[J]. Geomatics and Information Science of Wuhan University, 2013, 38(8):963-968. (in Chinese)
[10] 赵久彬,刘元雪,刘娜, 等. 海量监测数据下分布式BP神经网络区域滑坡空间预测方法[J]. 岩土力学, 2019,40(7):2866-2872. ZHAO Jiubin, LIU Yuanxue, LIU Na, et al. Spatial prediction method of regional landslide based on distributed bp neural network algorithm under massive monitoring data[J]. Rock and Soil Mechanics, 2019, 40(7):2866-2872. (in Chinese)
[11] Bui D T, Tuan T A,Klempe 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.
[12] Chen W,Xie X, Wang J, et al. A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility[J]. Catena, 2017, 151:147-160.
[13] Pham B T, Prakash I, Bui D T. Spatial prediction of landslides using a hybrid machine learning approach based on random subspace and classification and regression trees[J]. Geomorphology, 2018, 303:256-270.
[14] 朱庆, 丁雨淋, 苗双喜, 等. 动态观测数据驱动的滑坡灾害精准模拟分析方法[J]. 西南交通大学学报, 2016, 51(2):396-403. ZHU Qing, DING Yulin, MIAO Shuangxi, et al. Precise simulation method for dynamic data driven landslide hazards[J]. Journal of Southwest Jiaotong University, 2016, 51(2):396-403. (in Chinese)
[15] 苏白燕, 许强, 黄健, 等. 基于动态数据驱动的地质灾害监测预警系统设计与实现[J]. 成都理工大学学报(自然科学版), 2018, 45(5):615-625. SU Baiyan, XU Qiang, HUANG Jian, et al. Design and implementation of monitoring and early warning system of geological disasters based on dynamic data-driven technology[J]. Journal of Chengdu University of Technology (Science & Technology Edition), 2018, 45(5):615-625. (in Chinese)
[16] 张勤, 黄观文, 杨成生. 地质灾害监测预警中的精密空间对地观测技术[J]. 测绘学报, 2017, 46(10):1300-1307. ZHANG Qin, HUANG Guanwen, YANG Chengsheng. Precision space observation technique for geological hazard Monitoring and early warning[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10):1300-1307. (in Chinese)
[17] 贺为民,杨杰.豫西高速公路滑坡成因分析[J]. 自然灾害学报, 2013, 22(3):244-250. HE Weimin, YANG Jie. Analysis of landslide cause of expressway in western Henan Province[J]. Journal of Natural Disasters, 2013, 22(3):244-250. (in Chinese)
[18] 张江伟,李小军,迟明杰, 等. 滑坡灾害的成因机制及其特征分析[J]. 自然灾害学报, 2015, 24(6):42-49. ZHANG Jiangwei, LI Xiaojun, CHI Mingjie, et al. Analysis of formation mechanism and characteristics of landslide disasters[J]. Journal of Natural Disasters, 2015, 24(6):42-49. (in Chinese)
[19] 孙德亮. 基于机器学习的滑坡易发性区划与降雨诱发滑坡预报预警研究[D]. 华东师范大学, 2019. SUN Deliang. Mapping Landslide Susceptibility Based on Machine Learning and Forecast Warning of Landslide Induced by Rainfall[D]. East China Normal University, 2019. (in Chinese)
[20] 周志华. 机器学习[M]. 北京:清华大学出版社, 2016. ZHOU Zhihua. Mechine Learning[M]. Beijing:Tsinghua University Press, 2016. (in Chinese)
[21] 陈妙金, 汪小钦,吴思颖. 基于随机森林算法的水土流失影响因子重要性分析[J]. 自然灾害学报, 2019, 28(4):209-219. CHEN Miaojin, WANG Xiaoqin, WU Siying. Importance analysis of soil erosion influencing factors based on random forest[J]. Journal of Natural Disasters, 2019, 28(4):209-219. (in Chinese)
[22] 袁颖, 张天亮. 基于主成分分析和支持向量机的苏锡常地区地裂缝危险性预测[J]. 灾害学, 2019, 34(4):57-63. YUAN Ying, ZHANG Tianliang. Prediction of ground fissures risk in Suxichang Area Based on principal component analysis and support vector machine[J]. Journal of Catastrophology, 2019, 34(4):57-63. (in Chinese)
[23] 吴孝情,赖成光,陈晓宏, 等.基于随机森林权重的滑坡危险性评价:以东江流域为例[J]. 自然灾害学报, 2017, 26(5):119-129. WU Xiaoqing, LAI Chengguang, CHEN Xiaohong, et al. A landslide hazard assessment based on random forest weight:a case study in the Dongjiang River Basin[J]. Journal of Natural Disasters, 2017, 26(5):119-129. (in Chinese)
[24] 陈军飞, 董然. 基于随机森林算法的洪水灾害风险评估研究[J]. 水利经济, 2019, 37(3):55-61,87. CHEN Junfei, DONG Ran. Risk assessment of flood disasters based on random forest[J]. Journal of Economics of Water Resources, 2019, 37(3):55-61,87. (in Chinese)
[25] 田述军,张珊珊,唐青松, 等.基于不同评价单元的滑坡易发性评价对比研究[J]. 自然灾害学报, 2019, 28(6):137-145. TIAN Shujun, ZHANG Shanshan, TANG Qingsong, et al. Comparative study of landslide susceptibility assessment based on different evaluation units[J]. Journal of Natural Disasters, 2019, 28(6):137-145. (in Chinese)

相似文献/References:

[1]李海宏,吴吉东,王强,等.基于机器学习方法的上海市暴雨内涝灾情预测模型研究[J].自然灾害学报,2021,30(01):191.[doi:10.13577/j.jnd.2021.0120]
 LI Haihong,WU Jidong,WANG Qiang,et al.A study on rainstorm waterlogging disaster prediction models in Shanghai based on machine learning[J].,2021,30(03):191.[doi:10.13577/j.jnd.2021.0120]
[2]张洪吉,赵铮,陈建华,等.面向滑坡危险性评价的深度一维卷积神经网络方法——以四川省芦山县为例[J].自然灾害学报,2021,30(03):191.[doi:10.13577/j.jnd.2021.0321]
 ZHANG Hongji,ZHAO Zheng,CHEN Jianhua,et al.A deep one-dimensional convolutional neural network method for landslide risk assessment: A case study in Lushan, Sichuan, China[J].,2021,30(03):191.[doi:10.13577/j.jnd.2021.0321]

备注/Memo

备注/Memo:
收稿日期:2020-09-30;改回日期:2020-12-10。
基金项目:国家自然科学基金项目(41861059);兰州交通大学优秀平台(201806)
作者简介:温亚楠(1996-),男,硕士研究生,主要从事机器学习与灾害遥感研究.E-mail:wenyananrs@163.com
通讯作者:张志华(1980-),男,教授,博士,主要从事三维地学模拟、摄影测量与图像识别.E-mail:43447077@qq.com
更新日期/Last Update: 1900-01-01