滑坡易发性分区是预测滑坡的有效方法。利用径向基神经网络模型(RBFNN模型)耦合确定性指数(CF指数)构建混合模型(RBFNN-CF模型),开展陕西省汉中市城固县滑坡易发性分区研究。首先选取坡度、坡向、平面曲率、剖面曲率、高程、年平均降雨量、道路缓冲区、水系缓冲区、断层缓冲区、NDVI和地层岩组作为滑坡诱发因子,计算对应的CF指数并量化诱发因子;其次将野外调查的184个滑坡数据按照7∶3的比例划分为训练数据和测试数据,分别利用RBFNN-CF和RBFNN模型绘制滑坡易发性分区图;最后利用受试者工作特征曲线(ROC曲线)下的面积评估和对比分区的结果及模型的分类能力。结果表明:RBFNN-CF模型的分类能力和泛化性均强于RBFNN模型,值得在研究区推广,得到的滑坡易发性分区图可为当地的滑坡防治工作提供参考。
Abstract
Landslide susceptibility mapping is an effective means of landslide prediction. We built a hybrid model integrating RBFNN (Radial Basis Function Neural Network) with Certainty Factor (CF) for the mapping of landslide susceptibility in Chenggu County, Hanzhong City of Shaanxi Province. First of all, we selected slope, aspect, plane curvature, profile curvature, elevation, mean annual precipitation, distance to road, distance to river, distance to fault, NDVI and lithology as landslide's triggering factors and then quantified such factors by calculating the corresponding CF. Secondly, we divided the field survey data of 184 landslides into training data and test data with a ratio of 7∶3, and generate the landslide susceptibility maps using RBFNN-CF and RBFNN models, respectively. Finally, we evaluated and compared the mapping results and the classification ability of the models according to the area under the ROC curves. The results suggest that the classification and generalization ability of RBFNN-CF model are both superior to those of RBFNN model. The hybrid model is worth popularizing in the study area, and the landslide susceptibility maps obtained in this study could also provide references for local landslide prevention and control.
关键词
滑坡 /
易发性 /
RBFNN /
CF指数 /
混合模型 /
GIS /
ROC曲线
Key words
landslide susceptibility /
RBFNN /
certainty factor /
hybrid model /
GIS /
ROC curve
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 贺 鹏, 童立强, 郭兆成, 等. GIS支持下基于层次分析法的西藏札达地区滑坡灾害易发性评价研究[J]. 科学技术与工程, 2016, 16(25): 193-200.
[2] 张 文, 白世彪, 王 建. 基于专家经验值的滑坡易发性评价:以四川平武高坪铺库区为例[J]. 地质灾害与环境保护, 2010, 21(4): 20-23.
[3] ABEDINI M, TULABI S. Assessing LNRF, FR, and AHP Modelsin Landslide Susceptibility Mapping Index: A Comparative Study of Nojian Watershed in Lorestan Province, Iran[J]. Environmental Earth Sciences, 2018, 77(11): 405-423.
[4] ADITIAN A, KUBOTA T, SHINOHARA Y. Comparison of GIS-based Landslide Susceptibility Models Using Frequency Ratio, Logistic Regression,and Artificial Neural Network in a Tertiary Region of Ambon, Indonesia[J]. Geomorphology, 2018, 318(3): 101-111.
[5] 韩 玲, 张庭瑜, 张 恒. 基于IOE和SVM模型的府谷镇滑坡易发性分区[J]. 水土保持研究, 2019, 26(3): 373-378.
[6] 许 冲, 戴福初, 姚 鑫,等. 基于GIS与确定性系数分析方法的汶川地震滑坡易发性评价[J]. 工程地质学报, 2010, 21(1): 123-141.
[7] 张若琳, 孟 晖, 连建发, 等. 基于GIS的概率比率模型的滑坡易发性评价[J]. 地学前缘, 2010, 18(6): 291-297.
[8] TRIGILA A, IADANZA C, ESPOSITO C,et al. Comparison of Logistic Regression and Random Forests techniques for Shallow Landslide Susceptibility Assessment in Giampilieri (NE Sicily, Italy)[J]. Geomorphology, 2015, 249(3): 119-136.
[9] 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.
[10]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(7): 1085-1091.
[11]张庭瑜, 韩 玲, 张 恒, 等. 混合分类模型在滑坡易发性分区中的适用性研究:以延安市宝塔区为例[J]. 干旱区资源与环境, 2020, 34(1): 206-214.
[12]CHEN W, YAN X, ZHAO Z,et al. Spatial Prediction of Landslide Susceptibility Using Data Mining-based Kernel Logistic Regression, Naive Bayes and Rbfnetwork Models for the Long County Area (China)[J]. Bulletin of Engineering Geology & Environment, 2019, 78(1): 247-266.
[13]HE Q, SHAHABI H, SHIRZADI A,et al. Landslide Spatial Modelling Using Novel Bivariate Statistical Based Nave Bayes, RBF Classifier, and RBF Network Machine Learning Algorithms[J]. Science of The Total Environment, 2019, 663(1): 1-15.
[14]DEVKOTA K C, REGMI A D, POURGHASEMI H R,et al. Landslide Susceptibility Mapping Using Certainty Factor, Index of Entropy and Logistic Regression Models in GIS and Their Comparison at Mugling-Narayanghat Road Section in Nepal Himalaya[J]. Natural Hazards, 2013, 65(1): 135-165.
[15]WU Y, LI W, WANG Q,et al. Landslide Susceptibility Assessment Using Frequency Ratio, Statistical Index and Certainty Factor Models for the Gangu County, China[J]. Arabian Journal of Geosciences, 2016, 9(2): 84-99.
[16]VAKHSHOORI V, ZARE M. Landslide Susceptibility Mappingby Comparing Weight of Evidence, Fuzzy Logic, and Frequency Ratio Methods[J]. Geomatics, Natural Hazards and Risk, 2017, 7(5): 1731-1752.
[17]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.
[18]YALCIN A, REIS S, AYDINOGLU A C,et al. A GIS-based Comparative Study of Frequency Ratio, Analytical Hierarchy Process, Bivariate Statistics and Logistics Regression Methods for Landslide Susceptibility Mapping in Trabzon, NE Turkey[J]. Catena, 2011, 85(3): 274-287.
[19]CHONG X, XU X, DAI F, et al. Landslide Hazard Mapping Using GIS and Weight of Evidence Model in Qingshui River Watershed of 2008 Wenchuan Earthquake Struck Region[J]. Journal of Earth Science, 2012, 23(1): 97-120.
[20]张晓东, 刘湘南, 赵志鹏, 等. 信息量模型、确定性系数模型与逻辑回归模型组合评价地质灾害敏感性的对比研究[J]. 现代地质, 2018, 32(3): 39-45.
[21]田春山, 刘希林, 汪 佳. 基于CF和Logistic回归模型的广东省地质灾害易发性评价[J]. 水文地质与工程地质, 2016, 8(6): 104-110.
[22]杨 光, 徐佩华, 曹 琛, 等. 基于确定性系数组合模型的区域滑坡敏感性评价[J]. 工程地质学报, 2019, 27(5): 1152-1162.
基金
陕西省自然科学基础研究计划项目(2019JQ-945);中央高校基本科研业务费专项(300102351502);陕西省企业创新争先青年人才托举计划项目(2021-1-2)
PDF(2352 KB)
