ASSESSMENT OF GEOLOGICAL DISASTER SUSCEPTIBILITY BASED ON SVM-RF MODEL: A Case Study of Qingtian River Scenic Area in Boai County, Henan Province
-
摘要:
青天河景区位于焦作市博爱县境内, 景区内景观由于自然条件和人类修建工程活动的双重因素影响易形成致灾体.2021年夏季出现了"7·20""9·30"极端天气, 导致景区内地质灾害频发.区内灾害点整体规模虽不大, 但其隐蔽性与突发性的特点会给景区人员及设施带来较大影响与破坏, 故对景区地质灾害易发性评价的研究具有重要意义.依托暴雨前后两期遥感影像比对和野外调查验证, 及时获取暴雨后地灾点数据, 通过基于多种核函数的支持向量机(SVM)机器学习模型搭建随机森林(RF)模型, 建立地质灾害易发性评价模型.在综合考虑研究区域背景条件下, 从自然条件和人类活动条件下选取7类特征因子并经过处理作为模型训练输入值, 分别以linear、poly、rbf、sigmoid四种SVM核函数进行模型训练, 共生成了40个SVM模型.通过选取4种不同的模型参数种子, 得到4个RF模型.最后把两种预测的模型结果进行加权融合得到最终模型预测概率, 在GIS中输出预测结果并进行分区, 这样既保证模型稳定性, 又避免过拟合的情况.分区结果与本研究地灾点分布规律较为一致, 能较好地刻画模拟研究区地灾易发性规律, 填补青天河景区地灾易发性细化研究, 为青天河景区科学防灾提供有价值的依据.
Abstract:Located in Boai County of Jiaozuo City, the Qingtian River Scenic Area is prone to disaster due to the dual factors of natural conditions and human construction activities. In the summer of 2021, extreme weather occurred on July 20 and September 30, resulting in frequent geological disasters in the scenic area. Although the sizes of disaster sites are not big enough, hidden and sudden disasters can cause great damage to the personnel and facilities in the area, therefore the study on the assessment of geological disaster vulnerability is of great significance. Based on the comparison between two-period remote sensing image data and field survey verification before and after the storm, and timely acquisition of the disaster site data after the storm, the geological disaster susceptibility evaluation model is established through the construction of random forest (RF) model by the support vector machine (SVM) learning model based on multiple kernel functions. Based on the comprehensive consideration of regional background of the area, seven eigenfactors are selected from natural and human activity conditions and processed as input values for model training, and four SVM kernel functions including linear, poly, rbf and sigmoid are used respectively for model training to generate 40 SVM models. Four RF models are obtained by selecting four different model parameter seeds. Finally, the weighted fusion of two predicted model results is made to get the prediction probability of final model, and the prediction results are output and partitioned in GIS, so as to ensure the stability of the model and avoid overfitting. The zoning results are consistent with the distribution rule of disaster sites in the area, which can simulate the regularity of disaster susceptibility well, fill in the detailed study of disaster susceptibility, and provide valuable basis for scientific prevention of disaster in Qingtian River Scenic Area.
-
-
表 1 模型指标评价
Table 1. Index evaluation of models
模型类型 准确率
(Accuracy)F1分数
(F1-Score)召回率
(Recall)SVM 0.830 0.850 0.820 RF 0.883 0.902 0.865 融合模型(SVM-RF) 0.895 0.905 0.873 
下载: 导出CSV
表 2 研究区地质灾害与易发性分区关联统计表
Table 2. Correlation between geological disasters and susceptibility zoning in the study area
易发性分区 易发分级面积占比/% 地灾点占比/% 地灾点密度/(处/km2) 稳定区 35.91 0 0 低易发区 32.47 0 0 中易发区 19.75 11.54 0.59 高易发区 11.87 88.46 7.47
下载: 导出CSV
-
[1] 赵晓东, 王顺东, 张泰丽, 等. 不同精度下地表稳定性模型的评价[J]. 科学技术与工程, 2020, 20(25): 10207-10213. https://www.cnki.com.cn/Article/CJFDTOTAL-KXJS202025012.htm
Zhao X D, Wang S D, Zhang T L, et al. Model evaluation of geohazard susceptibility in different resolutions[J]. Science Technology and Engineering, 2020, 20(25): 10207-10213. https://www.cnki.com.cn/Article/CJFDTOTAL-KXJS202025012.htm
[2] 谭春. 基于3S技术的岩桑树水电站近坝区滑坡敏感性评价[D]. 长春: 吉林大学, 2013.
Tan C. Susceptibility appraisal of landslide adjacent to the dam site of Yansangshu hydro-power station based on 3S technology[D]. Changchun: Jilin University, 2013.
[3] 胡燕, 李德营, 孟颂颂, 等. 基于证据权法的巴东县城滑坡灾害易发性评价[J]. 地质科技通报, 2020, 39(3): 187-194. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ202003023.htm
Hu Y, Li D Y, Meng S S, et al. Landslide susceptibility evaluation in Badong County based on weights of evidence method[J]. Bulletin of Geological Science and Technology, 2020, 39(3): 187-194. https://www.cnki.com.cn/Article/CJFDTOTAL-DZKQ202003023.htm
[4] 尚敏, 马锐, 张英莹, 等. 基于GIS的证据权重法的崩塌敏感性分析研究[J]. 工程地质学报, 2018, 26(5): 1211-1218. https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ201805012.htm
Shang M, Ma R, Zhang Y Y, et al. GIS based weights of evidence method for rock fall susceptibility[J]. Journal of Engineering Geology, 2018, 26(5): 1211-1218. https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ201805012.htm
[5] 丁茜, 赵晓东, 吴鑫俊, 等. 基于RBF核的多分类SVM滑塌易发性评价模型[J]. 中国安全科学学报, 2022, 32(3): 194-200. https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK202203026.htm
Ding X, Zhao X D, Wu X J, et al. Landslide susceptibility assessment model based on multi-class SVM with RBF kernel[J]. China Safety Science Journal, 2022, 32(3): 194-200. https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK202203026.htm
[6] 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): 2244-2260. https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX202112012.htm
Wang Y, Fang Z C, Niu R Q, et al. Landslide susceptibility analysis based on deep learning[J]. Journal of Geo-information Science, 2021, 23(12): 2244-2260. https://www.cnki.com.cn/Article/CJFDTOTAL-DQXX202112012.htm
[7] Ebrahimy H, Feizizadeh B, Salmani S, et al. A comparative study of land subsidence susceptibility mapping of Tasuj Plane, Iran, using boosted regression tree, random forest and classification and regression tree methods[J]. Environmental Earth Sciences, 2020, 79(10): 223. doi: 10.1007/s12665-020-08953-0
[8] 周天伦, 曾超, 范晨, 等. 基于快速聚类-信息量模型的汶川及周边两县滑坡易发性评价[J]. 中国地质灾害与防治学报, 2021, 32(5): 137-150. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDH202105017.htm
Zhou T L, Zeng C, Fan C, et al. Landslide susceptibility assessment based on K-means cluster information model in Wenchuan and two neighboring counties, China[J]. The Chinese Journal of Geological Hazard and Control, 2021, 32(5): 137-150. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDH202105017.htm
[9] 樊芷吟, 苟晓峰, 秦明月, 等. 基于信息量模型与Logistic回归模型耦合的地质灾害易发性评价[J]. 工程地质学报, 2018, 26(2): 340-347. https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ201802008.htm
Fan Z Y, Gou X F, Qin M Y, et al. Information and logistic regression models based coupling analysis for susceptibility of geological hazards[J]. Journal of Engineering Geology, 2018, 26(2): 340-347. https://www.cnki.com.cn/Article/CJFDTOTAL-GCDZ201802008.htm
[10] 鲍帅, 刘纪平, 王亮. 联合DBSCAN聚类采样和SVM分类的滑坡易发性评价[J]. 震灾防御技术, 2021, 16(4): 625-636. https://www.cnki.com.cn/Article/CJFDTOTAL-ZZFY202104003.htm
Bao S, Liu J P, Wang L. Landslide susceptibility evaluation based on combined DBSCAN cluster sampling and SVM classification[J]. Technology for Earthquake Disaster Prevention, 2021, 16(4): 625-636. https://www.cnki.com.cn/Article/CJFDTOTAL-ZZFY202104003.htm
[11] 李坤, 赵俊三, 林伊琳, 等. 基于RF和SVM模型的东川泥石流易发性评价研究[J]. 云南大学学报(自然科学版), 2022, 44(1): 107-115. https://www.cnki.com.cn/Article/CJFDTOTAL-YNDZ202201025.htm
Li K, Zhao J S, Lin Y L, et al. Assessment of debris flow susceptibility in Dongchuan based on RF and SVM models[J]. Journal of Yunnan University (Natural Sciences Edition), 2022, 44(1): 107-115. https://www.cnki.com.cn/Article/CJFDTOTAL-YNDZ202201025.htm
[12] Peng L, Niu R Q, Huang B, et al. Landslide susceptibility mapping based on rough set theory and support vector machines: A case of the Three Gorges area, China[J]. Geomorphology, 2014, 204: 287-301.
[13] 夏辉, 殷坤龙, 梁鑫, 等. 基于SVM-ANN模型的滑坡易发性评价——以三峡库区巫山县为例[J]. 中国地质灾害与防治学报, 2018, 29(5): 13-19. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDH201805003.htm
Xia H, Yin K L, Liang X, et al. Landslide susceptibility assessment based on SVM-ANN models: A case study for Wushan County in the Three Gorges Reservoir[J]. The Chinese Journal of Geological Hazard and Control, 2018, 29(5): 13-19. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDH201805003.htm
[14] 牛瑞卿, 彭令, 叶润青, 等. 基于粗糙集的支持向量机滑坡易发性评价[J]. 吉林大学学报(地球科学版), 2012, 42(2): 430-439. https://www.cnki.com.cn/Article/CJFDTOTAL-CCDZ201202019.htm
Niu R Q, Peng L, Ye R Q, et al. Landslide susceptibility assessment based on rough sets and support vector machine[J]. Journal of Jilin University (Earth Science Edition), 2012, 42(2): 430-439. https://www.cnki.com.cn/Article/CJFDTOTAL-CCDZ201202019.htm
[15] 黄发明, 殷坤龙, 蒋水华, 等. 基于聚类分析和支持向量机的滑坡易发性评价[J]. 岩石力学与工程学报, 2018, 37(1): 156-167. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201801016.htm
Huang F M, Yin K L, Jiang S H, et al. Landslide susceptibility assessment based on clustering analysis and support vector machine[J]. Chinese Journal of Rock Mechanics and Engineering, 2018, 37(1): 156-167. https://www.cnki.com.cn/Article/CJFDTOTAL-YSLX201801016.htm
[16] 刘艺梁, 殷坤龙, 刘斌. 逻辑回归和人工神经网络模型在滑坡灾害空间预测中的应用[J]. 水文地质工程地质, 2010, 37(5): 92-96. https://www.cnki.com.cn/Article/CJFDTOTAL-SWDG201005020.htm
Liu Y L, Yin K L, Liu B. Application of logistic regression and artificial neural network in spatial assessment of landslide hazards[J]. Hydrogeology&Engineering Geology, 2010, 37(5): 92-96. https://www.cnki.com.cn/Article/CJFDTOTAL-SWDG201005020.htm
[17] 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.
[18] 薛永安, 王玉洁, 朱婧聪, 等. 基于CF与SVM的小样本斜坡地质灾害敏感性评价研究[J]. 太原理工大学学报, 2022, 53(4): 672-681. https://www.cnki.com.cn/Article/CJFDTOTAL-TYGY202204011.htm
Xue Y A, Wang Y L, Zhu J C, et al. Study of slope geological hazard susceptibility valuation with small sample based on CF and SVM[J]. Journal of Taiyuan University of Technology, 2022, 53(4): 672-681. https://www.cnki.com.cn/Article/CJFDTOTAL-TYGY202204011.htm
[19] Chapelle O, Haffner P, Vapnik V N. Support vector machines for histogram-based image classification[J]. IEEE Transactions on Neural Networks, 1999, 10(5): 1055-1064.
[20] Burges C J C. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(9): 121-167.
[21] 汪海燕, 黎建辉, 杨风雷. 支持向量机理论及算法研究综述[J]. 计算机应用研究, 2014, 31(5): 1281-1286. https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201405002.htm
Wang H Y, Li J H, Yang F L. Overview of support vector machine analysis and algorithm[J]. Application Research of Computers, 2014, 31(5): 1281-1286. https://www.cnki.com.cn/Article/CJFDTOTAL-JSYJ201405002.htm
[22] 赵传峰, 姜汉桥, 郭新华. 支持向量机在小样本预测中的应用[J]. 油气田地面工程, 2009, 28(2): 21-23. https://www.cnki.com.cn/Article/CJFDTOTAL-YQTD200902013.htm
Zhao C F, Jiang H Q, Guo X H. Application of support vector machine in prediction for small-sample cases[J]. Oil-Gas Field Surface Engineering, 2009, 28(2): 21-23. https://www.cnki.com.cn/Article/CJFDTOTAL-YQTD200902013.htm
[23] 杨硕, 李德营, 严亮轩, 等. 基于随机森林模型的乌江高陡岸坡滑坡地质灾害易发性评价[J]. 安全与环境工程, 2021, 28(4): 131-138. https://www.cnki.com.cn/Article/CJFDTOTAL-KTAQ202104019.htm
Yang S, Li D Y, Yan L X, et al. Landslide susceptibility assessment in high and steep bank slopes along Wujiang River based on random forest model[J]. Safety and Environmental Engineering, 2021, 28(4): 131-138. https://www.cnki.com.cn/Article/CJFDTOTAL-KTAQ202104019.htm
[24] 穆柯, 谢婉丽, 刘琦琦, 等. 基于LR-RF模型的滑坡易发性评价——以铜川市耀州区为例[J]. 灾害学, 2022, 37(3): 212-218. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHXU202203034.htm
Mu K, Xie W L, Liu Q Q, et al. Research on landslide susceptibility evaluation based on logistic regression and LR coupling model[J]. Journal of Catastrophology, 2022, 37(3): 212-218. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHXU202203034.htm
[25] 林荣福. 基于优化支持向量机模型的滑坡易发性评价——以陕西省商洛市为例[D]. 阜新: 辽宁工程技术大学, 2021.
Lin R F. Landslide susceptibility evaluation based on optimized support vector machine model: Taking Shangluo City of Shaanxi Province as an example[D]. Fuxin: Liaoning Technical University, 2021.
[26] 罗金. 基于各类机器学习方法的滑坡易发性评价及软件系统开发[D]. 西安: 长安大学, 2021.
Luo J. Evaluation of landslide susceptibility and software system development based on various machine learning methods[D]. Xi'an: Chang'an University, 2021.
[27] 石辉, 邓念东, 周阳. 随机森林赋权层次分析法的崩塌易发性评价[J]. 科学技术与工程, 2021, 21(25): 10613-10619. https://www.cnki.com.cn/Article/CJFDTOTAL-KXJS202125008.htm
Shi H, Deng N D, Zhou Y. Evaluation of collapse susceptibility based on random forest weighted analytic hierarchy process[J]. Science Technology and Engineering, 2021, 21(25): 10613-10619. https://www.cnki.com.cn/Article/CJFDTOTAL-KXJS202125008.htm
[28] 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. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201308019.htm
Wu X L, Ren F, Niu R Q. 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. https://www.cnki.com.cn/Article/CJFDTOTAL-WHCH201308019.htm
[29] 何书, 鲜木斯艳·阿布迪克依木, 胡萌, 等. 基于自组织特征映射网络-随机森林模型的滑坡易发性评价——以江西大余县为例[J]. 中国地质灾害与防治学报, 2022, 33(1): 132-140. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDH202201016.htm
He S, Xianmusiyan A, Hu M, et al. Evaluation on landslide susceptibility based on self-organizing feature map network and random forest model: A case study of Dayu County of Jiangxi Province[J]. The Chinese Journal of Geological Hazard and Control, 2022, 33(1): 132-140. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGDH202201016.htm
-
图(7)
表(2)
计量
- 文章访问数: 1047
- PDF下载数: 237
- 施引文献: 0