基于综合智能分析的广东省崩塌易发性评价

doi:10.13722/j.cnki.jrme.2022.1204

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (7107 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要本文旨在使用智能分析模型提高广东省崩塌易发性评价精度。为此，收集该省7 171个崩塌数据以及13个基础环境因子，并用分批分块的方式解决了海量数据处理的问题。利用随机森林模型(RF)和耦合频率比–随机森林模型(FR–RF)开展全省1∶5万精度的崩塌易发性评价，采用受试者工作曲线和易发性分布特征来评估模型性能，并与传统评价方法(层次分析法(AHP)、频率比法(FR)和耦合频率比–层次分析法(FR–AHP))进行比较。结果表明：(1) 13个基础环境因子无显著相关且都具有较高贡献度，地形起伏、高程、多年平均降雨量是影响广东省崩塌发生的最主要环境因子；(2) 广东省崩塌极高、高易发区主要分布在东北部、中部和西南部地区；(3) 5种模型中RF的预测精度最高，AUC值为0.884，其次为FR–RF(0.860)，FR–AHP(0.797)，FR(0.794)和AHP(0.601)，且RF和FR–RF的易发性指数不确定性较低。除AHP外，4种模型都能得到合理的崩塌易发性评价结果，而RF是最适宜评价广东省崩塌易发性的方法。总体而言，智能分析方法性能优于传统评价方法。本文成果可为大尺度低海拔区域崩塌易发性评价提供参考。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	雷成铭1
	刘春艳2
	张云斌2
	成建梅1
	赵锐锐1

关键词 ：边坡工程, 崩塌易发性评价, 层次分析法, 频率比法, 随机森林, 省级尺度

Abstract：This study aims to improve the evaluation accuracy of collapse susceptibility in Guangdong Province using an intelligent analysis model. To this end，7 171 collapse data and 13 basic environmental factors in the province are collected，and the problem of massive data processing is solved by batch and block methods. Random Forest model(RF) and the coupled Frequency Ratio-Random Forest model(FR–RF) are used to carry out 1∶50 000 accuracy evaluation of collapse susceptibility. The performance of the model is evaluated by the receiver operating curve and the susceptibility distribution characteristics. The evaluation results were compared with those of traditional evaluation methods(Analytic Hierarchy Process(AHP)，Frequency Ratio(FR) and Coupled Frequency Ratio-Analytic Hierarchy Process(FR–AHP)). The results show that：(1) The 13 basic environmental factors have no significant correlation，and they all have a high degree of contribution. Topographic relief，elevation and annual average rainfall are the most important environmental factors affecting the occurrence of collapses in Guangdong Province；(2) The very high and high susceptibility areas are mainly distributed in the northeast，central and southwestern regions；(3) Among the five models，the prediction accuracy of RF is the highest，with an AUC value of 0.884，followed by FR–RF(0.860)，FR–AHP(0.797)，FR(0.794) and AHP (0.601). The uncertainty of the susceptibility index of RF and FR–RF is low. Except for AHP，all four models can be used to obtain reasonable evaluation results of collapse susceptibility，and RF has been found to be the most suitable method to evaluate the collapse susceptibility of Guangdong Province. Overall，the performance of the intelligent analysis method is better than that of the traditional evaluation method. This study can be considered as a reference for the evaluation of collapse susceptibility in large-scale low-altitude areas.

Key words： slope engineering evaluation of collapse susceptibility analytical hierarchy process frequency ratio random forest provincial scale

引用本文:

雷成铭1，刘春艳2，张云斌2，成建梅1，赵锐锐1. 基于综合智能分析的广东省崩塌易发性评价[J]. 岩石力学与工程学报, 2023, 42(S2): 4248-4260.
LEI Chengming1，LIU Chunyan2，ZHANG Yunbin2，CHENG Jianmei1，ZHAO Ruirui1. Evaluation of collapse susceptibility in Guangdong Province based on comprehensive intelligent analysis. , 2023, 42(S2): 4248-4260.

链接本文:

http://rockmech.whrsm.ac.cn/CN/10.13722/j.cnki.jrme.2022.1204 或 http://rockmech.whrsm.ac.cn/CN/Y2023/V42/IS2/4248

[38]	REICHENBACH P，ROSSI M，MALAMUD B D，et al. A review of statistically-based landslide susceptibility models[J]. Earth-science reviews，2018，180：60-91.
[3]	邱海军. 区域滑坡崩塌地质灾害特征分析及其易发性和危险性评价研究——以宁强县为例[博士学位论文][D]. 西安：西北大学，2012.(QIU Haijun. Study on the regional landslide characteristic analysis and hazard assessment：a case study of Ningqiang County[Ph. D. Thesis][D]. Xi?an：Northwest University，2012.(in Chinese))
[4]	胡涛，樊鑫，王硕，等. 基于径向基神经网络的思南县崩塌易发性评价[J]. 科学技术与工程，2019，19(35)：61-69.(HU Tao，FAN Xing，WANG Suo，et al. Collapse susceptibility assessment of Sinan County based on radial basis function neural network[J]. Science Technology and Engineering，2019，19(35)：61-69.(in Chinese))
[8]	许冲，戴福初，姚鑫，等. GIS支持下基于层次分析法的汶川地震区滑坡易发性评价[J]. 岩石力学与工程学报，2009，28(增2)：3 978-3 985.(XU Chong，DAI Fuchu，YAO Xing，et al. GIS-based landslide susceptibility assessment using analytical hierarchy process in Wenchuan earthquake region[J]. Chinese Journal of Rock Mechanics and Engineering，2009，28(Supp.2)：3 978-3 985.(in Chinese))
[10]	王毅，唐川，李为乐，等. 基于GIS的模糊数学模型在泥石流敏感性评价中的应用[J]. 自然灾害学报，2017，26(1)：19-26. (WANG Yi，TANG Chuan，LI Weile，et al. Application of GIS-based fuzzy mathematics model to sensitivity evaluation of debris flow[J]. Journal of Natural Disasters，2017，26(1)：19-26.(in Chinese))
[13]	WANG X，LI S，LIU H，et al. Landslide susceptibility assessment in Wenchuan County after the 5•12 magnitude earthquake[J]. Bulletin of Engineering Geology and the Environment，2021，80(7)：5 369- 5 390.
[14]	TEHRANY M S，PRADHAN B，JEBUR M N. Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS[J]. Journal of Hydrology，2014，512：332-343.
[18]	CHEN W，PENG J，HONG H，et al. Landslide susceptibility modelling using GIS-based machine learning techniques for Chongren County，Jiangxi Province，China[J]. Science of the Total Environment，2018，626：1 121-1 135.
[20]	SUN D，WEN H，WANG D，et al. A random forest model of landslide susceptibility mapping based on hyperparameter optimization using Bayes algorithm[J]. Geomorphology，2020，362：107201.
[23]	CHOWDHURI I，PAL S C，ARABAMERI A，et al. Implementation of artificial intelligence based ensemble models for gully erosion susceptibility assessment[J]. Remote Sensing，2020，12(21)：3 620.
[24]	ARABAMERI A，ASADI N O，SAHA S，et al. Novel ensemble approaches of machine learning techniques in modeling the gully erosion susceptibility[J]. Remote Sensing，2020，12(11)：1 890.
[28]	POLAT A. An innovative，fast method for landslide susceptibility mapping using GIS-based LSAT toolbox[J]. Environmental Earth Sciences，2021，80(6)：1-18.
[6]	ZHU A X，MIAO Y M，WANG R X，et al. A comparative study of an expert knowledge-based model and two data-driven models for landslide susceptibility mapping[J]. Catena，2018，166：317-327.
[16]	王佳佳，殷坤龙，肖莉丽. 基于GIS和信息量的滑坡灾害易发性评价——以三峡库区万州区为例[J]. 岩石力学与工程学报，2014，33(4)：797-808.(WANG Jiajia，YIN Kanlong，XIAO Lili. Landslide susceptibility assessment based on GIS and weighted information value：a case study of Wanzhou district，Three Gorges Reservoir[J]. Chinese Journal of Rock Mechanics and Engineering，2014，33(4)：797-808.(in Chinese))
[2]	吕艳，陈天宝，王祚鹏，等. 太行山大峡谷崩塌发育特征及成因模式研究[J]. 工程地质学报，2022，30(4)：1 304-1 315.(LV Yan，CHEN Tianbao，WANG Zuopeng，et al. Study on the development characteristics and genetic patterns of collapses in the Taihang Mountain Grand Canyon，China[J]. Journal of Engineering Geology，2022，30(4)：1 304-1 315.(in Chinese))
[12]	张钟远，邓明国，徐世光，等. 镇康县滑坡易发性评价模型对比研究[J]. 岩石力学与工程学报，2022，41(1)：157-171.(ZHANG Zhongyuan，DENG Mingguang，XU Shiguang，et al. Comparison of landslide susceptibility assessment models in Zhenkang County，Yunnan Province，China[J]. Chinese Journal of Rock Mechanics and Engineering，2022，41(1)：157-171.(in Chinese))
[22]	HUANG F，CAO Z，GUO J，et al. Comparisons of heuristic，general statistical and machine learning models for landslide susceptibility prediction and mapping[J]. Catena，2020，191：104580.
[26]	PRADHAN B，LEE S. Landslide susceptibility assessment and factor effect analysis：back propagation artificial neural networks and their comparison with frequency ratio and bivariate logistic regression modelling[J]. Environmental Modelling and Software，2010，25(6)：747-759.
[30]	WANG Y，FENG L，LI S，et al. A hybrid model considering spatial heterogeneity for landslide susceptibility mapping in Zhejiang Province，China[J]. Catena，2020，188：104425.
[32]	GOETZ J N，BRENNING A，PETSCHKO H，et al. Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling[J]. Computers & Geosciences ，2015，81： 1-11.
[34]	ZHANG G，CAI Y，ZHENG Z，et al. Integration of the statistical index method and the analytic hierarchy process technique for the assessment of landslide susceptibility in Huizhou，China[J]. Catena，2016，142：233-244.
[1]	王国强，徐威，吴道祥，等. 安徽省环境地质特征与地质灾害[J]. 岩石力学与工程学报，2004，23(1)：164-169.(WANG Guoqiang，XU Wei，WU Daoxiang，et al. Characteristics of environmental geology and geological disasters of Anhui Province[J]. Chinese Journal of Rock Mechanics and Engineering，2004，23(1)：164-169.(in Chinese))
[5]	温鑫，范宣梅，陈兰，等. 基于信息量模型的地质灾害易发性评价：以川东南古蔺县为例[J]. 地质科技通报，2022，41(2)：290-299.(WEN Xin，FAN Xuanmei，CHENG Lan，et al. Susceptibility assessment of geological disasters based on an information value model：A case of Gulin County in Southeast Sichuan[J]. Bulletin of Geological Science and Technology，2022，41(2)：290-299.(in Chinese))
[11]	王春燕，王力. 三峡库区涉水重点滑坡危险性评价方法及防治对策——以白家包滑坡为例[J]. 三峡大学学报：自然科学版，2019，41(5)：47-52.(WANG Chunyan，WANG Li. Risk assessment methods and Countermeasures for key landslide in Three Gorges Reservoir area——Taking Baijibao landslide for example[J]. Journal of China Three Gorges University：Natural Science，2019，41(5)：47-52.(in Chinese))
[15]	李文彬，范宣梅，黄发明，等. 不同环境因子联接和预测模型的滑坡易发性建模不确定性[J]. 地球科学，2021，46(10)：3 777-3 795. (LI Wenshan，FAN Xuanmei，HUANG Faming，et al. Uncertainty of landslide susceptibility modeling under different environmental factor connections and prediction models[J]. Earth Sciences，2021，46(10)：3 777-3 795.(in Chinese))
[21]	仉文岗，何昱苇，王鲁琦，等. 基于水系分区的滑坡易发性机器学习分析方法——以重庆市奉节县为例[J]. 地球科学，2023，48(5)：2 024-2 038.(ZHANG Wengang，HE Yuwei，WANG Luqi，et al. Machine learning solution for landslide susceptibility based on hydrographic division：case study of Fengjie county in Chongqing[J]. Earth Sciences，2023，48(5)：2 024-2 038.(in Chinese))
[25]	王毅，方志策，牛瑞卿，等. 基于深度学习的滑坡灾害易发性分析[J]. 地球信息科学学报，2021，23(12)：2 244-2 260.(WANG Yi，FANG Zhiwen，LIU Liuqing，et al. Landslide susceptibility analysis based on deep learning[J]. Journal of Geo-information Science，2021，23(12)：2 244-2 260.(in Chinese))
[31]	BREIMAN L. Random forests[J]. Machine Learning，2001，45(1)： 5-32.
[35]	BRENNING A. Spatial prediction models for landslide hazards： review，comparison and evaluation[J]. Natural Hazards and Earth System Sciences，2005，5(6)：853-862.
[36]	李军，周成虎. 基于栅格GIS滑坡风险评价方法中格网大小选取分析[J]. 遥感学报，2003，(2)：86-92.(LI Jun，ZHOU Chenghu. Appropriate grid size for terrain based landslide risk assessment in Lantau Island，Hong Kong[J]. Journal of Remote Sensing，2003，(2)，86-92.(in Chinese))
[7]	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.(BAI Xianfu，DAI Yuqian，YE Liaoyuan，et al. A fuzzy logic modeling of landslide susceptibility mapping in Southwest Yunnan Province based on GIS and expert knowledge[J]. Journal of Seismological Research，2022，45(1)：118-131.(in Chinese))
[9]	ZHANG G F，CAI Y X，ZHENG Z，et al. Integration of the statistical index method and the analytic hierarchy process technique for the assessment of landslide susceptibility in Huizhou，China[J]. Catena，2016：233-244.
[17]	XU W，YU W，JING S，et al. Debris flow susceptibility assessment by GIS and information value model in a large-scale region，Sichuan Province(China)[J]. Natural Hazards，2013，65(3)：1 379-1 392.
[19]	CHEN W，SUN Z，ZHAO X，et al. Performance evaluation and comparison of bivariate statistical-based artificial intelligence algorithms for spatial prediction of landslides[J]. ISPRS International Journal of Geo-Information，2020，9(12)：696.
[27]	LI B，WANG N，CHEN J. GIS-based landslide susceptibility mapping using information，frequency ratio，and artificial neural network methods in Qinghai Province，Northwestern China[J]. Advances in Civil Engineering，2021：4758062.
[29]	ZHAO B，GE Y，CHEN H. Landslide susceptibility assessment for a transmission line in Gansu Province，China by using a hybrid approach of fractal theory，information value，and random forest models[J]. Environmental Earth Sciences，2021，80(12)：1-23.
[37]	YANG Y，SUN G，ZHENG H，et al. An improved numerical manifold method with multiple layers of mathematical cover systems for the stability analysis of soil-rock-mixture slopes[J]. Engineering Geology，2020，264：105373.
[33]	黄发明，胡松雁，闫学涯，等. 基于机器学习的滑坡易发性预测建模及其主控因子识别[J]. 地质科技通报，2021，41(2)：79-90. (HUANG Faming，HU Songyan，YAN Xueya，et al. Landslide susceptibility prediction and identification of its main environmental factors based on machine learning models[J]. Geological Science and Technology Bulletin，2021，41(2)：79-90.(in Chinese))
[39]	KAVZOGLU T，SAHIN E，COLKESEN I. Selecting optimal conditioning factors in shallow translational landslide susceptibility mapping using genetic algorithm[J]. Engineering Geology，2015，192：101-112.
[40]	ZHOU X，WEN H，ZHANG Y，et al. Landslide susceptibility mapping using hybrid random forest with GeoDetector and RFE for factor optimization[J]. Geoscience Frontiers，2021，12(5)：101211.