Prediction of groundwater level in landslide using multivariable PSO-SVM model" /> 多变量PSO-SVM模型预测滑坡地下水位
Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)
地球科学     
多变量PSO-SVM模型预测滑坡地下水位
黄发明1, 殷坤龙2, 张桂荣3, 唐志政2, 张俊2
1.中国地质大学（武汉） 地质调查研究院,湖北 武汉 430074；2.中国地质大学（武汉） 工程学院,湖北 武汉 430074；3.南京水利科学研究院,江苏 南京 210029
Prediction of groundwater level in landslide using multivariable PSO-SVM model
HUANG Fa-ming1, YIN Kun-long2, ZHANG Gui-rong3, TANG Zhi-zheng2, ZHANG Jun2
1. Geological Survey,China University of Geosciences,Wuhan 430074, China； 2. Faculty of Engineering, China University of Geosciencse, Wuhan 430074, China； 3. Nanjing Hydraulic Research Institute,Nanjing 210029,China
 全文: PDF(2229 KB)   HTML
摘要：

为了预测滑坡地下水位并揭示其与气温、降雨以及库水位等变量间的动态响应关系,提出基于多变量混沌理论的粒子群-支持向量机（PSO-SVM）模型.该模型采用定性分析和灰关联定量分析法确定各因素对地下水位的作用关系并重构多变量相空间.利用SVM模型对每月监测地下水位值进行预测,并采用PSO算法克服SVM模型参数选取困难的缺点,最后对预测结果进行对比分析.以三峡库区白家包滑坡为例进行分析,并将分析结果与单变量PSO-SVM模型相比较,结果表明：多变量PSO-SVM模型的预测结果比较理想,精度高于单变量PSO-SVM模型,可以真实地反映地下水位系统发展演化的本质特征.
Abstract:

A particle swarm optimization-support vector machine (PSO-SVM) model was introduced in order to forecast the groundwater level and reveal the dynamic response relationship between groundwater level and its impact factors. The PSO-SVM model was based on multivariate phase space reconstruction. The impact of various factors on the groundwater level was determined by qualitative analysis and grey relational analysis. The multivariate phase space reconstruction theory was applied to groundwater level time series and its influencing factors. The SVM model was established to predict the groundwater level, and PSO algorithm was used to select the optimal parameters of the SVM model. Finally, with Baijiabao landslide in the Three Geoger Reservoir, for example, the presented model was compared with the univariate PSO-SVM model. Results showed that the prediction accuracy of the proposed model was higher than that of the univariate PSO-SVM model. The proposed model can truly reflect the essential characteristics of groundwater level system evolution.
出版日期: 2015-06-01
:  P 694  
基金资助:

中国地质调查局县域地质灾害风险管理研究资助项目（1212011220173）；国家自然科学基金资助项目（41240023,41302230）
通讯作者: 殷坤龙,男，教授     E-mail: yinklong@163.com
作者简介: 黄发明（1988—）,男,博士生,从事滑坡灾害预测研究工作.E-mail：huang1503518@sina.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

黄发明, 殷坤龙, 张桂荣, 唐志政, 张俊. 多变量PSO-SVM模型预测滑坡地下水位[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2015.06.027.

HUANG Fa-ming, YIN Kun-long, ZHANG Gui-rong, TANG Zhi-zheng, ZHANG Jun.

Prediction of groundwater level in landslide using multivariable PSO-SVM model
. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2015.06.027.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2015.06.027    或    http://www.zjujournals.com/eng/CN/Y2015/V49/I6/1193

［1］ 荣冠,王思敬,王恩志,等.强降雨下元磨公路典型工程边坡稳定性研究［J］.岩石力学与工程学报, 2008, 27(4)： 704-711.
RONG Guan, WANG Si-jing, WANG En-zhi, et al.Stability analysis of yuanmo high way slope under intensive rainfall ［J］. Chinese Journal of Rock Mechanics and Engineering, 2008, 27(4)： 704-711.
［2］ 姜晨光,李少红,贺勇,等.地下水位变化与库岸滑坡体稳定性关系的研究［J］.岩土力学，2008，28（增刊）: 403-406.
JIANG Chen-Guang, LI Shao-hong,HE Yong, et al.Research on relations between bank stability of a reservoir and variations of groundwater level［J］.Rock and Soil Mechanics, 2008， 28(Supple.)：403-406.
［3］ 张桂荣,程伟.降雨及库水位联合作用下秭归八字门滑坡稳定性预测［J］.岩土力学,2011,32(增刊1)： 476-482.
ZHANG Gui-rong,CHENG Wei.Stability prediction for Bazimen landslide of Zigui County under the associative action of reservoir water lever fluctuations and rainfall infiltration ［J］.Rock and Soil Mechanics, 2011,32(supple.1)： 476-482.
［4］ SIEK M, SOLOMATINE D P. Nonlinear chaotic model for predicting storm surges ［J］.Nonlinear Processes in Geophysics,2010,17(5)： 405-420.
［5］ 金菊良,杨晓华,金保明,等.基于遗传算法的地下水位动态预测双线性模型［J］.水科学进展, 2001,12(3)： 361-366.
JIN Ju-liang,YANG Xiao-hua,JIN Bao-ming,et al.A bilinear time series model based on genetic algorithm for predicting groundwater level regime ［J］.Advances in Water Science,2001,12(3)： 361-166.
［6］ 杨忠平,卢文喜,李平.时间序列模型在吉林西部地下水动态变化预测中的应用［J］.水利学报,2005,32(12)：1475-1479.
YANG Zhong-ping,LU Wen-xi,LI Ping. Application of time series model to predict groundwater regime［J］.Journal of Hydraulic Engineering, 2005,32(12)： 1475-1479.
［7］ MAITI S, TIWARI R K. A comparative study of artificial neural networks, Bayesian neural networks and adaptive neuro-fuzzy inference system in groundwater level prediction ［J］.Environmental Earth Sciences,2014,71(7)： 3147-3160.
［8］ 赵敏,樊印海,孙辉.电力推进船舶电力负荷的多变量混沌局部预测［J］.系统仿真学报,2008,20(11)： 2797-2805.
ZHAO Min,FAN Yin-hai,SUN Hui.Chaos local forecasting of electric propulsion ship power load on multivariate time series［J］.Journal of System Simulation,2008,20(11)： 2797-2805.
［9］ 彭令,牛瑞卿,叶润清,等.基于进化支持向量机的滑坡地下水位动态预测［J］.中南大学学报：自然科学版, 2012,43(12)： 4788-4795.
PENG Ling,NIU Rui-qing,YE Run-qin, et al.Prediction of ground water level in landslides based on genetic-support vector machine ［J］.Journal of Central South University：Science and Technology, 2012,43(12)： 4788-4795.
［10］ 刘卫林,董增川,陈南祥,等.基于多变量相空间重构的地下水动态神经网络预测模型［J］.河海大学学报：自然科学版,2008, 36(1)： 14-18.
LIU Wei-lin,DONG Zeng-chuan,CHEN Nan-xiang,et al.Neural network model for groundwater prediction based on multivariate phase space reconstruction［J］.Journal of Hohai University： Natural Sciences, 2008, 36(1)： 14-18.
［11］ 王智磊,孙红月,刘永莉,等.降雨与边坡地下水位关系的时间序列分析［J］.浙江大学学报：工学版,2011, 45(7)： 1031-1037.
WANG Zhi-lei, SUN Hong-yue, LIU Yong-li, et al.Time series analysis about groundwater level in slope and rainfall［J］.Journal of Zhejiang University:Engineering Science,2011,45(7)： 1031-1037.
［12］ 王新迎,韩敏.基于极端学习机的多变量混沌时间序列预测［J］.物理学报,2012,61(8)： 080507.
WANG Xin-ying, HAN Min.Multivariate chaotic time series prediction based on extreme learning machine［J］.Acta Physica Sinica,2012,61(8)： 080507.
［13］ ZHOU Y D,MA H,LV W Y,et al.Prediction of the chaotic time series using multivariate local polynomial regression ［J］. Acta Physica Sinica,2007,56 (12)： 6809-6814.
［14］ HAN M,WANG Y. Analysis and modeling of multivariate chaotic time series based on neural network ［J］.Expert Systems with Applications,2009,36 (2)： 1280-1290.
［15］ 马广,陈宏金.基于农机化投入影响因素的灰关联分析［J］.浙江大学学报：农业与生命科学版,2005,31(6)：812-815.
MA Guang,CHEN Hong-jin. Grey correlation analysis on influence factors of agricultural mechanization investment ［J］. Journal of Zhejiang University: Agriculture and Life Sciences, 2005,31(6)： 812-815.
［16］ VACCARI D A, Multivariate polynomial regression for identification of chaotic time series［J］.Mathematical and Computer Modeling of Dynamical Systems,2007, 13(4)： 395-412.
［17］ 王德明,王莉,张广明,等.基于遗传BP神经网络的短期风速预测模型［J］.浙江大学学报：工学版,2012,46(5)：837-841.
WANG De-ming,WANG Li,ZHANG Guang-ming, et al.Short-term wind speed forecast model for wind farms based on genetic BP neural network ［J］. Journal of Zhejiang University:Engineering Science, 2012, 46(5)： 837-841.
［18］ FANG F, VOLTERRA adaptive real-time prediction of multivariate chaotic time series ［J］.Systems Engineering and Electronics, 2009, 31(10)： 2476-2479.
［19］ 彭令,牛瑞卿,吴婷.时间序列分析与支持向量机的滑坡位移预测［J］.浙江大学学报：工学版,2013, 47(9)： 1672-1679.
PENG Ling,NIU Rui-qing,WU Ting.Time series analysis and support vector machine for landslide displacement prediction ［J］.Journal of Zhejiang University：　Engineering Science,2013,47(9)： 1672-1679.
［20］ 郑丹丹,张培勇,吕冬明,等.基于粒子群优化算法的有用时钟偏差规划 ［J］.浙江大学学报：工学版,2010,44(4)： 665-669.
ZHENG Dan-dan,ZHANG Pei-yong,LV Dong-ming,et al.Useful clock skew scheduling based on particle swarm optimization ［J］.Journal of Zhejiang University: Engineering Science, 2010, 44(4)： 665-669.
［21］ ALAN W,JACK B S,HARRYL S,et al.Determining Lyapunov exponents from a time series ［J］. Physica D, 1986, 16(2)： 285-371.
［22］ 雷绍兰,孙才新,周湶,等.电力短期负荷的多变量时间序列线性回归预测方法研究［J］.中国电机工程学报,2006,26(2)： 25-29.
LEI Shao-lan,SUN Cai-xin,ZHOU Quan,et al.The research of local linear model of short-term electrical load on multivariate time series ［J］.Proceedings of the CSEE,2006,26(2)： 25-29.
［23］ CORTES C,VAPNIK V. Support-vector networks ［J］. Machine Learning, 1995,20(3)： 273-297.
No related articles found!