[1]张研,吴康丽,邓雪沁,等.基于相关向量机的蒋家沟泥石流平均流速预测模型[J].自然灾害学报,2019,28(06):146-153.[doi:10.13577/j.jnd.2019.0616]
 ZHANG Yan,WU Kangli,DENG Xueqin,et al.Prediction model of Jiangjiagou debris flow average velocity based on relevance vector machine[J].,2019,28(06):146-153.[doi:10.13577/j.jnd.2019.0616]
点击复制

基于相关向量机的蒋家沟泥石流平均流速预测模型
分享到:

《自然灾害学报》[ISSN:/CN:23-1324/X]

卷:
28
期数:
2019年06期
页码:
146-153
栏目:
出版日期:
2019-12-28

文章信息/Info

Title:
Prediction model of Jiangjiagou debris flow average velocity based on relevance vector machine
作者:
张研12 吴康丽2 邓雪沁2 王伟2
1. 广西岩土力学与工程重点实验室, 广西 桂林 541004;
2. 桂林理工大学 土木与建筑工程学院, 广西 桂林 541004
Author(s):
ZHANG Yan12 WU Kangli2 DENG Xueqin2 WANG Wei2
1. Guangxi Key Laboratory of Geomechanics and Geotechnical Engineering, Guilin 541004, China;
2. School of Civil and Architecture Engineering, Guilin University of Technology, Guilin 541004, China
关键词:
相关向量机泥石流平均流速预测灾害
Keywords:
relevance vector machinedebris flowaverage velocitypredictiondisaster
分类号:
P642.23;X9;X43
DOI:
10.13577/j.jnd.2019.0616
摘要:
泥石流是我国常见的一种地质灾害,泥石流的平均流速是泥石流灾害防治的重要参数之一,准确的预测泥石流平均流速对灾害预防具有重要意义。本文建立基于相关向量机的蒋家沟泥石流平均流速预测模型,通过与蒋家沟泥石流平均流速的支持向量机、BP神经网络模型预测结果对比,验证该模型预测精度;同时采用平均相对误差和均方差2个指标评价各个模型的整体性能和稳定情况。结果表明,与实测值相比,相关向量机预测最大相对误差仅为2.02%,平均相对误差为0.64%,均方差为0.06,远低于BP神经网络模型和支持向量机模型的预测结果。由此可知,本文提出的基于相关向量机的蒋家沟泥石流平均流速预测模型效果明显优于其他2种模型,且预测结果更为准确,模型整体性能和稳定情况较好,为泥石流平均流速获取提供一条新途径。
Abstract:
Debris flow is a common geological disaster in China, the average velocity of debris flow is one of the important parameters for the prevention and control of debris flow disaster. Predicting the average velocity of debris flow accurately has a great significance for disaster prevention. In this paper, a prediction model is built for average velocity of Jiangjiagou debris flow based on relevance vector machine. The prediction accuracy of the model is verified by comparing the prediction results with the model based on support vector machine and BP neural network. Average relative error and mean square error are used to evaluate the whole performance and stability of each model. The results show that compared with the measured values, the maximum relative error of relevance vector machine prediction is only 2.02%, the average relative error is 0.64%, the mean square error is 0.06, far lower than the BP neural network model and the support vector machine model prediction results. In conclusion, the prediction model based on relevance vector machine proposed in this paper is obviously better than the other two models. The prediction results are more accurate while the model is more stable, so the relevance vector machine provides a new way to obtain the average velocity of debris flow.

参考文献/References:

[1] 王毅, 唐川, 李为乐, 等.基于GIS的模糊数学模型在泥石流敏感性评价中的应用[J].自然灾害学报, 2017, 26(1):19-26. WANG Yi, TANG Chuan, LI Weile, et al. Application of GIS-based fuzzy mathematics model to sensitivity evaluation of debris flow[J]. Journal of Natural Disasters, 2017,26(1):19-26.(in Chinese)
[2] 沈简, 饶军, 傅旭东. 基于模糊综合评价法的泥石流风险评价[J]. 灾害学, 2016, 31(2):171-175. SHEN Jian, RAO Jun, FU Xudong. Assessment on debris flow risk based on fuzzy comprehensive evaluation method[J]. Journal of Catastrophology, 2016, 31(2):171-175. (in Chinese)
[3] 舒和平, 齐识, 宁娜, 等.甘肃省南部武都区泥石流灾害风险评价研究[J].自然灾害学报, 2016, 25(6):34-41 SHU Heping, QI Shi, NING Na, et al. Risk assessment of debris flow disaster:a case study of Wudu District in the south of Gansu Province, China[J]. Journal of Natural Disasters, 2016, 25(6):34-41. (in Chinese)
[4] 杨月巧, 胡俊锋, 郗蒙浩.基于灰色关联法的舟曲泥石流灾害影响因素分析[J].自然灾害学报, 2011, 20(3):139-144. YANG Yueqiao, HU Junfeng, XI Menghao. Analysis of influence factors of debris flow disaster in Zhouqu based on grey relevance method[J].Journal of Natural Disasters, 2011, 20(3):139-144.(in Chinese)
[5] 刘丽, 陈洪凯.泥石流运动力学研究现状及趋势[J].重庆交通大学学报:自然科学版, 2010, 29(2):233-239. LIU Li, CHEN Hongkai. Research status and trend about dynamic of debris flow[J]. Journal of Chongqing Jiaotong University(Natural Science), 2010, 29(2):233-239. (in Chinese)
[6] 吴积善, 康志成, 田连权, 等. 云南蒋家沟泥石流观测研究[M]. 北京:科学出版社, 1990:118-127. WU Jishan, KANG Zhicheng, TIAN Lianquan, et al. Observation of Debris Flow in Jiangjiagou, Yunnan Province[M]. Beijing:Science Press, 1990:118-127. (in Chinese)
[7] 程尊兰, 刘雷激.西藏古乡沟泥石流流速[J]. 山地研究, 1997, 15(4):293-295. CHENG Zunlan, LIU Leiji. Debris flow velocity in Guxianggou, Tibet[J]. Journal of Mountain Research, 1997, 15(4):293-295.(in Chinese)
[8] 中国科学院兰州冰川冻土研究所, 甘肃省交通科学研究所.甘肃泥石流[M].北京:人民交通出版社, 1982:27-43. Lanzhou Institute of Glacier and Permafrost, Chinese Academy of Sciences, Gansu Institute of Transportation Science. Gansudebris Flow[M]. Beijing:People’s Communications Press, 1982:27-43. (in Chinese)
[9] 黄芮.基于PPA的乌东德水电站库区泥石流流速模型建立与计算[D].长春:吉林大学, 2011. HUANG Ri. Model Building and Calculation of The Debris Flow Rate in Dam Site of Wudongde Hydropower Station Based on PPA[D]. Changchun:Jilin University, 2011. (in Chinese)
[10] 柴春岭, 陈守煜.模糊优选神经网络模型在泥石流平均流速预测中的应用研究[J].大连理工大学学报, 2008, 48(6):887-891. CHAI Chunling, CHEN Shouyu. Research on application of fuzzy optimization neural network model to debris flow average velocity forecasting[J]. Journal of Dalian University of Technology, 2008, 48(6):887-891. (in Chinese)
[11] 韩冰.泥石流平均流速的PSO-SVM预测模型[J]. 河北地质大学学报, 2018, 41(2):27-30. HAN Bing. Forecast for average velocity of debris flow based on PSO-SVM method[J]. Journal of Hebei GEO University, 2018, 41(2):27-30. (in Chinese)
[12] 徐黎明, 王清, 陈剑平, 等. 基于BP神经网络的泥石流平均流速预测[J]. 吉林大学学报(地球科学版), 2013, 43(1):186-191. XU Liming, WANG Qing, CHEN Jianping, et al. Forcast for average velocity of debris flow based on BP neural network[J]. Journal of Jilin University(Earth Science Edition), 2013, 43(1):186-191. (in Chinese)
[13] 魏振磊, 孙红月, 潘攀, 等.泥石流平均流速的MLS模型预测[J].自然灾害学报, 2016, 25(4):56-61. WEI Zhenlei, SUN Hongyue, PAN Pan, et al. Forecast for average velocity of debris flow based on MLS method[J]. Journal of Natural Disasters, 2016, 25(4):56-61. (in Chinese)
[14] TIPPING M E. The relevance vector machine[J]. Advances in Neural Information Processing Systems, 2001(12):652-658.
[15] BISHOP C M, TIPPING M E. Variational relevance vector machines[C]//Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence. San Francisco, CA, USA, 2000:46-53.
[16] TIPPING M E. Sparse bayesian learning and the relevance vector machine[J]. Journal of Machine Learning Research, 2001, 1(3):211-244
[17] 赵春晖, 张燚. 相关向量机分类方法的研究进展与分析[J]. 智能系统学报, 2012, 7(4):294-301. ZHAO Chunhui, ZHANG Yi. Research progress and analysis on methods for classification of RVM[J]. CAAI Transactions on Intelligent Systems, 2012, 7(4):294-301. (in Chinese)
[18] 杨国鹏, 周欣, 余旭初. 稀疏贝叶斯模型与相关向量机学习研究[J]. 计算机科学, 2010, 37(7):225-228. YANG Guopeng, ZHOU Xin, YU Xuchu. Research on sparse bayesian model and relevance vector machine[J]. Computer Science, 2010, 37(7):225-228. (in Chinese)
[19] 赵倩倩. 相关向量机的改进及应用研究[D]. 天津:河北工业大学, 2014. ZHAO Qianqian. Improvement on Relevance Vector Machine and Its Applications[D].Tianjin:Hebei University of Technology, 2014. (in Chinese)
[20] 徐永年. 崩塌土流动化机理及泥石流冲淤特性的实验研究[D]. 北京:中国水利水电科学研究院, 2001. XU Yongnian.Study on Flow Mechanism for Avalanche Soils and Scour and Silting Characteristics of Debris Flows[D]. Beijing:China Institute of Water Resources and Hydropower Research, 2001. (in Chinese)
[21] 于国强, 张茂省, 王根龙, 等. 支持向量机和BP神经网络在泥石流平均流速预测模型中的比较与应用[J]. 水利学报, 2012, 43(S2):105-110. YU Guoqiang, ZHANG Maosheng, WANG Genlong, et al. Application and comparison of prediction mosels of support vector mechines and back-propagation artificial neural network for debris flow average velocity[J]. Journal of Hydraulic Engineering, 2012, 43(S2):105-110. (in Chinese)
[22] 洪正修.泥石流流速公式探讨[J].中国地质灾害与防治学报, 1996(1):26-33,25. HONG Zhengxiu. Discussion of debris flow velocity formula[J]. The Chinese Journal of Geological Hazard and Control, 1996(1):26-33,25.(in Chinese)

相似文献/References:

[1]聂娟,范一大,邓磊,等.山洪灾害雷达遥感灾情评估技术研究与应用[J].自然灾害学报,2010,19(03):105.
 NIE Juan,FAN Yi-da,DENG Lei,et al.Research and application of torrential flood loss assessment based on radar remote sensing technology[J].,2010,19(06):105.
[2]刘希林,陈宜娟.泥石流点密度和面密度对区域泥石流危险度的影响——对比研究[J].自然灾害学报,2011,20(02):036.
 LIU Xi-lin,CHEN Yi-juan.Influence of debris flow spot and area densities on regional hazardousness of debris flow:a comparative study[J].,2011,20(06):036.
[3]杨成林,陈宁生,李战鲁.汶川地震次生泥石流形成模式与机理[J].自然灾害学报,2011,20(03):031.
 YANG Cheng-lin,CHEN Ning-sheng,LI Zhan-lu.Formation mode and mechanism fordebris flow induced by Wenchuan earthquake[J].,2011,20(06):031.
[4]杨月巧,胡俊锋,郗蒙浩.基于灰色关联法的舟曲泥石流灾害影响因素分析[J].自然灾害学报,2011,20(03):139.
 YANG Yue-qiao,HU Jun-feng,XI Meng-hao.Analysis of influence factors of debris flow disaster in Zhouqu based on grey relevance method[J].,2011,20(06):139.
[5]李倩,黄勇.新疆天山公路泥石流风险评价研究[J].自然灾害学报,2011,20(04):154.
 LI Qian,HUANG Yong.Risk evaluation of debris flow for Tianshan Highway in Xinjiang[J].,2011,20(06):154.
[6]梁专明.新化县水车镇泥石流灾害研究[J].自然灾害学报,2011,20(05):032.
 LIANG Zhuan-ming.Study on debris flow disaster in Shuiche Town, Xinhua County[J].,2011,20(06):032.
[7]李朝安,胡卸文,王良玮.山区铁路沿线泥石流泥位自动监测预警系统[J].自然灾害学报,2011,20(05):074.
 LI Chao-an,HU Xie-wen,WANG Liang-wei.Automatic monitoring and early warning system of mud-position of debris flow along railway line in mountainous area[J].,2011,20(06):074.
[8]陈春光,姚令侃,杨庆华,等.基于堰流理论的泥石流堵河模型研究[J].自然灾害学报,2012,21(06):131.
 CHEN Chunguang,YAO Lingkan,YANG Qinghua,et al.Study of river-blocking due to debris flow based on weir flow theory[J].,2012,21(06):131.
[9]耿慧辉,贾景超.都江堰龙池镇三神公泥石流灾害特征[J].自然灾害学报,2012,21(06):136.
 GENG Huihui,JIA Jingchao.Features of Sanshengong debris flow hazard in Longchi Town of Dujiangyan City[J].,2012,21(06):136.
[10]冯杭建,唐小明,周爱国.浙江省泥石流与降雨历时关系研究及应用检验[J].自然灾害学报,2013,22(01):159.
 FENG Hangjian,TANG Xiaoming,ZHOU Aiguo.Study on relationship between rainfall duration and occurrence of debris flow in Zhejiang Province and its application examination[J].,2013,22(06):159.

备注/Memo

备注/Memo:
收稿日期:2019-03-02;改回日期:2019-05-17。
基金项目:国家自然科学基金项目(51409051)
作者简介:张研(1983-),男,副教授,博士,主要从事岩土体稳定性分析研究.E-mail:yanzi22858@126.com
更新日期/Last Update: 1900-01-01