[1]段中满,贾亮亮,蒋明光,等.基于不同特征选择方法和随机森林法的滑坡易发性评价——以湖南中西部地区为例[J].华南地震,2023,(02):115-124.[doi:10.13512/j.hndz.2023.02.13]
 DUAN Zhongman,JIA Liangliang,JIANG Mingguang,et al.Landslide Susceptibility Assessment Based on Different Feature Selection Methods and Random Forest Method—a Case Study of Central and Western Hunan[J].,2023,(02):115-124.[doi:10.13512/j.hndz.2023.02.13]
点击复制

基于不同特征选择方法和随机森林法的滑坡易发性评价——以湖南中西部地区为例()
分享到:

华南地震[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年02期
页码:
115-124
栏目:
地震与地质灾害
出版日期:
2023-06-20

文章信息/Info

Title:
Landslide Susceptibility Assessment Based on Different Feature Selection Methods and Random Forest Method—a Case Study of Central and Western Hunan
文章编号:
1001-8662(2023)02-0115-10
作者:
段中满1贾亮亮23蒋明光34雷耀波1陈雅娜1
1.湖南省自然资源事务中心,长沙 410118;2.遵义师范学院,贵州遵义563006;3.中南大学,长沙 410083;4.湖南容诚致远工程技术有限公司,长沙 410000
Author(s):
DUAN Zhongman1JIA Liangliang23JIANG Mingguang34LEI Yaobo1CHEN Yana1
1.Hunan Center of Natural Resources Affairs , Changsha 410118, China;2.Zunyi Normal University, Zunyi 563006, China;3.Central South University , Changsha 410083, China;4.Hunan Rongcheng Zhiyuan Engineering Technology Co., Ltd., Changsha 410000, China
关键词:
滑坡最大互信息系数递归特征选择随机森林
Keywords:
LandslideMaximal mutual information coefficientRecursive feature selectionRandom forest
分类号:
P237
DOI:
10.13512/j.hndz.2023.02.13
文献标志码:
A
摘要:
湘中、湘西地区是湖南省滑坡地质灾害最为频发的地区,同时该区旅游资源和自然资源丰富,是滑坡管理的重点区域。为研究湘中、湘西地区滑坡易发性评价模型的适用性,以湖南中西部地区为例,在初步选取的15个滑坡致灾因子的基础上,采用最大互信息系数、递归特征选择、基于随机森林的基尼不纯度指标和平均精确度指标等方法开展滑坡致灾因子优化,分析剔除了平面曲率和剖面曲率两个不重要因子,最终提取了13个重要因子,利用随机森林模型开展了研究区易发性评价,并采用最近两年滑坡数据开展验证。结果表明:不同特征选择方法优化后的滑坡因子结合随机森林模型所得的模型结果与实际情况吻合性较好,中、较高和高易发区滑坡占比77.58%,验证结果为79.58%,该模型对湘中、湘西地区地质灾害易发性评价模型选取提供了参考与借鉴。
Abstract:
The central and western Hunan is the most frequent area of landslide geological disasters in Hunan Province. At the same time, the area is rich in tourism and natural resources, and is the key area for landslide management. In order to study the applicability of the landslide susceptibility evaluation model in central and western Hunan,the historical landslides points and their corresponding features in central and western Hunan are taken as analysis data. Based on the 15 landslide disaster factors initially selected, the maximum mutual information coefficient, recursive feature selection, Gini impurity index based on random forest and average accuracy index are used to optimize the landslide disaster factors. Two unimportant factors of plane curvature and profile curvature are eliminated,and 13 important factors are finally extracted. The random forest model is used to evaluate the susceptibility of the study area, and the landslide data in the last two years are used for verification. The results show that the model results obtained by combining the landslide factors optimized by different feature selection methods with the random forest model are in good agreement with the actual situation. The proportion of landslides in medium, high and high prone areas is 77.58 % , and the verification result is 79.58 % . The model provides a reference for the selection of geological disaster susceptibility evaluation models in central and western Hunan.

参考文献/References:

[1] Neuland, Herbert. A prediction model of landslips[J]. Catena,1976,3(2),215-230[2] Rasmussen C E,Nickisch H. Gaussian processes for machine learning (GPML)toolbox[J]. Journal of Machine Learning Research,2010,11(6),3011-3015[3] Chen Weitao,Li Xianju,Wang Yanxin,et al. Forested landslide detection using LiDAR data and the random forest algorithm: a case study of the Three Gorges, China[J]. Remote Sensing of Environment,2014(152):291-301.[4] Amiri M,Pourghasemi H R,Ghanbarian G A,et al. Assessment of the importance of gully erosion effective factors using Boruta algorithm and its spatial modeling and mapping using three machine learning algorithms[J]. Geoderma,2019(340):55-69.[5] Abu El-magd S A,Ali S A,Pham Q B. Spatial modeling and susceptibility zonation of landslides using random forest, na?ve bayes and K-nearest neighbor in a complicated terrain [J]. Earth Science Informatics,2021,14(3):1227-1243.[6] Van Den Eeckhaut M,Marre A,Poesen J. Comparison of two landslide susceptibility assessments in the Champagne-Ardenne region(France)[J]. Geomorphology,2010,115(1/2):141-155.[7] Zhou C,Yin K L,Cao Y,et al. Landslide susceptibility modeling applying machine learning methods:a case study from Longju in the Three Gorges Reservoir area,China[J]. Computers&Geosciences,2008(112):23-37.[8]付旭东,王金艳,李龙燕,等.基于随机森林算法的风场预报[J].兰州大学学报(自然科学版),2021,57(4):503-509.[9] Sajadi P,Sang Y F,Gholamnia M,et al. Evaluation of the landslide susceptibility and its spatial difference in the whole Qinghai-Tibetan Plateau region by five learning algorithms [J]. Geoscience Letters,2022(9):1-25.[10] Sun D L,Gu Q Y,Wen H J,et al. A hybrid landslide warning model coupling susceptibility zoning and preci-pitation[J]. Forests,2022,13(6):827.[11]郭明珠,刘晃,王欢欢,等.金沙江上游贡扎村岩质滑坡发育特征及演化成因分析[J].地震研究,2021,44(2):242-250.[12] Reshef D N,Reshef Y A,Finucane H K,et al. Detecting novel associations in large data sets[J]. Science,2011,334 (6062):1518-1524.[13] Guyon I,Weston J,Barnhill S,et al. Gene selection for cancer classification using support vector machines[J]. Machine learning,2022,46(1-3):389-422.[14]姚登举,杨静,詹晓娟.基于随机森林的特征选择算法[J].吉林大学学报(工学版),2014,44(1):137-141.[15] Breiman L. Random forests[J]. Machine Learning,2001,45 (1):5-32.[16]刘坚,李树林,陈涛.基于优化随机森林模型的滑坡易发性评价[J].武汉大学学报(信息科学版),2018,43(07):1085-1091.[17]姚雄,余坤勇,刘健,等.基于随机森林模型的降水诱发山体滑坡空间预测技术[J].福建农林大学学报(自然科学版),2016,45(02):219-227.[18] Wang L Q,Zhang Z H,Huang B L,et al. Triggering mechanism and possible evolution process of the ancient Qingshi landslide in the Three Gorges Reservoir[J]. Geomatics Natural Hazards & Risk,2021,12(1):3160-74.[19] Zhang K Q,Wang L Q,Zhang W G,et al. Formation and failure mechanism of the Xinfangzi landslide in Chongqing City(China)[J]. Applied Sciences,2021,11(19):8693[20]白仙富,戴雨芡,叶燎原,等.基于GIS和专家知识的滇西南地区滑坡敏感性模糊逻辑推理方法[J].地震研究, 2022,45(1):118-131.[21] Li L,Lan H,Guo C,et al. A modified frequency ratio method for landslide susceptibility assessment[J]. Landsli-des,2016,14(2):727-741.[22] Long J J,Liu Y,Li C D,et al. A novel model for regional susceptibility mapping of rainfall reservoir induced landslides in Jurassic slide-prone strata of western Hubei Province, Three Gorges Reservoir area[J]. Stochastic Environmental Research and Risk Assessment,2021,35 (7):1403-26.[23] Sun D L,Xu J H,Wen H J,et al. Assessment of landslide susceptibility mapping based on Bayesian hyperparameter optimization:a comparison between logistic regression and random forest[J]. Engineering Geology,2021(281):105792.[24] Zhou X Z,Wen H J,Li Z W,et al. An interpretable model for the susceptibility of rainfall-induced shallow landslides based on shap and xgboost[J]. Geocarto International,2022, 37(23):1-27.[25] Weiss A. Topographic position and landforms analysis[R]. San Diego,CA :ESRI user conference,2001.[26]叶润青,李士垚,郭飞,等.基于RS和GIS的三峡库区滑坡易发程度与土地利用变化的关系研究[J].工程地质学报,2021,29(03):724-33.[27] Gariano S L,Rianna G,Petrucci O,et al. Assessing future changes in the occurrence of rainfall-induced landslides at a regional scale[J]. Sci Total Environ,2017(596/597):417-426 .[28] He Q,Shahabi H,Shirzadi A, et al. Landslide spatial modelling using novel bivariate statistical based Naive Bayes,RBF Classifier,and RBF Network machine learning algorithm[J]. Sci Total Environ,2019(663):1-15.[29] Juliev M,Mergili M,Mondal I,et al. Comparative analysis of statistical methods for landslide susceptibility mapping in the Bostanlik District, Uzbekistan[J]. Sci Total Environ, 2019(653):801-814.

相似文献/References:

[1]邱慧玲,龙文华,卿展晖.模糊数学在滑坡治理工程后评价中的应用[J].华南地震,2023,(04):75.[doi:10.13512/j.hndz.2023.04.10]
 QIU Huiling,LONG Wenhua,QING Zhanhui.Application of Fuzzy Mathematics in Post-evaluation of Landslide Treatment Project[J].,2023,(02):75.[doi:10.13512/j.hndz.2023.04.10]

备注/Memo

备注/Memo:
收稿日期:2022-10-12基金项目:基于大数据分析和地质-岩土-降雨耦合的降雨诱发型滑坡预警模型应用示范(湘财建二指[2019]19号);遵义师范学院学术新苗培育项目(遵师XM[2021]1号-07);遵义师范学院2021年乡村振兴项目(黔教合KY字[2016]018-5号)联合资助。作者简介:段中满(1975-),男,硕士,高级工程师,长期从事地质灾害监测预警、调查评价工作。E-mail:1002295900@qq.com通信作者:贾亮亮(1986-),男,博士研究生,副教授,长期从事地质灾害监测预警、调查评价工作。E-mail:451518464@qq.com
更新日期/Last Update: 2023-06-15