Analyzing the influence of non-landslide sample selection on landslide susceptibility: Case studies from Wenchuan, Lixian and Maoxian Counties
-
摘要:
研究探索了机器学习在评估滑坡易发性中的应用，重点关注非滑坡样本的选择问题。以四川省汶川县、理县和茂县为研究区，选取坡度、坡向、高程、距水系距离、距断层距离、岩性和土地利用7个评价因子，从信息量模型（I）、证据权重模型（WOE）、确定性系数模型（CF）、频率比模型（FR）划分的较低和极低易发区以及缓冲区外（B）和全区（G）随机选取非滑坡样本，构建基于不同非滑坡样本选取方法的支持向量机模型（SVM）并展开易发性评价。结果显示：I-SVM、WOE-SVM、CF-SVM、FR-SVM的ROC曲线下AUC值分别为
0.9804 、0.9726 、0.9368 、0.8451 ，优于B-SVM的0.7869 和G-SVM的0.7389 ，说明采用数学统计模型所选取的非滑坡样本准确性更高，信息量模型是选取非滑坡样本的最优方法，为非滑坡样本的选取提供新思路。Abstract:This research explores the integration of machine learning in assessing landslide susceptibility, scrutinizing the selection of non-landslide samples. Taking Wenchuan County, Lixian County, and Maoxian County in Sichuan Province as the study areas, 7 evaluation factors were considered, including slope, aspect, elevation, distance to the water system, distance to the fault, lithology, and land use. Non-landslide samples were randomly selected from the lower and extremely low susceptibility zones divided by the information value model (I), weight of evidence model(WOE), coefficient of determination model (CF), and frequency ratio model(FR), as well as form the buffer zones (B) and the entire region (G). These samples were then analyzed using a support vector machine (SVM) model. The results showed that the AUC values for I-SVM, WOE-SVM, CF-SVM, and FR-SVM were
0.9804 ,0.9726 ,0.9368 , and0.8451 , respectively, which were superior to the AUC values of B-SVM (0.7869 ) and G-SVM (0.7389 ). This highlight the effectiveness of using mathematical-statistical models for the selection of non-landslide samples, with particular emphasis on the accuracy of the information value model. This study offers a novel approach to selecting non-landslide samples, significantly enhancing predictive accuracy in landslide susceptibility assessments. -
-
表 1 基于不同非滑坡样本选取方法的SVM模型
Table 1. SVM model based on different non-landslide sample selection methods
模型名称 非滑坡样本选取方法：基于数学统计模型（4种） 非滑坡样本选取方法：常规（2种） I-SVM WOE-SVM CF-SVM FR-SVM B-SVM G-SVM 模型编号 1 2 3 4 5 6 命名规则 前面字母代表着选取非滑坡样本的方法，后面字母代表着所使用的SVM模型 非滑坡样本
选取区域信息量模型划分的
较低、极低易发区证据权模型划分的
较低、极低易发区确定性系数模型划分的
较低、极低易发区频率比模型划分的
较低、极低易发区将距滑坡点1 km以内地区设为
缓冲区，从缓冲区外随机选取整个
研究区
下载: 导出CSV
表 2 不同模型的最优参数
Table 2. Optimal parameters for different models
参数 I-SVM WOE-SVM CF-SVM FR-SVM B-SVM G-SVM Gamma 0.01 0.01 0.02 0.1 0.01 0.02 C 160 180 8 2 40 1
下载: 导出CSV
表 3 易发性分级面积及滑坡面积占比
Table 3. Classification area of susceptibility and proportion of landslide area
易发性分级 极低 较低 中等 较高 极高 易发性
分级面积/km2I-SVM 2696.75 2244.36 2006.25 2189.49 3120.79 WOE-SVM 3058.40 2250.93 1869.58 1984.89 3093.82 CF-SVM 3190.05 1975.34 1817.33 2060.21 3214.70 FR-SVM 2780.17 2293.44 2265.99 2454.95 2463.09 B-SVM 2647.25 3111.23 3095.24 2299.57 1104.34 G-SVM 1381.98 3186.95 3089.52 2652.01 1947.17 滑坡面积
占比/%I-SVM 0.11 0.59 4.06 13.15 82.10 WOE-SVM 1.03 1.19 4.98 20.78 72.01 CF-SVM 0.10 5.41 4.75 19.55 70.19 FR-SVM 0.21 2.56 15.66 10.94 70.64 B-SVM 1.58 5.85 18.14 42.98 31.45 G-SVM 3.31 11.46 25.82 13.97 45.44
下载: 导出CSV
-
[1] XIA Ding,TANG Huiming,SUN Sixuan,et al. Landslide susceptibility mapping based on the germinal center optimization algorithm and support vector classification[J]. Remote Sensing,2022,14(11):2707. doi: 10.3390/rs14112707
[2] 郭飞,王秀娟,陈玺,等. 基于不同模型的赣南地区小型削方滑坡易发性评价对比分析[J]. 中国地质灾害与防治学报,2022,33(6):125 − 133. [GUO Fei,WANG Xiujuan,CHEN Xi,et al. Comparative analyses on susceptibility of cutting slope landslides in southern Jiangxi using different models[J]. The Chinese Journal of Geological Hazard and Control,2022,33(6):125 − 133. (in Chinese with English abstract)]
GUO Fei, WANG Xiujuan, CHEN Xi, et al. Comparative analyses on susceptibility of cutting slope landslides in southern Jiangxi using different models［J］. The Chinese Journal of Geological Hazard and Control, 2022, 33（6）: 125 − 133. （in Chinese with English abstract）
[3] DENG Hui,WU Xiantan,ZHANG Wenjiang,et al. Slope-unit scale landslide susceptibility mapping based on the random forest model in deep valley areas[J]. Remote Sensing,2022,14(17):4245. doi: 10.3390/rs14174245
[4] QUAN Hechun,JIN Guangri,DESTECH PUBLICAT I. Landslide susceptibility mapping in Changbai Mountain Area using GIS and artificial neural network(ANN); proceedings of the international conference on GIS and resource management (ICGRM),Guangzhou,PEOPLES R CHINA,F Jan 03-05,2014[C]. 2014.
[5] KAVZOGLU T,SAHIN E K,COLKESEN I. Landslide susceptibility mapping using GIS-based multi-criteria decision analysis,support vector machines,and logistic regression[J]. Landslides,2014,11(3):425 − 439. doi: 10.1007/s10346-013-0391-7
[6] DOU Jie,YUNUS A P,BUI D T,et al. Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island,Japan[J]. The Science of the Total Environment,2019,662:332 − 346. doi: 10.1016/j.scitotenv.2019.01.221
[7] 陈飞,蔡超,李小双,等. 基于信息量与神经网络模型的滑坡易发性评价[J]. 岩石力学与工程学报,2020,39(增刊1):2859 − 2870. [CHEN Fei,CAI Chao,LI Xiaoshuang,et al. Evaluation of landslide susceptibility based on information quantity and neural network model[J]. Chinese Journal of Rock Mechanics and Engineering,2020,39(Sup 1):2859 − 2870. (in Chinese)]
CHEN Fei, CAI Chao, LI Xiaoshuang, et al. Evaluation of landslide susceptibility based on information quantity and neural network model［J］. Chinese Journal of Rock Mechanics and Engineering, 2020, 39（Sup 1）: 2859 − 2870. （in Chinese）
[8] 周晓亭,黄发明,吴伟成,等. 基于耦合信息量法选择负样本的区域滑坡易发性预测[J]. 工程科学与技术,2022,54(3):25 − 35. [ZHOU Xiaoting,HUANG Faming,WU Weicheng,et al. Regional landslide susceptibility prediction based on negative sample selected by coupling information value method[J]. Advanced Engineering Sciences,2022,54(3):25 − 35. (in Chinese with English abstract)]
ZHOU Xiaoting, HUANG Faming, WU Weicheng, et al. Regional landslide susceptibility prediction based on negative sample selected by coupling information value method［J］. Advanced Engineering Sciences, 2022, 54（3）: 25 − 35. （in Chinese with English abstract）
[9] 陈芯宇,师芸,温永啸,等. 基于确定性系数与支持向量机的滑坡易发性评价[J]. 科学技术与工程,2023,23(2):518 − 527. [CHEN Xinyu,SHI Yun,WEN Yongxiao,et al. Landslide susceptibility evaluation based on certainty factor and support vector machines[J]. Science Technology and Engineering,2023,23(2):518 − 527. (in Chinese with English abstract)] doi: 10.3969/j.issn.1671-1815.2023.02.012
CHEN Xinyu, SHI Yun, WEN Yongxiao, et al. Landslide susceptibility evaluation based on certainty factor and support vector machines［J］. Science Technology and Engineering, 2023, 23（2）: 518 − 527. （in Chinese with English abstract） doi: 10.3969/j.issn.1671-1815.2023.02.012
[10] LIU Jiping,LIN Rongfu,XU Shenghua,et al. Landslide susceptibility evaluation based on optimized support vector machine[J]. Proceedings of the ICA,2021,4:1 − 4.
[11] 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. [ZHOU Tianlun,ZENG Chao,FAN Chen,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. (in Chinese with English abstract)]
ZHOU Tianlun, ZENG Chao, FAN Chen, 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. （in Chinese with English abstract）
[12] 熊小辉,汪长林,白永健,等. 基于不同耦合模型的县域滑坡易发性评价对比分析——以四川普格县为例[J]. 中国地质灾害与防治学报,2022,33(4):114 − 124. [XIONG Xiaohui,WANG Changlin,BAI Yongjian,et al. Comparison of landslide susceptibility assessment based on multiple hybrid models at county level:A case study for Puge County,Sichuan Province[J]. The Chinese Journal of Geological Hazard and Control,2022,33(4):114 − 124. (in Chinese with English abstract)]
XIONG Xiaohui, WANG Changlin, BAI Yongjian, et al. Comparison of landslide susceptibility assessment based on multiple hybrid models at county level: A case study for Puge County, Sichuan Province［J］. The Chinese Journal of Geological Hazard and Control, 2022, 33（4）: 114 − 124. （in Chinese with English abstract）
[13] NEUHÄUSER B,DAMM B,TERHORST B. GIS-based assessment of landslide susceptibility on the base of the Weights-of-Evidence model[J]. Landslides,2012,9(4):511 − 528. doi: 10.1007/s10346-011-0305-5
[14] 陈建国,钟连祥. 基于CF-AHP耦合模型的高速公路沿线崩塌地质灾害易发性评价——以蓉遵高速公路土城——旺隆段为例[J]. 中国地质灾害与防治学报,2023,34(6):105 − 115. [CHEN Jianguo,ZHONG Lianxiang. Assessment of rockfall susceptibility along the expressway based on the CF-AHP coupling model:A case study of the Tucheng-Wanglong section of the Rongzun expressway[J]. The Chinese Journal of Geological Hazard and Control,2023,34(6):105 − 115. (in Chinese with English abstract)]
CHEN Jianguo, ZHONG Lianxiang. Assessment of rockfall susceptibility along the expressway based on the CF-AHP coupling model: A case study of the Tucheng-Wanglong section of the Rongzun expressway［J］. The Chinese Journal of Geological Hazard and Control, 2023, 34（6）: 105 − 115. （in Chinese with English abstract）
[15] BERHANE G,KEBEDE M,ALFARAH N,et al. Landslide susceptibility zonation mapping using GIS-based frequency ratio model with multi-class spatial data-sets in the Adwa-Adigrat Mountain chains,northern Ethiopia[J]. Journal of African Earth Sciences,2020,164:103795. doi: 10.1016/j.jafrearsci.2020.103795
[16] 周萍,邓辉,张文江,等. 基于信息量模型和机器学习方法的滑坡易发性评价研究——以四川理县为例[J]. 地理科学,2022,42(9):1665 − 1675. [ZHOU Ping,DENG Hui,ZHANG Wenjiang,et al. Landslide susceptibility evaluation based on information value model and machine learning method:A case study of Lixian County,Sichuan Province[J]. Scientia Geographica Sinica,2022,42(9):1665 − 1675. (in Chinese with English abstract)]
ZHOU Ping, DENG Hui, ZHANG Wenjiang, et al. Landslide susceptibility evaluation based on information value model and machine learning method: A case study of Lixian County, Sichuan Province［J］. Scientia Geographica Sinica, 2022, 42（9）: 1665 − 1675. （in Chinese with English abstract）
[17] 付智勇,李典庆,王顺,等. 基于多时空滑坡编录和TrAdaBoost迁移学习的滑坡易发性评价[J]. 地球科学,2023,48(5):1935 − 1947. [FU Zhiyong,LI Dianqing,WANG Shun,et al. Landslide susceptibility assessment based on multitemporal landslide inventories and TrAdaBoost transfer learning[J]. Earth Science,2023,48(5):1935 − 1947. (in Chinese with English abstract)]
FU Zhiyong, LI Dianqing, WANG Shun, et al. Landslide susceptibility assessment based on multitemporal landslide inventories and TrAdaBoost transfer learning［J］. Earth Science, 2023, 48（5）: 1935 − 1947. （in Chinese with English abstract）
[18] WANG Xiao,LI Shaoda,LIU Hanhu,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):5369 − 5390. doi: 10.1007/s10064-021-02280-9
[19] 贾雨霏,魏文豪,陈稳,等. 基于SOM-I-SVM耦合模型的滑坡易发性评价[J]. 水文地质工程地质,2023,50(3):125 − 137. [JIA Yufei,WEI Wenhao,CHEN Wen,et al. Landslide susceptibility assessment based on the SOM-I-SVM model[J]. Hydrogeology & Engineering Geology,2023,50(3):125 − 137. (in Chinese with English abstract)]
JIA Yufei, WEI Wenhao, CHEN Wen, et al. Landslide susceptibility assessment based on the SOM-I-SVM model［J］. Hydrogeology & Engineering Geology, 2023, 50（3）: 125 − 137. （in Chinese with English abstract）
[20] 姚皖路,赵俊三,李坤. 基于信息增益比-支持向量机的泥石流易发性评价[J]. 城市勘测,2023(5):181 − 186. [YAO Wanlu,ZHAO Junsan,LI Kun. Assessment of debris flow susceptibility based on information gain ratio-support vector machine[J]. Urban Geotechnical Investigation & Surveying,2023(5):181 − 186. (in Chinese with English abstract)] doi: 10.3969/j.issn.1672-8262.2023.05.040
YAO Wanlu, ZHAO Junsan, LI Kun. Assessment of debris flow susceptibility based on information gain ratio-support vector machine［J］. Urban Geotechnical Investigation & Surveying, 2023（5）: 181 − 186. （in Chinese with English abstract） doi: 10.3969/j.issn.1672-8262.2023.05.040
[21] HUANG Wubiao,DING Mingtao,LI Zhenhong,et al. An efficient user-friendly integration tool for landslide susceptibility mapping based on support vector machines:SVM-LSM toolbox[J]. Remote Sensing,2022,14(14):3408. doi: 10.3390/rs14143408
-
图(9)
表(3)
计量
- 文章访问数: 11
- PDF下载数: 1
- 施引文献: 0