|
|
- 2016
GIS支持下应用PSO-SVM模型预测滑坡易发性
|
Abstract:
滑坡灾害易发性预测是滑坡监测、预警与评估的关键技术。如何有效地选取评价因子和构建预测模型是滑坡灾害定量预测研究中的难题。本文以三峡库区长江干流岸坡作为研究区,通过地形、地质和遥感等多源数据融合,提取滑坡孕灾环境和诱发因素的信息作为评价因子。在此基础上,针对滑坡灾害的非线性和不确定性特征,采用粒子群算法对支持向量机模型参数进行全局寻优,构建粒子群算法(particle swarm optimization, PSO)-支持向量机(support vector machine, SVM)模型,定量预测滑坡易发性。最后通过分类精度比较分析基于格网单元和对象单元的滑坡易发性预测精度,结果表明,基于对象单元的PSO-SVM预测精度较高,其曲线下面积为0.841 5,Kappa系数为0.849 0,预测结果与野外实际调查情况较为一致,可为三峡库区滑坡防灾减灾工作提供参考
| [1] | Huang S, Luo L. Stability Analysis and Results of the Landslide Monitoring Datum in the Three Gorges Reservoir Area[J]. <em>Geomatics and Information Science of Wuhan University</em>, 2014,39(3):367-372(黄声享, 罗力. 三峡库区滑坡监测基准的稳定性分析及结果[J]. 武汉大学学报·信息科学版, 2014,39(3):367-372) |
| [2] | He S W, Pan P, Dai L, et al. Application of Kernel-based Fisher Discriminant Analysis to Map Landslide Susceptibility in the Qinggan River Delta, Three Gorges, China[J]. <em>Geomorphology</em>, 2012, 171/172:30-41 |
| [3] | Niethammer U, James M R, Rothmund S, et al. UAV-based Remote Sensing of the Super-Sauze Landslide:Evaluation and results[J]. <em>Eng Geol</em>, 2012, 128:2-11 |
| [4] | Gong J H, Yue Y J, Zhu J, et al. Impacts of the Wenchuan Earthquake on the Chaping River Upstream Channel Change[J]. <em>Int J Remote Sens</em>, 2012, 33(12):3907-3929 |
| [5] | Yao X,Tham L G, Dai F C. Landslide Susceptibility Mapping Based on Support Vector Machine:A Case Study on Natural Slopes of Hong Kong, China[J]. <em>Geomorphology</em>, 2008, 101:572-582 |
| [6] | Wu X, Ren F,Niu R. Landslide Susceptibility Assessment Using Object Mapping Units, Decision Tree, and Support Vector Machine Models in the Three Gorges of China[J]. <em>Environ Earth Sci</em>, 2014, 71:4725-4738 |
| [7] | Kennedy J,Eberhart R C. Particle Swarm Optimization[C]. IEEE Int Conf Neural Netw, New York, 1995 |
| [8] | Pradhan B, Lee S. Landslide Susceptibility Assessment and Factor Effect Analysis:Backpropagation Artificial Neural Networks and Their Comparison with Frequency Ratio and Bivariate Logistic Regression Modeling[J]. <em>Environ Modell Softw</em>, 2010, 25:747-759 |
| [9] | Nandi A. A Application of Logistic Regression Model for Slope Instability Prediction in Cuyahoga River Watershed, Ohio, USA[J]. <em>Georisk</em>, 2008, 2(1):16-27 |
| [10] | Ballabio C, Sterlacchini S. Support Vector Machines for Landslide Susceptibility Mapping:The Staffora River Basin Case Study, Italy[J]. <em>Math Geosci</em>, 2012, 44:47-70 |
| [11] | Vapnik V. Nature of Statistical Learning Theory[M]. New York:Wiley, 1995 |
| [12] | Pradhan B. Landslide Susceptibility Mapping of a Catchment Area Using Frequency Ratio, Fuzzy Logic and Multivariate Logistic Regression Approaches[J]. <em>J Indian Soc Remote Sens</em>, 2010,38(2):301-320 |
| [13] | Zare M, Pourghasemi H R, Vafakhah M, et al. Landslide Susceptibility Mapping at Vaz Watershed (Iran) Using an Artificial Neural Network Model:A Comparison Between Multilayer Perceptron (MLP) and Radial Basic Function (RBF) Algorithms[J]. <em>Arab J Geosci</em>, 2013, 6(8):2873-2888 |
| [14] | Pradhan B. A Comparative Study on the Predictive Ability of the Decision Tree, Support Vector Machine and Neuro-Fuzzy Models in Landslide Susceptibility Mapping Using GIS[J]. <em>Comput Geosci</em>, 2013, 51:350-365 |
| [15] | Wu Xueling, Ren Fu, Niu Ruiqing, et al. Landslide Spatial Prediction Based on Slope Units and Support Vector Machines[J]. <em>Geomatics and Information Science of Wuhan University</em>, 2013,38(12):1499-1503(武雪玲, 任福, 牛瑞卿, 等. 斜坡单元支持下的滑坡易发性评价支持向量机模型[J]. 武汉大学学报·信息科学版, 2013,38(12):1499-1503) |
| [16] | Bui D T, Lofman O, Revhaug I, et al. Landslide Susceptibility Analysis in the Hoa Binh Province of Vietnam Using Statistical Index and Logistic Regression[J]. <em>Nat Hazards</em>, 2011, 59:1413-1444 |
| [17] | Wu Xueling, Ren Fu, Niu Ruiqing. Spatial Intelligent Prediction of Landslide Hazard Based on Multi-source Data in Three Gorges Reservoir Area[J]. <em>Geomatics and Information Science of Wuhan University</em>, 2013,38(8):963-968(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) |
| [18] | Xu C, Dai F C, Xu X W, et al. GIS-Based Support Vector Machine Modeling of Earthquake-Triggered Landslide Susceptibility in the Jianjiang River Watershed, China[J]. <em>Geomorphology</em>, 2012, 145:70-80 |
| [19] | Chen Deji, Man Zuowu. The Research and Demonstration of Some Major Geological Problems of Three Gorges Project[J]. <em>Engineering Sciences</em>, 2011, 13(7):43-50(陈德基, 满作武. 三峡工程几个重大地质问题的研究与论证[J]. 中国工程科学, 2011, 13(7):43-50) |
| [20] | Zheng Shouren. Some Considerations on Trial Impoundment Operation of Three Gorges Project at 175 m Water Level[J]. <em>Yangtze River</em>, 2010, 41(8):1-4(郑守仁. 三峡工程试验性蓄水175 m水位运行的相关问题[J]. 人民长江, 2010, 41(8):1-4) |
